Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 138 appraisals
Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association
Artificial Intelligence Tools for Gastrointestinal Research: A Practical Guide
Artificial intelligence (AI) tools, including large language models (LLMs) such as ChatGPT, Claude, and Gemini, are increasingly used in biomedical research. However, practical guidance for integrating these tools into the manuscript writing workflow remains limited. This narrative review provides a structured, step-by-step guide for gastrointestinal (GI) researchers and clinicians seeking to use AI responsibly across the stages of manuscript preparation.
2 Aug 2026
Read appraisal →Artificial intelligence in medicine
Artificial intelligence language models for medical text analysis: A systematic review
Medical text records serve as essential repositories of patient information, providing a foundation for informed clinical decision-making, accurate diagnosis, reliable prognosis, and effective treatment planning. Recent advancements in Artificial Intelligence (AI), particularly in Natural Language Processing (NLP) and Machine Learning (ML), have positioned AI-driven language models as powerful tools for analyzing, classifying, and generating medical textual data. In this systematic literature review, an initial search retrieved 548 records published between 1 January 2000 and 1 July 2024. After rigorous screening based on predefined inclusion and exclusion criteria, 22 original research articles were included. The review highlights substantial progress in applying advanced architectures such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-trained Transformers (GPT) to medical text processing tasks. These models consistently outperform conventional NLP and ML approaches, achieving superior results in disease classification, automated clinical documentation, and predictive analytics. However, critical challenges persist, including the limited availability of clinically validated datasets, variability in data preprocessing protocols, insufficient external validation, and the lack of interpretable AI frameworks, all of which collectively hinder clinical trust and large-scale adoption. Future research should prioritize the development of hybrid AI systems that integrate multimodal data sources (text, imaging, and structured records), incorporate explainable AI mechanisms, and adhere to standardized reporting frameworks. Addressing these methodological gaps will be pivotal in enhancing the reliability, clinical applicability, and impact of AI language models, thereby advancing evidence-based medicine, personalized treatment strategies, and overall patient care.
2 Aug 2026
Read appraisal →Surgery
Artificial intelligence to revolutionize surgical decision-making is still just around the corner.
Medical artificial intelligence, especially large language models, has engendered both excitement and unease across the medical community, promising improved surgical diagnostic accuracy, perioperative decision-making, and patient safety amidst concerns of considerable bias and its implications on the future of human expertise. The evolution of artificial intelligence clinical decision support originated in the surgical field through early systems like AAPHelp, which leveraged Bayesian reasoning to diagnose acute abdominal pain. Despite the initial promise of artificial intelligence clinical decision support, attempts to develop more robust diagnostic tools largely fell short in the 1980s, with instruments unable to adequately diagnose and manage complex presentations, a lack of transparency in their decision-making processes, and limitations in scope. It was not until the 2010s that clinical decision support began to show renewed potential as a meaningful adjunct in surgical practice, largely driven by advancements in machine learning techniques and wider access to large clinical data sets. New artificial intelligence models, particularly those utilizing large language models, now demonstrate impressive capabilities, from predicting the risk of postoperative complications for individual patients to streamlining clinical documentation and beyond. However, challenges persist regarding transparency, bias, reliability, and integration into clinical workflows. Despite these hurdles, artificial intelligence-based tools like large language models represent an exciting new chapter in surgical decision-making. Built on a long history of clinical decision support systems in surgery, these technologies hold great promise to meaningfully augment surgical practice and improve care for patients.
1 Aug 2026
Read appraisal →JMIR formative research
Teaching Health Informatics in a Skills-First Era: A Curriculum Mapping Approach Aligned With Workforce Demand
Academic programs in health informatics have been urged to align curricula with evolving workforce needs to better prepare graduates for practice. Such alignment supports workforce readiness, addresses talent shortages, and reduces onboarding burdens for employers. Although employers increasingly seek graduates who can demonstrate applied skills and competencies beyond textbook knowledge, academic programs continue to face challenges in translating workforce demand into curricular design. This Viewpoint is directed at health informatics program faculty and administrators and presents the author's perspective on a skills-first curriculum mapping approach aligned with current industry needs. The author argues that connecting program-level outcomes, course objectives, and learning activities to industry-recognized competencies strengthens workforce readiness while maintaining academic rigor. Drawing on the literature on competency-based education, workforce development, and health informatics training, this paper argues for intentional curriculum design that integrates transferable skills, stackable credentials, and stakeholder engagement. The key messages are as follows: (1) workforce demand should anchor curriculum design in health informatics programs, (2) curriculum mapping is a practical mechanism for operationalizing skills-first alignment, and (3) credential integration and continuous congruency evaluation support long-term program sustainability. This approach positions health informatics education to remain responsive, scalable, and aligned with the rapidly evolving professional landscape.
31 July 2026
Read appraisal →PloS one
Pronunciation assessment in foreign language learning: Reliability and scoring bias in human-generative AI evaluation
This study examines the reliability and scoring bias of generative AI (Gen-AI)-based pronunciation assessment compared with human raters, addressing whether AI-generated scores can be trusted in real educational settings. Sixty students participated in a 12-week program. A total of 180 pronunciation samples were evaluated across eight subcomponents (individual phonemes, stress, rhythm, intonation, linking, reduction, fluency, and clarity) by three standardized human raters and Gen-AI using the same 7-point rubric. Quantitative analyses (intraclass correlation coefficients, paired-samples t-tests, and Pearson correlations) assessed reliability and bias, while semi-structured interviews with raters provided explanatory qualitative insights. Gen-AI demonstrated moderate reliability with human raters across most components, showing the highest agreement in fluency and the weakest in individual phonemes. However, Gen-AI consistently assigned significantly higher scores than human raters across all subcomponents. Qualitative findings revealed that discrepancies originated from Gen-AI's limited discriminative power, systematic flaws in handling missing data, decontextualized scoring approach, lack of sensitivity to L1 interference, and inability to interpret pragmatic context. While Gen-AI cannot fully replace human expertise, it can function as a complementary tool for formative assessment and autonomous practice. A hybrid assessment model integrating Gen-AI's efficiency with human raters' contextual and interpretive insights is recommended for effective foreign language pronunciation education.
31 July 2026
Read appraisal →PloS one
Evaluating the cultural alignment of multilingual LLMs in typical Japanese workplace scenarios
While current evaluations of LLM cultural alignment predominantly rely on static benchmarks in Western contexts, their ability to navigate generative, high-context socio-pragmatic demands in non-Western environments remains critically underexplored. This study investigates how multilingual LLMs adapt to the Japanese workplace-a stringent stress-test environment characterized by strong high-context communication norms and rigid honorific conventions-using Hofstede's six cultural dimensions as a heuristic framework. We evaluated five state-of-the-art LLMs (LLM-jp, Phi, Llama, Qwen, and GLM) through a large-scale crowdsourced human evaluation. Based on 1,718 valid evaluator sessions, native Japanese raters assessed model outputs to generate a holistic Japanese Workplace Cultural Alignment Score (JWCAS). To dissect the underlying communicative strategies, we paired this with a three-layer diagnostic sub-score analysis (Linguistic Form, Socio-Cultural Values, and Social Action). Our results reveal that leading multilingual models (Phi and GLM) achieved overall JWCAS scores comparable to, or significantly higher than, the native Japanese model (LLM-jp). Crucially, our sub-score analysis demonstrates that holistic evaluation metrics can obscure deep pragmatic deficits: while LLM-jp overfits to surface-level linguistic politeness (Layer 1), it shows critical weaknesses in socio-cultural values (Layer 2) and context-aware social strategies (Layer 3). In contrast, leading multilingual models demonstrate balanced competence across all layers. These findings suggest that true cultural competence requires moving beyond native linguistic mastery, highlighting the necessity of multi-dimensional diagnostic frameworks for cross-cultural AI alignment.
29 July 2026
Read appraisal →Proceedings of the National Academy of Sciences of the United States of America
Active linking through narratives facilitates associative inference
In daily life, we often draw inferences about novel associations from prior experiences. This ability, associative inference, is thought to be a key process by which memory guides future behavior. Prior studies have typically instructed participants to use narratives or mental imagery to aid memory of object associations. However, these studies have not explicitly tested the role of narratives, leaving an important question: how crucial are narratives in associative inference, and what role might they play? We used a modified associative inference paradigm to answer these questions. Our design factorially combined two factors during associative encoding: use of narratives, and explicitly linking the two objects. Participants separately learned AB and BC object pairs within ABC triads using four sets of instructions: i) generate narratives to link objects together, ii) generate narratives for objects separately, iii) compare perceptual properties of two objects, and iv) describe perceptual properties of objects individually. We tested participants' ability to infer AC associations as a function of encoding strategy. Across two experiments, using narratives to actively link objects produced a robust associative memory advantage that persisted across 1-day delay and remained substantial under more stringent retrieval conditions. This benefit was not attributable to a simple linking effect or to surface-level linguistic similarity between stories. A follow-up experiment revealed that this benefit did not generalize to perceptual memory for individual objects; instead, perceptual encoding facilitated perceptual object memory. These results reveal that deep, extended encoding emphasizing either narrativity or perceptual processing can benefit different aspects of retrieval.
28 July 2026
Read appraisal →Proceedings of the National Academy of Sciences of the United States of America
Race-conscious admissions algorithms and the law.
In recent years, colleges and universities have begun to use machine learning (ML) systems to inform admissions decisions. Meanwhile, in the 2023 case Students for Fair Admissions, Inc. v. President and Fellows of Harvard College, the Supreme Court held that colleges and universities may not make admissions decisions "on the basis of race." These parallel developments-the rise of ML in admissions and the fall of race-based affirmative action-will force educational institutions, and ultimately courts, to confront the difficult question of what it means for ML systems to differentiate "on the basis of race." We begin by mapping the Students for Fair Admissions decision onto different uses of race in predictive AI. We distinguish between "first-order" and "second-order" race consciousness at both the training and predictive phases of machine learning, and we argue that each category of race consciousness raises distinct legal and normative issues. We go on to show that the Students for Fair Admissions decision potentially permits-and even endorses-certain forms of race consciousness. Our analysis is grounded in the observation that the process of developing ML-based systems enables policymakers to calibrate decision making algorithms much more precisely and explicitly in response to specific criticisms of race-conscious affirmative action.
28 July 2026
Read appraisal →International journal of nursing education scholarship
Effect of concept mapping on critical thinking skills in nursing students: a systematic review with meta-analysis
BACKGROUND: Critical thinking (CT) among nursing students is crucial for delivering high-quality nursing care to patients. Concept mapping (CM) is one of the evidence-based pedagogies that helps to improve CT in individuals. OBJECTIVES: The objective of this review and meta-analysis was to evaluate the impact of concept mapping on CT abilities, academic achievement, and clinical skills in nursing students. METHODS: This systematic review and meta-analysis aimed to identify published articles on the effect of CM on CT in nursing students, written in English and published from 2011 to 2024. The articles were sourced from SCOPUS, Web of Science (WoS), ScienceDirect, Google Scholar, and PubMed databases. To ensure a comprehensive and relevant search, the following MeSH terms were used: "Effectiveness" OR "Impact," AND "Concept Mapping," AND "CT," AND "Nursing Student," AND "RCT" OR "Randomized Controlled Trials" OR "Quasi-Experimental." This study used the Cochrane Collaboration's Risk of Bias (RoB) tool and Standardized Mean Difference (SMD) for outcome measurement, with results analyzed using RevMan Web. RESULTS: This study analyzed 14 RCTs and quasi-experimental studies involving 1,747 participants (E=870, C=877). The meta-analysis found that concept mapping enhanced nursing students' CT skills (MD=4.86, 95 % CI [2.16 to 7.56], p=0.0004), academic achievements (MD=3.38, 95 % CI [0.76 to 5.99], p=0.01), and performance in clinical practice (MD=5.94, 95 % CI [3.22 to 8.65], p<0.0001) when compared to routine instructional methods. CONCLUSIONS: CM provides valuable insights into enhancing CT and clinical skills in nursing students, eventually preparing them to become excellent nursing professionals in the healthcare system.
26 July 2026
Read appraisal →PloS one
Enhancing the sustainability of cultural identity in science curricula through artificial intelligence as an innovative educational approach
This study investigates the role of AI as an innovative educational approach in promoting the sustainability of cultural identity within science curricula. To achieve this aim, a qualitative research design was employed, using semi-structured interviews and classroom observations as primary data collection methods. The study sample consisted of forty-seven science teachers from the Al-Qassim and Al-Ahsa regions in Saudi Arabia, selected purposively based on their experience with technology-enhanced instruction. The collected data were analyzed using systematic qualitative procedures involving open and axial coding, which facilitated the emergence of key categories related to AI integration, cultural relevance, and instructional practices. Accordingly, the analytical process is best understood as an inductive thematic qualitative approach rather than a full grounded theory methodology, as it does not include theoretical sampling, data saturation, or iterative cycles of data collection. This clarification ensures methodological transparency and alignment between design and analysis. Findings derived from both teachers' perceptions and classroom observations indicate that AI is not perceived merely as a tool for knowledge transmission, but rather as a supportive instructional mechanism that enables the contextualization of scientific concepts within local cultural settings. In addition, AI-supported instructional practices appear to foster more interactive and collaborative classroom environments, while also contributing to more responsive approaches to assessment. However, it is important to emphasize that these findings are based on teachers' reported perceptions and observed instructional practices rather than direct measurement of student learning outcomes. Despite this limitation, classroom observations suggest that integrating culturally relevant examples, analyzing cultural texts, and designing collaborative, culturally responsive learning activities may enhance student engagement and strengthen their connection to cultural identity within science learning contexts. Overall, the study highlights the potential of AI to bridge scientific knowledge and local cultural heritage in science education. It contributes to the growing body of literature on AI in education by emphasizing its role in fostering culturally responsive pedagogy and enhancing meaningful learning experiences. The study further underscores the importance of providing teachers with targeted professional development in AI integration, developing culturally responsive instructional materials, and designing assessment practices that address both conceptual understanding and cultural dimensions of learning.
24 July 2026
Read appraisal →MedEdPORTAL : the journal of teaching and learning resources
Artificial Intelligence and Large Language Models: A Case-Based, Peer-Teaching Workshop for Preclinical Medical Students
INTRODUCTION: Artificial intelligence tools have rapidly become integrated in health care settings and are quickly affecting medical student education. However, there remains limited formal teaching on such tools in student curricula. This project sought to introduce preclerkship medical students to the basics of large language models and allow them to practice ways to best use these tools to supplement their learning. METHODS: The authors designed, implemented, and evaluated a 60-minute lecture and 100-minute workshop for second-year medical students. The workshop included interactive cases covering various aspects of artificial intelligence use, and some groups were led entirely by student leaders, allowing for peer teaching. RESULTS: One hundred sixty-eight students from Harvard Medical School and Harvard School of Dental Medicine were enrolled in this session. Anonymous pre- and postsession surveys (N = 124 and N = 62, respectively) were collected and compared via unpaired t test assuming unequal variance and showed statistically significant increase in the mean ratings of six 5-point Likert scale questions assessing artificial intelligence-related knowledge/self-efficacy (P < .01) and mixed changes to 5 questions relating to attitudes/behavioral intent. DISCUSSION: Our artificial intelligence and large language model session provides a framework for teaching medical students, early in their educational journey, the basics of these tools. Our session provides interactive exercises to illustrate how best to leverage such tools while also discussing their potential risks. Such education will be important to incorporate into medical student curricula as artificial intelligence technologies grow increasingly common.
23 July 2026
Read appraisal →Journal of medical Internet research
AI-Powered Simulation for Nursing Education: Mixed Methods Systematic Review
BACKGROUND: Traditional simulation-based nursing education is often constrained by high costs, resource intensity, and limited scalability. AI-powered simulations offer dynamic, scalable, and personalized alternatives. However, the empirical evidence regarding their pedagogical effectiveness and learner acceptance remains fragmented. OBJECTIVE: This study aimed to systematically evaluate and synthesize evidence on the effectiveness and learner perceptions of AI-powered simulations in nursing education. METHODS: Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, we systematically searched 11 electronic databases (PubMed, CINAHL, Embase, Web of Science, Cochrane Library, Scopus, SinoMed, CNKI, Wanfang, VIP, and Google Scholar) for studies published between January 2014 and September 2025. Two independent reviewers performed study selection, data extraction, and quality appraisal using design-specific tools (risk of bias 2 tool [RoB 2; Cochrane Bias Methods Group] for randomized controlled trials [RCTs], Risk Of Bias in Nonrandomized Studies of Interventions [ROBINS-I; Cochrane Bias Methods Group] for nonrandomized studies, Mixed Methods Appraisal Tool [MMAT] for mixed methods, Joanna Briggs Institute [JBI] for qualitative, and Agency for Healthcare Research and Quality [AHRQ] for cross-sectional studies). Quantitative data were synthesized narratively, and qualitative findings were integrated using JBI meta-aggregation. A convergent segregated approach with joint display was used to generate meta-inferences. RESULTS: Nineteen studies involving 1253 participants (primarily prelicensure nursing students, with some interdisciplinary cohorts) were included. AI modalities comprised generative AI/large language models (n=7), AI-driven virtual patients/mannequins (n=5), AI-enhanced virtual/mixed reality (n=5), and chatbots (n=2). Three studies were RCTs, 4 were quasiexperimental with control groups, 3 were uncontrolled pre-post studies, 4 were mixed methods, 4 were qualitative, and one was a cross-sectional survey. Quantitative synthesis showed that evidence from RCTs and controlled quasiexperimental studies indicates significant improvements in cognitive knowledge and affective outcomes, including self-efficacy and communication confidence; however, effects on complex psychomotor skills were inconsistent, with one RCT finding AI-assisted simulation inferior to standardized patient simulation. Findings from uncontrolled designs are preliminary. Qualitative meta-aggregation revealed that learners valued safe, repeatable, nonjudgmental practice environments that reduced anxiety and bridged the theory-practice gap. Persistent challenges included technical frustrations, "robotic" interactions, lack of nonverbal cues, and system instability, collectively constituting an "authenticity gap." CONCLUSIONS: AI-powered simulations show promise for developing foundational clinical reasoning and communication skills in nursing education, though the evidence base is limited by the predominance of uncontrolled designs, reliance on self-reported measures, and absence of longitudinal data on skill retention or clinical transfer. Due to current technological limitations in replicating physical and emotional authenticity, AI should be implemented as a complementary tool alongside traditional simulation methods and clinical placements, rather than as a replacement. Future research should prioritize longitudinal outcomes, standardized competency measures, RCTs with active comparators, and implementation strategies addressing technical barriers.
22 July 2026
Read appraisal →Journal of robotic surgery
Transfer of technical skills from virtual reality robotic simulation to non-virtual surgical performance: a systematic review and meta-analysis
Virtual Reality Robotic Surgery Simulators (VR-RSS) are widely used, but their educational value depends on whether skills acquired in virtual reality (VR) training transfer to non-virtual performance. This review evaluated whether VR training improves transferable robotic surgical skills. We searched PubMed, Scopus, Web of Science, and Cochrane from inception to March 3, 2026, for randomized trials evaluating VR robotic simulator training with transfer to non-virtual settings. Screening was performed in Rayyan. Data were extracted systematically, risk of bias was assessed with RoB 2, and random-effects meta-analyses using Hedges' g were conducted in R. Eight trials were included in the review, and seven were included in meta-analysis. Sample sizes ranged from 12 to 35 participants. Although the pooled standardized mean difference (SMD) for global technical skill scores favored the VR training group, it did not reach statistical significance (g = 0.77, 95% CI -0.64-2.18; p = 0.205). Task completion time was also shorter in the VR training group, but this difference was not statistically significant (g = 0.47, 95% CI -0.35-1.29; p = 0.164). This review suggests a potential benefit of VR-based robotic simulation for transferring trained skills to non-VR environments. Future studies should include larger sample sizes and longitudinal assessments using validated metrics to better characterize these trends.
21 July 2026
Read appraisal →Medicine
Exploring the role of generative artificial intelligence in enhancing clinical skills training: A bibliometric analysis
BACKGROUND: Traditional clinical skills training faces challenges such as limited standardized patient resources, high costs of simulation equipment, and restricted opportunities for repeated practice. Generative artificial intelligence (GAI), particularly large language models, has attracted increasing attention as a potential tool for simulation, feedback, and adaptive learning in medical education. However, the research landscape and thematic development of GAI in clinical skills training remain insufficiently mapped. METHODS: A bibliometric analysis was conducted using literature retrieved from the Web of Science Core Collection from January 1, 2011 to April 1, 2025. VOSviewer, the Bibliometrix R package, and CiteSpace were used to analyze publication trends, country and institutional contributions, journal distribution, collaboration networks, keyword co-occurrence, co-cited references, and citation bursts. RESULTS: A total of 322 publications were included. Research activity remained limited before 2023 but increased rapidly thereafter. The United States contributed the largest number of publications, followed by China and India. Major contributing institutions included the National University of Singapore, Gazi University, and Nova Southeastern University. Frequently publishing journals included JMIR Medical Education, Medical Teacher, and BMC Medical Education. Keyword and thematic analyses showed that current research attention is mainly concentrated on ChatGPT, large language models, natural language processing, clinical reasoning simulation, personalized learning, virtual patient interaction, and ethical governance. CONCLUSIONS: Research on GAI in clinical skills training is in an early but rapidly expanding stage, with growing scholarly attention to language-model-driven educational applications and related ethical issues. The bibliometric findings reflect research activity, knowledge structure, and thematic priorities rather than direct evidence of educational effectiveness. Future studies should adopt rigorous empirical designs and standardized evaluation frameworks to assess the effectiveness, safety, and appropriate boundaries of GAI applications in clinical skills training.
19 July 2026
Read appraisal →Science (New York, N.Y.)
AI in scientific publishing: Slower, worse, and more expensive.
There's a saying in the management world, popularized by NASA administrator Daniel Goldin in the 1990s, that the goal of technological improvements is to make products faster, better, and cheaper. Although this strategy had some success in the aerospace industry, the zealots of artificial intelligence (AI) have been making the same argument regarding how it will transform work, claiming that so little human effort will be required that humanity will enter an era of radical abundance, free from disease, drudgery, and danger, among other benefits, leaving society with more time for creative pursuits. But history tells a different story. When machines began to increase productivity during the second industrial revolution, American engineer Frederick Winslow Taylor's The Principles of Scientific Management encouraged corporations to use surveillance to get employees to work harder and longer, an approach that exhausted and discouraged workers and led to the transfer of knowledge and any decision-making from workers to management, while enriching the profits for only those at the top. Yet, it remains foundational to the American economic enterprise. Indeed, scientific publishing is starting to experience some Taylorism with the insertion of AI. Rigorous human checking of AI-generated research papers is creating bottlenecks as publishers strive to maintain the integrity of the scientific record. The challenge is requiring even more human effort, making the whole endeavor slower and more expensive.
17 July 2026
Read appraisal →International journal of medical informatics
Examining user-AI interaction patterns in health-information queries
In this study, we examine how individuals utilize generative artificial intelligence (GAI) when seeking health-related information. Using a dataset of user-GAI chat logs available on Hugging Face, we analyzed real-world interactions in which users posed health-related questions to a generative model. We applied a combination of data and text-analytic methods to categorize these interactions, including supervised machine learning techniques such as Support Vector Machines (SVMs). SVMs were selected for their efficiency and strong performance in high-dimensional text classification tasks, and used to identify recurrent themes in user queries and interactions. We found that users frequently consult AI chatbots for symptom exploration, medical education, mental health support, and general health advice. The findings suggest that GAI tools may not only function as informational resources, but also as preliminary support tools that can shape users' health knowledge and encourage them to seek consultation with medical professionals.
16 July 2026
Read appraisal →Gut and liver
Data-Informed Intuition in Hepatology: Integrating Evidence, Context, and Clinical Reasoning
Artificial intelligence and data-driven models are changing hepatology, but expert clinical judgment remains essential. Liver diseases are complex and evolve over time, requiring reasoning that links numerical data with clinical context. We propose data-informed intuition (DII), a conceptual framework bridging evidence-based medicine with clinical experience and reflective reasoning. Instead of presenting a validated prediction model, it proposes DII as an integrative scaffold for clinical reasoning that can be examined and revised. DII is viewed as a trainable skill that improves with data feedback, not mere guesswork. Clinicians continually calibrate their judgment as patient information accumulates. In hepatology, DII helps interpret disease trajectories, adapt predictive scores to context, and handle uncertainty in liver transplantation, hepatocellular carcinoma, acute liver failure, and related conditions. The DII framework describes eight axes (time, rate, magnitude, pattern, context, causality, integration, and uncertainty) that make visible how data and intuition interact in clinical reasoning. Integrating DII into fellowship training and artificial intelligence-assisted systems could nurture clinicians who combine algorithmic precision with human insight. This perspective summarizes the conceptual basis, clinical uses, and educational value of DII, and outlines both a research agenda for its empirical testing and a path toward data-informed professionalism in hepatology.
15 July 2026
Read appraisal →Scientific reports
Satisfaction with telepsychiatry and mental health stigma among health sciences students in Egyptian universities
Health sciences students have a higher incidence of mental health disorders; however, stigma and barriers have complicated help-seeking. Telepsychiatry may be a solution, but acceptance, satisfaction, and stigma in this population, especially in Egypt, remain unclear. This study aimed to evaluate the levels of satisfaction regarding telepsychiatry, stigma perceived with respect to mental illness, among health sciences students towards mental health services. It also aims to assess sociodemographic factors associated with these outcomes. This was a questionnaire-based cross-sectional study conducted among 799 students from various universities in Egypt. It was conducted between August and November 2025, and the questionnaire involved sociodemographic data, the telepsychiatry satisfaction scale (21 items), and the STIG-9 stigma scale. Data were analyzed using descriptive statistics, chi-square and t-tests, and linear regression, with significance set at p < 0.05. Overall, participants had a mean age of 21.4 years, while 66.8% of participants were female. In total, 24.0% agreed, and 18.4% strongly agreed to being satisfied with telepsychiatry, with a mean total satisfaction score of 67.84/105. The mean STIG‑9 stigma score was 14.44/27. Linear regression identified sociodemographic variables independently associated with satisfaction and stigma; higher stigma was also positively associated with higher satisfaction. In this cohort of Egyptian health sciences students with prior telepsychiatry experience, satisfaction with telepsychiatry was positively associated with perceived stigma. These findings suggest that addressing socio-cultural stigma may support the acceptability of telepsychiatry and improve engagement with digital mental health services in similar student populations.
13 July 2026
Read appraisal →PLoS medicine
How to benchmark medical AI agents
Medical artificial intelligence research is shifting from single-task models toward multimodal large language model-based agents for complex clinical workflows, requiring benchmarks that assess clinical reasoning, process safety, and resource stewardship rather than final outputs alone.
12 July 2026
Read appraisal →JMIR medical education
Youth-Elder Co-Learning Model in Psychiatric Long-Term Care Education: Mixed Methods Evaluation of Communication and Empathy Outcomes
BACKGROUND: Taiwan is projected to become a "super-aged" society by 2025, leading to an increasing demand for community psychiatric long-term care (LTC). This demographic shift necessitates frontline professionals equipped with specialized communication skills and deep empathy. However, traditional didactic teaching often fails to adequately prepare students for the complex emotional and practical challenges of real-world psychiatric caregiving. OBJECTIVE: This study aimed to evaluate the effectiveness of the innovative youth-elder co-learning instructional model, which uniquely integrates micro-movie discussions and an intergenerational empathy board game, on adult learners' professional knowledge, communication competence, empathic development, and overall learning satisfaction. METHODS: A mixed methods, single-group, pre-post design was used. The educational intervention was implemented within an 18-week elective community psychiatric LTC course. Participants included 38 adult learners and continuing education students (aged 19-64 years). Notably, the majority of the cohort (n=29, 76.3%) had no prior practical experience in LTC. Quantitative data were collected using self-assessed and peer-evaluated scales for professional knowledge, communication competence, and empathy at pre-, mid-, and post-course time points, alongside an end-of-semester course student feedback survey. Qualitative data were systematically gathered through structured reflective journals and analyzed using a rigorous 6-phase thematic analysis framework. RESULTS: Students reported high course satisfaction rates, ranging from 92.4% to 95.3%. Quantitative analysis revealed a notable divergence: there were significant improvements in peer-evaluated outcomes (P<.001) and self-assessed communication competence (P=.004), but there was more conservative, statistically nonsignificant growth in self-assessed scores for professional knowledge (P=.14) and empathy (P=.09). This discrepancy likely reflects adult learners' heightened awareness of professional complexity and self-reflective humility. Furthermore, the qualitative thematic analysis uncovered the following three narrative shifts: (1) the dismantling of generational stereotypes through authentic, face-to-face interaction with real older adults; (2) an empathic awakening regarding the often-invisible burden of family caregivers, catalyzed by the micro-movies; and (3) the successful translation of theoretical nonviolent communication concepts into real-time clinical problem-solving during board game role-plays. CONCLUSIONS: The youth-elder co-learning model shows promise as an innovative, experiential pedagogical approach. By bridging theoretical frameworks with authentic intergenerational contact, the intervention supported students in translating general empathic concepts into actionable communication competencies. However, given the exploratory nature of this study and the absence of a control group, the quantitative findings must be interpreted cautiously. Future research using randomized controlled trial designs across multiple institutions is warranted to establish definitive causal impacts.
10 July 2026
Read appraisal →Clinical infectious diseases : an official publication of the Infectious Diseases Society of America
More Than a Message: Death by a 1000 'Chats'.
Secure electronic messaging within the electronic health record (EHR), such as Epic Chat, has transformed communication in hospitals by enabling rapid, asynchronous communication. Yet for Infectious Diseases (ID) consultants, the constant barrage of messages comes at a cost: fragmented attention, disrupted clinical reasoning, and potential patient harm. Messages that are repetitive, trivial, or casually worded can also fuel miscommunication and even medicolegal risk. As this type of messaging becomes increasingly prevalent in clinical practice, we must establish clearer boundaries and a cultural shift that values purposeful communication. Practical strategies include defining what requires chat versus direct phone or in-person conversation, batching responses, protecting focus time, and teaching messaging etiquette. To optimize patient care and protect clinician well-being, we must be intentional about when and how we communicate.
9 July 2026
Read appraisal →Journal of global health
Leapfrogging medical infrastructure: a novel bilateral exchange model driven by digital medicine in Kazakhstan.
The geographic maldistribution of highly specialised neurosurgical care in Central Asia, particularly Kazakhstan, presents a critical challenge driven by medical education pipeline constraints and brain drain. Traditional assistance models relying on short-term missions or conventional hardware donations are insufficient to bridge this fundamental infrastructural gap. We present a novel 'Bilateral Medical Exchange Model' established between Showa Medical University in Japan and top Kazakh medical institutions. By utilising advanced digital medicine - specifically, high-performance computing-driven artificial intelligence and 3D extended reality visualisation - as the primary diplomatic catalyst, this framework successfully engaged both grassroots clinicians and top-tier government officials. We highlight how targeting these technologies toward localised capacity building and edge-computing infrastructure circumvents traditional barriers. While long-term clinical outcomes remain to be systematically evaluated, this technology-driven diplomatic approach provides a foundational, hypothesis-generating framework for bridging the digital divide, integrating digital innovation with decentralised education to ultimately improve equitable patient outcomes in transitioning economies.
6 July 2026
Read appraisal →JMIR formative research
Knowledge, Attitudes, and Practices Related to AI in Learning and Research Among Medical Students in Vietnam: Cross-Sectional Study
BACKGROUND: In recent years, artificial intelligence (AI) has ushered in a promising era in medicine, particularly in medical education. However, studies assessing the knowledge, attitudes, and practices related to AI among medical students in Vietnam remain limited. OBJECTIVE: This study aimed to evaluate AI knowledge, attitudes, and practices among Vietnamese medical students in learning and research, and to identify factors associated with their AI practices. METHODS: A cross-sectional study was conducted among medical students at Thai Binh University of Medicine and Pharmacy from November to December 2025. Data were collected using an online structured questionnaire covering demographic characteristics and AI knowledge, attitudes, and practices. The main outcome of interest was AI practices in learning and research. Descriptive statistics and multivariable linear regression were used to examine associated factors. Regression coefficients (β), 95% CIs, and P values are reported. RESULTS: A total of 1002 medical students (mean age 21.00, IQR 19.00-23.00 years; n=596, 59.5% female) were included. The median percentage of maximum possible (POMP) score of AI knowledge was 66.67 (IQR 33.33-83.33), with a high level of familiarity with common tools (n=798, 79.6%). AI attitudes were generally positive (median POMP score 70.00, IQR 53.33-76.67). AI-related practices were lower (median POMP score 50.00, IQR 46.88-71.88), with AI being used primarily for information retrieval and literature research support. In the multivariable analysis, knowledge POMP score (β=0.12, 95% CI 0.08-0.16) and attitudes POMP score (β=0.42, 95% CI 0.34-0.51) were significantly associated with AI practices POMP score (P<.001). Age, gender, major, grade point average classification, and having participated in an AI seminar or training were not associated with AI practices. CONCLUSIONS: Medical students showed favorable knowledge and positive attitudes, but their AI practices remained limited. Integrating AI into medical curricula, including fundamentals, applications, and ethical aspects, is essential to prepare future physicians for AI-driven health care.
5 July 2026
Read appraisal →Langenbeck's archives of surgery
The role of large language models in the writing of surgical reviews: fact or fantasy?
BACKGROUND: Amidst the current enthusiasm concerning artificial intelligence and its possible application in the composition of different kinds of scientific and non-scientific written documents, we evaluated the usage of artificial intelligence for writing surgical short reviews. METHODS: In order to assess the formal and content quality of AI-generated texts compared to human written texts, ten AI-based text generators (five chatbots and five content creators) and four surgeons in training received the same prompt for a short scientific article on a liver surgery theme. All texts were anonymized and subsequently evaluated by three experienced liver surgeons based on a pre-defined scoring scheme, as well as for quality of references and readability according to readability indices. Furthermore, all texts were tested for plagiarism using PlagScan. RESULTS: Overall percentage of correct assessment for AI/non-AI generation by experienced surgeons lay at 78.57%. Human written text had a mean word count of 1054 versus 874 in AI-generated text, with a higher mean Flesh Reading Ease Score (FRE, 26.2 ± 5.1 versus 17.7 ± 6.1). References were PubMed-listed in 100% for human versus 46% for AI-generated text, with only one non-human text reaching 100% formally correct citation of references. PlagScan found 6.4%±1.3 mean resemblance to existing texts for human versus 7.6%±4.5 for AI-generated text. DISCUSSION: Overall, AI could already mislead experienced scientific surgeons in 26.7% of cases into believing it to be human. However, formal requirements, especially considering referencing, are still in great need of improvement with only one of AI-generated articles fulfilling our quality requirements.
4 July 2026
Read appraisal →Korean journal of radiology
Agentic Artificial Intelligence for the Automated Generation of Accurate Summary Podcasts of Radiology Research Papers
OBJECTIVE: To evaluate whether a custom agentic artificial intelligence (AI) pipeline can overcome the limitations of general-purpose large language model tools, when compared with a generic commercial tool (Google NotebookLM [NBLM]), for generating podcast-style summaries of radiology research articles. MATERIALS AND METHODS: Twenty-two PDF-format original research articles published in the April 2025 issue of Radiology were processed using our Programmable, Phoneme-Aware PDF-to-Podcast Pipeline (P5) and NBLM to generate 44 audio episodes. P5 utilizes a multi-agent workflow for script generation, quality assurance, pronunciation enhancement, and audio synthesis. Four radiologists from a pool of 25 (7 generalists and 18 specialists) were randomly assigned to evaluate each blinded audio episode, yielding 176 total evaluations. The primary outcomes were the number of hallucinations (factual errors) per episode and the percentage of hallucination-free episodes. Secondary outcomes included the number of inappropriate statements, mispronunciations, and flow disruptions; the composite quality score (Quality Assessment of Educational Podcasts [QAEP]); the key results coverage score; and overall listener preference. Data were analyzed using generalized linear mixed models. RESULTS: The P5 method produced significantly fewer hallucinations per episode compared with NBLM (mean, 0.32 vs. 0.93; P < 0.001) and a higher proportion of hallucination-free episodes (71.6% [63/88] vs. 56.8% [50/88]; P = 0.013), consistently across generalists and specialists. P5 demonstrated significantly fewer mispronunciations (mean, 0.11 vs. 1.62; P < 0.001) and flow disruptions (mean, 0.19 vs. 1.06; P < 0.001) per episode, as well as higher mean QAEP composite scores (4.62 vs. 4.28; P < 0.001), compared with NBLM, consistently across generalists and specialists. Raters preferred P5 over NBLM in 72.7% (64/88) of comparisons (P = 0.003). CONCLUSION: Our custom agentic AI pipeline generated podcast-style summaries of radiology research articles with significantly higher quality and greater listener preference than the generic commercial tool.
3 July 2026
Read appraisal →Journal of medical Internet research
Transformation Versus Innovation in Digital Health Care and the Future of Clinical AI
Digital innovation is frequently presented as the key to transforming health care. In this News and Perspectives article, JMIR Correspondent and academic physician Boon-How Chew reports on the distinction between and the direction of transformation and innovation, reflecting on the future of clinical AI and what lasting change in health care ultimately requires.
3 July 2026
Read appraisal →The Behavioral and brain sciences
Large language models have learned to use language.
Acknowledging that large language models have learned to use language can open doors to breakthrough language science. Achieving these breakthroughs may require abandoning some long-held ideas about how language knowledge is evaluated and reckoning with the difficult fact that we have entered a post-Turing test era.
2 July 2026
Read appraisal →Medical education online
Consensus and learning climate in temporary versus permanent teams in team-based learning
BACKGROUND: In team-based learning, students are typically placed in fixed teams based on the idea that stable group membership fosters collaboration: as teammates get to know each other, they share more information, resolve differences and feel motivated to contribute. This rationale had not been tested in a randomized controlled trial. OBJECTIVE: The study compares team-based learning in temporary teams with the default permanent teams regarding individual and team readiness assurance test performance (iRAT, tRAT), reaching team consensus, the learning climate, and intrinsic motivation. DESIGN: In a randomized controlled trial, first-year medical students were assigned either to permanent TBL teams or to teams that were re-assigned for each problem. The team readiness assurance test (tRAT) votes, submitted individually and covertly, served as an indirect indicator for team consensus (concordant versus discordant tRAT vote). RESULTS: Discordant tRATs (n = 268, 11.8% of all votes) were submitted more frequently in temporary than in permanent teams, both for correct and incorrect majority decisions. The self-rated learning climate was more cooperative in permanent than in temporary teams, while intrinsic motivation and tRAT scores were similar for both types of teams. A poorer learning climate was associated with a higher proportion of discordant tRATs. CONCLUSION: Working in temporary teams does not lead to inferior intrinsic motivation; this was previously also shown for knowledge gain. However, the poorer learning climate, together with reaching a consensus less often, might indicate that at least some members of temporary teams feel not adequately appreciated in the discussion and do not accept the majority decision. With instructional strategies promoting a cooperative learning climate in temporary teams, preclinical TBL courses might serve as an early promoter of the relational team competencies required for subsequent clinical workplace learning in temporary teams.
1 July 2026
Read appraisal →Medical education online
Exploring medical Artificial Intelligence Readiness among Korean medical students: a cross-sectional study
INTRODUCTION: Artificial intelligence (AI) is rapidly transforming healthcare systems and clinical practice, increasing the need to prepare future physicians to work effectively with AI technologies in clinical contexts. Despite growing interest in integrating AI into medical education, empirical evidence regarding medical students' readiness to use AI remains limited. This study aimed to assess medical AI readiness among Korean medical students and explore factors associated with their readiness. METHODS: A cross-sectional survey was conducted among medical students enrolled in a six-year medical program at a university in Korea. A total of 204 students participated in the study. Medical AI readiness was measured using the Medical Artificial Intelligence Readiness Scale for Medical Students (MAIRS-MS), which assesses four domains: cognition, ability, vision, and ethics. Descriptive statistics, independent t-tests, and Pearson's correlation analyses were performed using SPSS version 27. RESULTS: The overall mean score of medical AI readiness was 4.19 on a 7-point Likert scale, indicating a moderate level of medical AI readiness. Among the subscales, ethics showed the highest mean score (4.69), followed by vision (4.44), ability (4.18), and cognition (3.92). The frequency of AI use was significantly associated with medical AI readiness, whereas the daily duration of AI use was not. No significant gender differences were observed. When students were divided into the low (pre-medical years 1-2) and high (medical years 1-4) groups, the high group showed significantly higher scores only in the ability subscale. CONCLUSIONS: The findings suggest that medical students are not yet sufficiently prepared to utilize AI technologies in clinical practice, particularly in terms of knowledge and practical competencies related to AI. These results highlight the need for structured and longitudinal AI education in medical curricula to better prepare future physicians for AI-integrated healthcare environments.
1 July 2026
Read appraisal →JMIR medical education
Exploring the Role of Early Career Medical Professionals From a Digital-Oriented University in Germany in Promoting Digital Health in Professional Settings: Qualitative Interview Study
BACKGROUND: To address care delivery gaps, the health care system must embrace innovative digital solutions. Additionally, the rising integration of digitalization as a topic into medical education is providing students with broader opportunities to engage with digitalization overall. As digital health becomes an increasingly integral component of medical education and health care practice, digitally affine early career medical professionals constitute a vital resource for advancing digitalization within the health care sector. OBJECTIVE: This study examines how early career medical professionals from Witten/Herdecke University in Germany, with various courses focusing on digitalization, acquire digital knowledge, apply it across diverse practical contexts-ranging from start-ups and corporate environments to traditional clinical settings-and how they contribute to the advancement of digitalization within the entire health care sector. METHODS: Using a qualitative approach, 19 interviews were conducted with early career medical professionals who graduated in the last 15 years at Witten/Herdecke University. Subsequently, the interviews were transcribed and analyzed using a deductive-inductive approach. RESULTS: The findings reveal that medical graduates often acquire digital skills through intensive self-study and learning on the job, integrating them in various ways into their professional lives. Moreover, while graduates recognize their high potential to make their own contribution to the advancement of digitalization, they also face significant barriers such as knowledge gaps, limited resources, and complex regulations, which hinder their ability to contribute to digitalization in a variety of professional settings. Medical graduates report that they face a pressing need for enhanced knowledge access, improved institutional frameworks, and supportive policy measures to maximize their potential in advancing digitalization initiatives. CONCLUSIONS: Recent medical graduates represent an underused resource for health care digitalization. Unlocking this potential requires coordinated action across medical education, health care institutions, and policymaking to create appropriate conditions for graduates to actively drive digitalization.
26 June 2026
Read appraisal →Journal of Korean medical science
Evaluating Large Language Models for Post-Publication Promotion: A Blinded Comparative Study of Social Media Posts in Public Health
BACKGROUND: Social media platforms such as X (formerly Twitter) are increasingly used by journals, authors, and institutions to promote newly published research. Well-designed posts can enhance visibility, accelerate knowledge translation, and increase altmetric attention. However, creating accurate and policy-compliant content is time-intensive. Large language models (LLMs) offer a potential solution, yet systematic evaluations of their performance in post-publication promotion remain limited. METHODS: We conducted a blinded, crossed, offline evaluation of four LLMs: GPT-5 (OpenAI), Gemini 2.5 Pro (Google DeepMind), Grok-3 (xAI), and Perplexity Pro (Perplexity AI), tasked with generating X-style posts (≤ 260 characters) for 36 open access articles from The Lancet Public Health, The Lancet Planetary Health, and Annual Review of Public Health. Posts were generated using a standardized system and user prompt. A single blinded rater scored outputs using a five-domain rubric (factual accuracy, clarity, policy compliance, call-to-action quality, structure/metadata; maximum score 10). Secondary measures included character count, hashtag use, and readability (Flesch-Kincaid Grade Level). General linear models with Bonferroni-adjusted post hoc tests and non-parametric analyses were applied. RESULTS: All four models achieved perfect factual accuracy and no policy violations. Mean total quality scores differed significantly by model, P < 0.001. GPT-5 (9.60) and Perplexity Pro (9.60) performed best, followed by Gemini 2.5 Pro (9.47), while Grok-3 scored lower (8.80). Domain analyses showed Grok-3 underperformed in call-to-action quality (1.40 vs. ≥1.97 in other models, P < 0.001) and produced significantly shorter posts (median 194 characters, P < 0.001). Perplexity Pro scored highest for policy compliance, while GPT-5 and Gemini 2.5 Pro achieved superior structural scores. Readability varied: GPT-5 8.9 (7.3-9.2) and Perplexity Pro 7.3 (6.5-8.8) generated more complex outputs, whereas Gemini 2.5 Pro 5.1 (4.8-6.5) and Grok-3 4.5 (3.6-6.3) produced more accessible posts. CONCLUSION: LLMs can reliably generate accurate and policy-compliant social media posts for research promotion, with differences in style and readability that may inform audience targeting. GPT-5, Gemini 2.5 Pro, and Perplexity Pro produced high-quality outputs, while Grok-3 underperformed across several domains. These findings highlight the potential of LLMs as scalable first-draft tools for post-publication promotion, capable of improving the reach and accessibility of scientific research. Careful model selection, tailored to audience and communication goals, together with human oversight, remains essential.
25 June 2026
Read appraisal →BMJ health & care informatics
Clarifying the relationship between biomedical and health informatics and digital health: expert perspectives.
The rise of digital health (DH) has sparked debates about its relationship with the long-established field of biomedical and health informatics (BMHI), with some questioning the need for new academic programmes in DH since much of the likely content is already covered in BMHI training programmes. At the International Medical Informatics Association panel, 'Shaping the Future of Biomedical and Health Informatics in the Digital Health Era' (MEDINFO 2025), only one-third of participants clearly distinguished the two fields, highlighting conceptual ambiguities and the influence of DH narratives. This article compiles the perspectives expressed by the panellists, all experienced BMHI scholars, presenting their distinct viewpoints on how the field can maintain its scientific identity while engaging with emerging DH initiatives.
24 June 2026
Read appraisal →Archives of disease in childhood
AI-simulated clinical consultations: Assessing the potential of ChatGPT to support medical training
BACKGROUND: Simulated medical scenarios are useful for evaluating and developing clinical competencies but scheduling them is expensive and time-consuming. Large language models show promise in role-playing tasks. We investigated the fidelity with which ChatGPT can mimic patients, clinicians and examiners in educational settings. OBJECTIVE: To determine the realism with which ChatGPT can portray patient, doctor and examiner roles, and the utility of these agents in clinical education. METHOD: We selected four paediatric scenarios from mock objective structured clinical examinations (OSCEs) and set up separate patient, doctor and examiner ChatGPT agents for each. The patient and doctor agents conversed with each other in written format. The examiner agent marked the doctor agent based on this conversation. Patients and clinicians familiar with the OSCE assessed the dialogues. RESULTS: The patient agent was judged to be true to character most of the time and good at expressing emotion. The doctor agent was reported to be an effective communicator but occasionally used jargon. Both agents tended to produce repetitive responses which undermined realism. The examiner agent had good correlation with human clinicians. There was moderate support for using the simulated interactions for educational purposes. CONCLUSION: Although the realism of the agents can be improved, ChatGPT can generate plausible proxies of participants in medical scenarios and could be useful for complementing standardised patient-based training.
24 June 2026
Read appraisal →NEJM evidence
A Randomized Trial of Interval Likelihood Ratios for Clinical Decision-Making
BACKGROUND: Dichotomized reporting of diagnostic test results may oversimplify test characteristics. Interval likelihood ratios (ILRs), test characteristics across a range of values, offer a nuanced alternative, but their impact on decision-making is uncertain. We assessed whether ILRs improve clinical decisions compared to two traditional formats: single-threshold and binary test characteristics. METHODS: We conducted a multicenter randomized trial of internal medicine residents, attending physicians, and advanced practice providers. Participants were presented with two fictional vignettes (cases involving pulmonary embolism diagnosis and heart failure treatment), each with a clearly correct response centered on a key diagnostic test result. The vignettes were identical except for participants' random assignment to one of three test characteristic presentations: (1) single threshold, (2) binary test characteristics, or (3) ILRs. We compared the correct management decision rates between the ILR and threshold groups and between the ILR and binary groups. Secondary objectives included comparing threshold and binary groups and subgroup analyses by case vignette. RESULTS: The trial enrolled 611 participants. The correct decision rate was 93.4% in the ILR group compared with 82.2% in the threshold group (difference of 11.2 percentage points; 95% confidence interval [CI], 6.9-15.6, P<0.001) and compared with 75.1% in the binary group (difference of 18.3 percentage points; 95% CI, 13.5-23.1, P<0.001). In the pulmonary embolism case, the correct response rate was 91.9% in the ILR group, 70.9% in the threshold group, and 64.7% in the binary group. In the heart failure case, the correct response rate was 94.9% in the ILR group, 93.4% in the threshold group, and 85.6% in the binary group. CONCLUSIONS: Presenting diagnostic test information using ILRs improved vignette-based clinical decisions. The magnitude of improvement appeared to vary by case vignette.
24 June 2026
Read appraisal →Current opinion in anaesthesiology
Traditional learning meets adaptive learning: the present and future of education in nonoperating room anesthesia.
PURPOSE OF REVIEW: Nonoperating room anesthesia (NORA) and continuing education in this setting are both in a state of change. Procedures performed outside the operating room, especially those that require nuanced anesthetic care, are becoming increasingly prevalent. Numerous new innovations are transforming care across NORA settings, especially within gastroenterology, interventional and neurointerventional radiology, and electrophysiology. Concurrently, education for NORA providers is rapidly evolving, influenced by technological advancements and artificial intelligence. RECENT FINDINGS: Traditional learning, a mode of education in which each learner receives essentially the same content, is now blending with adaptive learning, a field of precision education in which dynamic educational content is curated for individual learners, timed and paced to their preferences and progress, and coupled with artificial intelligence-generated feedback. The mainstays of traditional education for NORA providers remain relevant: content created by professional societies, podcasts, textbooks, and primary literature. Yet new, artificial intelligence-driven approaches for adaptive learning have entered the scene: clinical decision-making tools, literature review and knowledge mapping assistants, online platforms for precision education, virtual reality, and synthetic patients or avatars. SUMMARY: This article explores the blending of traditional and adaptive educational modalities in NORA continuing education and discusses the implications and obstacles for the future.
23 June 2026
Read appraisal →Journal of psycholinguistic research
Statistical Analysis of Human and AI Machine Translation Accuracy, Style, and Context in Academic English
AI-driven Machine Translation (MT) technology has raised doubts about whether it can replace Human Translation (HT), particularly in the academic English field. This research contrasts AI-based MT and HT of academic English on accuracy, stylistic quality, errors, contextual appropriateness, and overall suitability. A quantitative comparative design was employed for the translation of eight Chinese texts with various genres. Using purposive sampling, 4 certified human translators were selected to produce the HT, and also used AI-based MT systems such as DeepL, ChatGPT, and Google Translate to translate the text. 69 experts evaluated the translated versions, and this data was examined using SPSS software. HT produced better performance than MT through mean accuracy, stylistic quality, contextual appropriateness, and overall suitability (Human: 4.76, AI: 3.73), revealed statistically significant differences (p < 0.001), and effect sizes (Cohen's d = 1.53 to 2.81). Compared to HT, the MT showed higher grammatical and semantic errors (Cohen's d = 2.81). The fluency, tone, and register of stylistic quality were evaluated at higher levels for HT (p < 0.001). Among AI-MT tools, DeepL shows higher performance in translation (M = 4.16, SD = 0.37). The genre-wide comparison of MT and professionally certified HT, and the comparison among multiple AI tools, towards various translation dimensions, provides insights into the differences in translating quality. The research indicates a continued reliance on human professionals for important scholarly translations while encouraging continued development in AI translation software for better quality.
22 June 2026
Read appraisal →Medical education online
Cross-cultural adaptation and psychometric evaluation of the artificial intelligence learning intention scale (AILIS) among medical sciences students: a methodological study
BACKGROUND: This study aimed to adapt and psychometrically evaluate the Artificial Intelligence Learning Intention Scale (AILIS) among Iranian medical sciences students. METHODS: This methodological psychometric study was conducted among 800 medical sciences students at Babol University of Medical Sciences, Iran. The AILIS was translated and culturally adapted into Persian using a standardized cross-cultural adaptation process. Construct validity was examined through exploratory factor analysis (EFA) and confirmatory factor analysis (CFA). Reliability was assessed using Cronbach's alpha, McDonald's omega, and the intraclass correlation coefficient (ICC). Convergent and discriminant validity were evaluated using composite reliability (CR) and average variance extracted (AVE). Measurement invariance across gender and structural stability were assessed using multi-group confirmatory factor analysis and exploratory graph analysis (EGA). RESULTS: EFA supported a four-factor structure consisting of Epistemic Capacity, Psychological Attitudes, Facilitating Environments, and Psychological and Behavioral Outcomes, explaining 44.55% of the total variance, with factor loadings greater than 0.40. Confirmatory factor analysis indicated an acceptable model fit, supporting the proposed factor structure (χ²/df = 3.42, RMSEA = 0.078, CFI = 0.932). Internal consistency and test-retest reliability were satisfactory, with Cronbach's alpha ranging from 0.854 to 0.904, McDonald's omega from 0.854 to 0.899, and ICC from 0.750 to 0.860. Composite reliability values were adequate, while AVE values indicated acceptable but partially limited evidence of convergent validity. Discriminant validity was generally supported. In addition, multi-group analysis demonstrated measurement invariance across gender, and exploratory graph analysis confirmed the structural stability of the four-factor model. CONCLUSION: The Persian AILIS is a valid and reliable instrument for assessing AI learning intention among medical sciences students. Beyond its psychometric robustness, the instrument may support curriculum planning, evaluation of AI-related educational interventions, and evidence-based decision-making in medical sciences education by providing a standardized measure of students' intentions to engage with AI learning.
20 June 2026
Read appraisal →JMIR medical education
Training Empathetic Communication Skills in Medical Students With a Role-Prompted GPT-4o Chatbot: Quasi-Experimental Intervention Study
BACKGROUND: There is growing concern that artificial intelligence (AI) may diminish the quality of human relationships. However, in a context of widespread social importance (empathetic conversations between doctors and patients), AI can actually improve human conversational skills, potentially enhancing professional relationships. Recent advances in AI allow for realistically role-prompted counterparts for practicing professional conversations, enabling relational learning without the need for human counterparts. OBJECTIVE: This study aimed to show the effectiveness of AI chatbots for learning professional communicative skills in medical education. Specifically, we hypothesized that a single conversation with an AI chatbot improves communication skills in medical students across 4 different conversational competencies. METHODS: We conducted a quasi-experimental intervention study involving 4 distinct role-prompted scenarios (ie, shared decision-making, motivational interviewing, sexually transmitted diseases, and breaking bad news)-each designed to elicit in-depth empathic conversational skills aligned with key learning objectives in medical curricula. Students rated their competence for the 4 scenarios before and after a conversation with GPT-4o (OpenAI) using default settings, without fine-tuning. We expected higher perceived communication competence (PCC) in their conversation topic after the interaction compared with before the interaction in a 2-sided paired t test. Participants received AI-generated feedback, which they rated regarding adequacy. Post hoc analyses addressed gender and case effects, feedback adequacy, and prevalues in PCC. RESULTS: This study shows that a role-prompted GPT chatbot improves PCC in 162 medical students after a single conversation with mean of 13 (SD 4.8; 95% CI 12-14) prompt-response pairs. We found an increase in PCC with a mean difference of 0.94 (SD 1.64; 95% CI 0.69-1.20; Cohen d=0.58) from 5.89 (95% CI 5.55-6.23; scale 0-10) before the conversation to 6.83 (95% CI 6.55-7.12) after the conversation across 4 different patient role prompts. Furthermore, we found participants rating AI feedback of their conversation to be useful (mean 7.92, SD 1.61; 95% CI 7.67-8.17; scale 0-10), but feedback adequacy did not correspond to PCC increase (r=0.08; P=.32). CONCLUSIONS: Our results demonstrate how role-prompted GPT increases self-assessed communication competencies, introducing a novel tool for teaching relational learning. Our results present a starting point for using AI in education, particularly teaching communication in professional roles. On the basis of our findings in medical education, we anticipate further studies to investigate conversational training between lawyers and clients, marketers and customers, or managers and employees. Our research thus has implications for any field with a need for conversational training and relational learning.
14 June 2026
Read appraisal →Critical care explorations
Multiagent First-Person Perspective Analysis for Leadership Assessment in Pediatric Emergency Simulations: A Feasibility Study
BACKGROUND: Conventional leadership assessments provide structured ratings but offer limited observer-independent metrics. Because leadership and teamwork are interdependent, capturing team dynamics requires multiagent, time- and space-synchronized analysis. This pilot study examined the feasibility of applying multiagent, spatiotemporally synchronized first-person perspective analysis (FPA) in emergency simulations. METHODS: This exploratory simulation study was conducted in a real patient-care room within the PICU of our institution. Two physicians-a critical care specialist (L1) and a pediatric resident (L2)-each completed one scenario as team leader. Leadership behaviors were evaluated using the Ottawa Global Rating Scale, focusing on Situational Awareness and Communication. Wearable smart glasses recorded first-person video and gaze data, enabling identification of fixations within five predefined areas ("patient," "member," "device," "screen," and "unknown"). Eye-contact events were quantified using face detection based on You Only Look Once, version 8, a deep learning-based object detection model, combined with gaze-vector estimation, and analyzed in relation to the timing of verbal communication. RESULTS: Multiagent, time-synchronized FPA was implemented without device- or software-related interruption, and no critical data loss occurred. The mean analyzable session duration relative to total operating time was 77.1%, and the mean percentage of frames excluded from object tracking was 29.3%, primarily due to target objects being outside the field of view. As secondary, illustrative findings, Ottawa Global Rating Scale scores indicated that both leaders were rated within the competent range. FPA further showed that both leaders spent approximately 80% of the scenario fixating on predefined relevant areas (L1: 599/731 s; L2: 565/693 s). Greater patient-directed fixation and balanced gaze transitions were observed in L1, whereas L2 showed prolonged fixation within nonspecific areas. L1 also established eye contact with team members more frequently during direct orders or information sharing. CONCLUSIONS: This study demonstrates the feasibility of multiagent, time-synchronized FPA for extracting gaze-based behavioral information relevant to leadership assessment in emergency simulations.
14 June 2026
Read appraisal →JMIR medical education
Evaluating the Pediatric Behavior Guidance of Students Based on Actual Clinical Transcripts Scored by Faculty and Large Language Models: Pilot Comparative Study
BACKGROUND: Personalized feedback improves the clinical pediatric behavior guidance performance of students but is prohibitively time-consuming to provide. Large language models (LLMs) can automate the process of evaluating clinical sessions but are limited to text-only input and consistency issues. OBJECTIVE: This study compared the use of text-only transcripts against the use of video recordings for evaluating the clinical behavior guidance performance of dental students. Additionally, the consistency and accuracy of LLMs in evaluating the transcripts were compared against a human assessor. METHODS: This study was conducted by using 40 video-recorded clinical encounters involving final-year dental students who were managing patients aged between 4 and 12 years at the Faculty of Dentistry, National University of Singapore. The videos were scored by using a previously validated pediatric behavior guidance scale. Clinical encounters were transcribed verbatim and scored by a study member using a modified version of the scale (nonverbal components removed). The time taken to rate the transcripts was recorded. Video scores were compared with transcript scores. Both the free-to-use version and the paid version of the ChatGPT LLM were also used to score the transcripts; consistency was evaluated and compared against the human assessor. RESULTS: The average time taken to rate the transcripts (mean 12, range 3-25 min) was significantly (P<.001) lower than the average video length (mean 73, range 37-120 min). Comparing transcript scores with video scores resulted in a consistency intraclass correlation coefficient of 0.830 (95% CI 0.679-0.910; P<.001), demonstrating good reliability. Comparing transcript scores with the free-to-use LLM's and paid LLM's scores yielded an absolute agreement intraclass correlation coefficient of 0.729 (95% CI 0.475-0.859; P<.001) and 0.670 (95% CI 0.377-0.825; P<.001), respectively, demonstrating moderate agreement. The LLMs were inconsistent, producing variable scores with the same prompt. The free-to-use and paid versions produced the same score for all 3 runs in only 7 (18%) and 4 (10%) of the 40 clinical encounters, respectively. CONCLUSIONS: Using transcripts to evaluate students' clinical behavior guidance was time-saving for faculty, demonstrated good agreement with video-based evaluation, and could improve clinical teaching. Although LLMs can automate the task, improvements are needed to improve their consistency and accuracy.
14 June 2026
Read appraisal →JMIR nursing
Assessing Digital Literacy Among Nursing Faculty Under the Artificial Intelligence-Enhanced Technological Pedagogical Content Knowledge Framework: Cross-Sectional Survey Analysis
BACKGROUND: Digital literacy has become a core competence for nursing faculty to adapt to the digital transformation of education, improve teaching quality, and cultivate innovative nursing talents. OBJECTIVE: This study aimed to investigate the digital literacy status and influencing factors among nursing faculty in colleges and universities in Fujian province, China. METHODS: A cross-sectional survey analysis was conducted among 339 participants from July 2023 to June 2024 by selecting nursing faculty from 3 medical universities and 5 colleges in Fujian province. A general information questionnaire and a teacher digital literacy questionnaire (designed based on the artificial intelligence-enhanced technological pedagogical content knowledge theoretical model) were used to conduct the survey. The questionnaires included the following dimensions: an intelligent integration ethics layer (digital social responsibility), attention to the moral boundaries of applying technology; an awareness layer (digital awareness), the willingness to actively adapt to technological changes; a knowledge layer (digital technology knowledge and skills), mastery of the integration point of intelligent tools and subject teaching; an ability layer (digital application), the ability to design intelligent teaching plans; and a thinking layer (professional development; innovative thinking for the critical integration of technology). Statistical analysis included descriptive statistics, a 1-way ANOVA, Pearson correlation analysis, and multiple linear regression (using SPSS 28.0 software). RESULTS: The overall digital literacy of the nursing faculty was at a medium level (mean score 101.92, SD 16.47), with the highest score in digital awareness (mean 20.21, SD 9.43) and the lowest score in digital technology knowledge and skills (mean 9.68, SD 2.92). For the dimension of digital technology knowledge and skills, both age (β=-.142; P=.009) and years of teaching (β=-.147; P=.006) were significant negative predictors. Regarding digital application, age was found to be a significant negative predictor (β=-0.124; P=.02) but teaching experience was a positive predictor (β=0.123, P=.02). Similarly, age also had a significant negative impact on the professional development dimension (β=-.153; P=.005) and the overall digital literacy level (β=-.136; P=.01). CONCLUSIONS: The digital literacy of nursing faculty is at a medium level, with especially low scores in technical knowledge. Age and teaching experience are key influencing factors. Recommendations to promote balanced development of awareness and skills include providing targeted training for senior faculty, integrating courses with clinical practice, optimizing the allocation of digital resources, promoting interdisciplinary cooperation, and strengthening ethical and safety training.
14 June 2026
Read appraisal →PloS one
The application of large language models in bariatric surgery: A scoping review
BACKGROUND: Exploratory applications of large language models within the specialized field of metabolic and bariatric surgery have begun to emerge. Nevertheless, existing research remains fragmented, lacking comprehensive integration. OBJECTIVE: To conduct a scoping review of studies on the application of large language models in the field of metabolic and bariatric surgery, aiming to provide a reference for clinical practice and future research. METHODS: This scoping review adhered to the Joanna Briggs Institute methodological framework and followed the preferred reporting items for systematic reviews and meta-Analyses extension for scoping reviews (PRISMA-ScR) guidelines.PubMed, Web of Science, The Cochrane Library, Embase, CINAHL, CNKI, Wanfang, and VIP databases were searched for relevant studies, with the search timeframe from database inception to November 2025. The included literature was summarized and analyzed. RESULTS: A total of 21 English-language studies were included. LLMs were primarily applied in scenarios such as patient education and information consultation, clinical decision support, and professional knowledge assessment. While LLMs performed well in information-provision tasks, they showed low consistency with expert opinions in complex clinical tasks such as individualized surgical recommendations. Performance varied across different models, with GPT-4 generally demonstrating superior performance, and domain-specific models showing professional potential. Current research still faces challenges regarding information accuracy, readability, and clinical applicability. CONCLUSION: Large language models hold auxiliary potential in the field of metabolic and bariatric surgery, particularly for knowledge dissemination and patient education. However, their reliability in complex clinical decision-making remains limited. Future efforts should focus on conducting high-quality studies, advancing model specialization and standardized evaluation, and exploring safe and effective human-AI collaboration models.
7 June 2026
Read appraisal →Regional anesthesia and pain medicine
Recommendations for disclosure of artificial intelligence in scientific writing and publishing: a regional anesthesia and pain medicine modified Delphi study
INTRODUCTION: The use of artificial intelligence (AI) in the scientific process is advancing at a remarkable speed, thanks to continued innovations in large language models. While AI provides widespread benefits, including editing for fluency and clarity, it also has drawbacks, including fabricated content, perpetuation of bias, and lack of accountability. The editorial board of Regional Anesthesia & Pain Medicine (RAPM) therefore sought to develop best practices for AI usage and disclosure. METHODS: A steering committee from the American Society of Regional Anesthesia and Pain Medicine used a modified Delphi process to address definitions, disclosure requirements, authorship standards, and editorial oversight for AI use in publishing. The committee reviewed existing publication guidelines and identified areas of ambiguity, which were translated into questions and distributed to an expert workgroup of authors, reviewers, editors, and AI researchers. RESULTS: Two survey rounds, with 91% and 87% response rates, were followed by focused discussion and clarification to identify consensus recommendations. The workgroup achieved consensus on recommendations to authors about definitions of AI, required items to report, disclosure locations, authorship stipulations, and AI use during manuscript preparation. The workgroup formulated recommendations to reviewers about monitoring and evaluating the responsible use of AI in the review process, including the endorsement of AI-detection software, identification of concerns about undisclosed AI use, situations where AI use may necessitate the rejection of a manuscript, and use of checklists in the review process. Finally, there was consensus about AI-driven work, including required and optional disclosures and the use of checklists for AI-associated research. DISCUSSION: Our modified Delphi study identified practical recommendations on AI use during the scientific writing and editorial process. The workgroup highlighted the need for transparency, human accountability, protection of patient confidentiality, editorial oversight, and the need for iterative updates. The proposed framework enables authors and editors to harness AI's efficiencies while maintaining the fundamental principles of responsible scientific communication and may serve as an example for other journals.
7 June 2026
Read appraisal →Journal of neural engineering
An online brain-computer interface for detecting incongruity in augmented reality applications
Objective.Augmented reality can provide digital information about physical entities presented within its real-world context. However, this information might disagree with the user's expectations due to factual errors in the data or cognitive biases. Such incongruity can impair user experience and undermine trust in the AR system. To address this issue, we propose detecting inconsistencies between physical objects and digital information through hybrid brain-computer interfaces.Approach.We conducted two complementary experiments. First, we implemented a strategy that integrates eye-tracking and brain signals for incongruity detection in an offline study. Subsequently, we assessed our approach in an online study in which participants received immediate feedback on the classification.Main results.The grand average event-related potentials revealed consistent electroencephalographic responses to incongruent augmentations, specifically a centroparietal N400 effect, across both experiments. We could further distinguish between congruent and incongruent information with an average balanced accuracy of 70% in the online study.Significance.These findings demonstrate the feasibility of detecting incongruity online, allowing for autonomous system adaptation, like presenting information in a more accessible format or providing contextual support.
31 May 2026
Read appraisal →JMIR medical education
Performance of Large Language Models on the Brazilian National Medical Education Examination: Comparative Benchmark Study
BACKGROUND: Large language models (LLMs) are rapidly incorporated into medical education and examination preparation; yet, most benchmarking evidence is derived from English-language material. Whether frontier commercial models and Brazilian Portuguese domain-specialized systems perform equivalently on high-stakes Brazilian medical examinations remains unclear. OBJECTIVE: This study aims to quantify and compare the performance of 9 frontier commercial LLMs and 1 Brazilian Portuguese domain-specialized system (Charcot, Voa Health) on 2026 Brazilian National Medical Education Examination (Exame Nacional de Avaliação da Formação Médica [ENAMED] 2026) and to describe the patterns of systematic between-model error as complementary quality signal. METHODS: All 100 items of ENAMED 2026 (99 valid after annulment) were administered to 10 frontier-panel models across 5 independent runs under identical Portuguese prompts (temperature=0; top-p=.95). Commercial models were accessed through a unified OpenRouter client layer (DeepSeek provider-pinned). The primary outcome was mean accuracy against the preliminary key; the secondary outcomes were convergence error (CE), normalized mean response time (NMRT), and intermodel agreement. Accuracy was analyzed with Shapiro-Wilk, Levene, Kruskal-Wallis (ε2), Dunn-Holm post hoc, and a binomial generalized linear mixed model with question and run random intercepts. NMRT excluded Charcot (different stack) and Grok 4 (latency outlier). A total of 7 open-weight and small language models were assessed as a small language model (SLM) substudy. RESULTS: Frontier-panel accuracy ranged from 73.74% (365/495) for GPT-4o-mini to 96.97% (480/495) for Charcot. Accuracy was nonnormal (Shapiro-Wilk, W=0.82; P<.001) with homogeneous variance (Levene P=.26). Kruskal-Wallis showed large between-model differences (H9=47.65; P<.001; ε2=0.97). Dunn-Holm flagged 8 of 45 pairs: Charcot was separable from GPT-4o-mini, DeepSeek v3.2-exp, and Grok 4, but not from the top frontier cluster. The generalized linear mixed model preserved the ranking (all comparators odds ratio<1 vs Charcot; upper CI<1 except GPT-5). A total of 9 items met the default CE criterion; item 77 showed 10-of-10 convergence, later confirmed by Instituto Nacional de Estudos e Pesquisas Educacionais Anísio Teixeira rectification, and sensitivity analysis preserved the CE set (5-20 items). Intermodel agreement was high (Fleiss κ=0.852; Krippendorff α=.852). Among 8 retained commercial models, NMRT correlated positively with accuracy (Spearman ρ=0.74; P=.04); these results are interpreted as descriptive of an orchestration-level latency-accuracy law. SLM accuracy ranged from 47.47% (Gemma 3 4B) to 82.22% (GPT-OSS 120B), with lower agreement (Fleiss κ=0.508) and 17 CE items. The best SLM-panel model lagged every frontier-panel model except GPT-4o-mini, with a 12-15 percentage-point gap against the top cluster. CONCLUSIONS: On ENAMED 2026, a Brazilian Portuguese domain-specialized system ranked first, indistinguishable from frontier commercial cluster and above subfrontier and open-weight systems. Charcot's architecture is not publicly disclosed; these findings should be interpreted as comparative black-box evidence of performance and not as mechanistic evidence of specialization. CE was stable, and it prospectively flagged 1 rectified item, supporting its use as a quality assurance screen.
31 May 2026
Read appraisal →European radiology experimental
Towards an accessible, centralised, searchable database for AI courses in Europe: the Artificial Intelligence in Medical Imaging and Radiation Oncology Education (AIMIROE) project.
OBJECTIVE: Artificial intelligence (AI) is transforming medical imaging and radiation oncology, yet limited understanding and access to education hinder adoption. This study, led by the European Society of Medical Imaging Informatics (EuSoMII) in collaboration with the European Federation of Radiographer Societies (EFRS), aimed to create an accessible, centralised, searchable database including all AI courses in Europe. MATERIALS AND METHODS: An electronic survey was developed to collect data on European AI course characteristics, such as format, delivery, content, target audience and European Qualifications Framework (EQF) level. This was disseminated via purposive sampling through social media and mailing lists of the EuSoMII and the EFRS between September 2024 and January 2025. Quantitative data were analysed using descriptive statistics and visual representations using Python Seaborn and Geopandas. RESULTS: This study identified 29 AI courses in Europe. Of them, 53.6% were offered by universities. Courses targeted radiographers (59%), medical physicists (52%), and radiologists (41%), mainly at EQF level 7 (44.4%). Most courses were standalone (65.6%) and online (55.1%), while 41.3% were free of charge. English was the primary language of delivery (79%). CONCLUSIONS: Different AI courses across Europe offer some entry-level knowledge but are often short in duration. Expanding formats, building practical competencies, providing multilingual access, and European-wide reach are essential for meaningful, practical, and equitable AI integration. RELEVANCE STATEMENT: With the scaling-up of AI adoption in medical imaging and radiation oncology, there is a variety of AI education provisions currently available. Accessing these options via an open, centralised, regularly updated database enables people to make an informed decision about their training and practise safely and meaningfully. KEY POINTS: We identified 29 different AI European courses varying in language, content, and delivery. Many clinical practitioners and researchers are unaware of these resources. We need a centralised database for customising AI learning choices and guiding future course design.
31 May 2026
Read appraisal →Medicine
A bibliometric analysis of artificial intelligence in anatomy education: Current situation, hot spots, and global trends
INTRODUCTION: Artificial intelligence (AI) is increasingly being integrated into anatomy education, yet a comprehensive overview of the field's development and emerging trends remains lacking. This study identifies research hotspots and trends in AI applications in anatomy education through a bibliometric analysis. METHODS: English-language publications on AI in anatomy education were systematically collected from the Web of Science database. Using bibliometric tools, including R, VOSviewer, CiteSpace, and Excel, data were synthesized to explore global research trends and focal areas. RESULTS: A total of 184 papers published between 2005 and 2024 were included. The United States emerged as the leading contributor in terms of publication output and citation impact. Over the past 2 decades, research focus has shifted from general medical education applications toward AI-driven image segmentation, deep learning, and surgical guidance. More recently, large language models (e.g., ChatGPT) have begun to attract attention in anatomy education. CONCLUSION: This bibliometric analysis maps the intellectual landscape of AI in anatomy education, identifying key thematic shifts and emerging frontiers. The findings provide a foundation for guiding future research directions in this rapidly evolving field.
31 May 2026
Read appraisal →World journal of urology
Assessing multiple chatGPT versions on novel content in the Taiwan urology board examination: accuracy, speed, and domain-specific performance
PURPOSE: Large language models demonstrate increasing utility in healthcare; however, their capacity to handle newly developed medical content beyond training data boundaries remains unclear. This study evaluated the performance of four ChatGPT models on 120 newly developed questions from the 2024 Taiwan Urology Board Examination, all created after the models' October 2023 training cutoff, thereby reducing the risk of prior model exposure. METHODS: Model performance was assessed using accuracy and processing time. Of 150 examination items, the first 120 newly developed questions constituted the primary analysis set; the remaining 30 previously used archival questions were excluded to reduce potential bias from prior exposure. The primary paired accuracy comparison evaluated o1-preview versus GPT-4o across all 120 questions. Additional analyses across 12 urological subspecialties and question-complexity strata were treated as exploratory. RESULTS: Across all 120 questions, o1-preview achieved 66.7% accuracy and significantly outperformed GPT-4o (55.8%; p = 0.012), although with longer processing time (19.20 vs. 14.94 s). Performance varied significantly across 12 urological subspecialties (p < 0.001). Unlike the other tested models, o1-preview showed slightly higher accuracy on high-complexity than on low-complexity questions (68.3% vs. 65.0%). On high-complexity surgical anatomy items, o1-preview achieved 80.0% accuracy, whereas GPT-4o and GPT-4o mini both scored 0.0% (p = 0.024). CONCLUSION: On this newly developed post-cutoff, text-based urology board question set, o1-preview achieved higher overall accuracy than GPT-4o, particularly on high-complexity surgical anatomy items, at the cost of longer response times. These findings suggest that reasoning-oriented models may offer advantages for selected specialty-level assessment tasks, although generalizability to other languages, modalities, and clinical settings requires further validation.
30 May 2026
Read appraisal →JMIR medical education
Exploring the Feasibility of an Examiner-Worn Neck-Mounted Camera for Objective Structured Clinical Examination Assessment: Pilot Feasibility Study
BACKGROUND: The Objective Structured Clinical Examination (OSCE) is a prevalent method for evaluating clinical competence in medical education. As OSCEs become increasingly standardized and resource intensive, alternative evaluation methods are being explored, particularly because of the limited availability of certified examiners. However, few studies have investigated whether wearable technologies can support OSCE assessment. Wearable devices may provide a means of recording clinical skills from the examiner's perspective. OBJECTIVE: This pilot study, conducted in 2024, aimed to investigate the feasibility of using an examiner-worn neck-mounted camera for recording OSCE scenarios and to evaluate the evaluability of clinical performance from the recorded footage. METHODS: In total, 9 experienced medical educators participated in a simulated OSCE scenario involving electrocardiogram lead placement. All participants completed the initial live assessment and the postuse questionnaire, while 8 of 9 (89%) participants completed the subsequent video-based reassessment. Video recordings from both a fixed camera and a neck-mounted camera (THINKLET) were used to assess the evaluability of each OSCE item. Following a washout period, evaluators reassessed the neck-mounted camera recordings by using the original checklist, while fixed-camera recordings were used to judge the evaluability of each item. Agreement between live and video-based scoring was analyzed using percent agreement and the Cohen κ coefficient. A postevaluation questionnaire captured evaluators' experiences with the wearable device. RESULTS: Cohen κ ranged from 0.258 to 0.913 (mean 0.67, SD 0.20). Across checklist observations, more items were judged to be evaluable in the neck-mounted camera recordings than in the fixed-camera recordings, particularly for tasks requiring observation of fine motor skills. Evaluators reported generally positive experiences with the device, although some noted issues related to audio quality, comfort, posture restriction, and limited visibility at low angles. CONCLUSIONS: Although further investigation is needed, this pilot study suggests that an examiner-worn neck-mounted camera may be a valuable supplementary assessment tool for selected OSCE tasks. Further work is needed to refine the device, standardize recording protocols, and clarify how it can best support review and verification alongside live evaluation.
29 May 2026
Read appraisal →JMIR formative research
Virtual Reality-Based Training in Radiologic Technology for Contrast-Enhanced Computed Tomography Brain Imaging: Randomized Controlled Trial
BACKGROUND: Radiologic technology (RT) education faces challenges in bridging theory and practice due to limited clinical opportunities. While virtual reality (VR) enables safe and repeatable practice, a systematic instructional design framework is needed to develop scalable, procedure-focused modules. OBJECTIVE: This study evaluates the Radiologic Technology Virtual Reality (RTVR) framework that integrates 360-degree video capture, instructional overlays, interactive assets, and an immersive content authoring platform to deliver a contrast-enhanced computed tomography (CECT) brain scan module. METHODS: In this open-label, parallel-group, randomized controlled trial, 36 year-2 and year-3 RT students with no prior clinical training in diagnostic radiology at a university hospital in Thailand were randomly allocated (1:1) to a VR group or a conventional document-based instruction (control) group. The VR group completed the VR module, a grounded instructional design framework using 360-degree videos and a structured prebrief and debrief, for 20 minutes using a head-mounted display. The control group studied standard curriculum materials for the same duration. Blinding of participants was not possible. Outcome assessment was blinded. The primary outcome was declarative knowledge gain, assessed using a 20-item multiple-choice test before and after intervention. Secondary outcomes included technology acceptance, student satisfaction, and physiological responses during VR immersion. RESULTS: All 36 randomized participants (VR: n=18, control: n=18) completed the study and were included in the analysis. Experts validated the module as suitable and highly appropriate. Students reported high technology acceptance and satisfaction. Both VR and conventional methods produced substantial gains in declarative knowledge. No statistically significant difference in knowledge gain was detected between groups (test × group: unstandardized regression coefficient β=.056, 95% CI -1.360 to 1.473, P=.94). Year-2 students, who had less prior clinical exposure, showed larger pretest to posttest knowledge gains compared to year-3 students. Physiological monitoring showed a reduction in heart rate across the session, while blood pressure remained stable. No adverse events or VR-related discomfort requiring discontinuation was observed. CONCLUSIONS: The RTVR framework, which uses a real 360-degree video of authentic clinical settings, offers a scalable approach to procedural VR content creation without requiring specialist technical skills, distinguishing it from prior VR studies in radiography. These findings support the RTVR framework as a feasible, evidence-informed supplement to RT curricula for knowledge-focused procedural teaching, with learning outcomes comparable to those of conventional instruction in this context.
29 May 2026
Read appraisal →JMIR medical education
Generative AI's Impact on the Mental Health of Medical Students: Scenario Analysis
BACKGROUND: Generative artificial intelligence (AI) is quickly changing medical education, even as medical students still face high levels of stress, anxiety, and burnout. These simultaneous trends-technological upheaval and ongoing mental health issues-bring up important questions about how future doctors will be trained and supported. Understanding how these factors might influence each other is crucial for developing resilient, future-ready medical education systems. OBJECTIVE: We carried out a foresight study using scenario analysis to examine potential futures at the crossroads of generative AI adoption and medical students' mental health. An initial environmental scan of the literature was conducted to pinpoint emerging trends and weak signals related to AI in medical education and well-being. These phenomena were categorized within a macro-meso-micro framework and analyzed through a multilevel sociotechnical change perspective. The study focused on 2 principal factors: the extent of generative AI integration into medical curricula and the availability of mental health support, as key drivers and critical uncertainties influencing future trajectories. METHODS: These dimensions resulted in 4 distinct scenarios: Analog Happiness (high support and low AI integration), Gen AI Paradise (high support and high integration), Disconnected Struggles (low support and low integration), and Gen AI Takeover (low support and high integration). Each scenario demonstrates how various institutional responses can impact students' digital readiness, psychological well-being, and professional growth. For each one, we identified the main systemic risks and suggested immediate institutional measures to address them. RESULTS: The findings suggest that technological innovation and mental health support must coevolve in medical education. Prioritizing one without the other risks producing either digitally unprepared or emotionally fragile physicians. Faculty readiness, ethical frameworks, and participatory curriculum design are critical to ensuring balanced integration. We formulated practical recommendations tailored to students, educators, and other stakeholders to guide balanced adaptation. CONCLUSIONS: Generative AI is more than just an additional tool in medical education; it is a systemic force that redefines how future physicians learn and operate. If technological change and student mental health are tackled separately, medical education risks creating graduates who are either unprepared for digital demands or mentally overwhelmed. This study highlights key systemic risks and suggests initial institutional steps to address them, providing a foresight-driven framework to assist educators and policymakers in responsible AI integration while safeguarding the well-being of future doctors.
28 May 2026
Read appraisal →JMIR perioperative medicine
AI-Generated Avatar Videos for Postoperative Patient Education Among Health Care Workers: Pilot Randomized Controlled Trial
BACKGROUND: Effective postoperative communication is vital for patient recovery, yet traditional text-based discharge instructions often lead to poor comprehension and adherence, particularly among patients with limited health literacy. Although educational videos improve understanding and retention, their widespread use has been hampered by high production costs. Generative artificial intelligence (AI) offers a scalable solution for creating engaging video content. OBJECTIVE: The primary objective of this pilot study was to assess the feasibility of creating and deploying AI-generated, avatar-led videos for postoperative instruction delivery. Secondary objectives included comparing knowledge retention, engagement, perceived clarity, and user experience between AI-generated video and traditional text-based handout formats among health care workers. METHODS: In this randomized pilot study, 38 health care worker volunteers were recruited as a convenience sample to pilot-test the intervention before patient implementation. Participants were assigned to either a text handout group (n=19, 50%) or an AI-generated video group (n=19, 50%). Both groups received information on 10 common postoperative topics. The primary outcome was objective knowledge, assessed via a 10-item quiz. Secondary outcomes, measured through surveys with 5-point Likert scales, included engagement time, subjective engagement, perceived clarity, usefulness, confidence in understanding, and information retention. Qualitative feedback was also collected. RESULTS: Objective knowledge quiz scores did not differ significantly between groups (mean 8.89, SD 1.20 for the AI-generated video group vs mean 8.21, SD 1.78 for the text handout group; P=.17; Cohen d=0.45). Participants in the AI-generated video group demonstrated significantly higher engagement time (mean 15.11, SD 7.78 minutes vs mean 8.84, SD 4.03 minutes; P=.004; Cohen d=1.04). They also rated instructions as significantly clearer (mean 4.63, SD 0.50 vs mean 4.00, SD 0.82; P=.007; Cohen d=0.93), more engaging (mean 4.05, SD 0.78 vs mean 3.32, SD 1.00; P=.02; Cohen d=0.81), and more effective for retention (mean 4.42, SD 0.84 vs mean 3.37, SD 0.68; P<.001; Cohen d=1.38). Qualitative feedback highlighted the engaging nature of AI-generated videos but noted areas for avatar refinement. CONCLUSIONS: In this pilot study with health care workers, AI-generated avatar videos did not improve objective knowledge scores but significantly enhanced engagement, perceived retention and perceived clarity (Cohen d=0.81-1.38). Future studies in actual patient populations with diverse health literacy levels are needed to determine whether these engagement advantages translate into improved knowledge outcomes.
28 May 2026
Read appraisal →Medical education online
AI-assisted case-based learning and flipped classroom to improve clinical decision-making: a randomized controlled trial in reproductive medicine
BACKGROUND: Efficient training of reproductive medicine clinicians is critical in the context of declining global fertility and increasing infertility. Traditional lecture‑based instruction often fails to sufficiently develop clinical decision‑making skills within limited residency rotations. Innovative strategies that integrate artificial intelligence (AI) with case‑based learning (CBL) and flipped classroom (FC) formats may enhance clinical reasoning, however rigorous evidence in reproductive medicine education remains limited. METHODS: We conducted a randomized controlled trial involving 50 obstetrics and gynecology residents at the First Hospital of Jilin University. Participants were randomly assigned to an AI‑assisted CBL+FC group or a traditional lecture control group. The AI‑assisted CBL+FC group completed pre‑class interactive case work with virtual standardized patients on the DoctorU platform and case analyses on the Superstar Learning platform, followed by interactive in‑class discussions. Primary outcomes included post‑course theoretical knowledge tests, Mini‑Clinical Evaluation Exercise (Mini‑CEX), and Objective Structured Clinical Examination (OSCE) scores. Secondary outcomes assessed learner motivation, clinical thinking, self‑directed learning, and perceived course effectiveness using a 5‑point Likert scale. RESULTS: Baseline characteristics were comparable between groups. After the intervention, the AI‑assisted CBL+FC group achieved significantly higher theoretical test scores than the control group. The AI‑assisted CBL+FC group also demonstrated superior overall clinical competence in Mini‑CEX assessments and higher OSCE total scores. Participants in the AI‑assisted CBL+FC group reported greater improvements in learning motivation, clinical reasoning, self‑directed learning, and perceived course effectiveness. CONCLUSIONS: The AI‑assisted CBL+FC instructional model significantly enhances theoretical knowledge, clinical decision‑making skills, and learner engagement among reproductive medicine residents. This blended learning model offers an efficacious and generalizable methodology for training practitioners to address the evolving clinical requirements within contemporary fertility care.
28 May 2026
Read appraisal →Journal of radiation research
Feasibility of retrieval-augmented generation for large language models with Japanese input in radiotherapy
Large language models (LLMs) have recently gained attention for their potential. However, concerns remain regarding their reliability due to limitations such as hallucinations and insufficient domain-specific knowledge. Retrieval-augmented generation (RAG) has emerged as a promising approach, enabling LLMs to reference external knowledge sources and generate accurate outputs. We aimed to clarify the potential of RAG-enhanced LLMs with Japanese input in the field of radiotherapy. This was assessed by evaluating performance on three certification examinations in Japan: the Japanese Medical Physicist Examination, the Japanese Board Examination for Radiologists, and the Japanese Board Examination for Radiation Oncologists. In this study, we constructed a RAG system named Rad-Hub, consisting of a Japanese Radiotherapy Knowledge Database (JRKD) and a retrieval framework built on Microsoft Azure. The JRKD was populated with 32 Japanese radiotherapy textbooks and clinical guidelines. We assessed its utility by inputting all multiple-choice questions from the three examinations into ChatGPT-4o, both with and without Rad-Hub, and recording the answers. They were then compared with reference answers determined by experienced medical physicists and radiation oncologists. Rad-Hub improved accuracy across all examinations. Accuracy increased from 77.0% ± 2.6% to 84.6% ± 1.5% in the Medical Physicist examination, from 74.9% ± 2.0% to 82.1% ± 1.1% in the Radiologist examination, and from 55.6% ± 4.4% to 71.7% ± 4.5% in the Radiation Oncologist examination. Performance gains ranged from 7.2% to 16.1%. These findings highlight the potential of RAG-enhanced LLMs, particularly ChatGPT-4o with Rad-Hub, for integration into radiotherapy applications, such as educational and clinical decision assistance.
27 May 2026
Read appraisal →Clinical and experimental dermatology
A systematic review of the barriers to diagnosis of vulval lichen sclerosus in primary care
BACKGROUND: Vulval lichen sclerosus (VLS) is a chronic, inflammatory genital skin condition causing itch, pain, anatomical changes and increased risk of vulval cancer. Diagnostic delay and misdiagnosis are common. Once diagnosed, VLS can be effectively treated using very strong topical corticosteroids. Most women with symptoms of VLS first present to primary care in the UK. OBJECTIVES: To identify patient and professional perspectives on barriers to diagnosis of VLS in primary care through systematic review and thematic synthesis of the literature. METHODS: Separate literature searches of seven databases relevant to patient and professional perspectives were conducted. Two reviewers screened titles and abstracts, with one performing a full text review. Data extracted were coded 'line by line', codes were organized into descriptive themes and subsequently developed into analytical themes. RESULTS: We identified 2468 references; a total of 56 studies met inclusion criteria. Six analytical themes were developed: (i) a medically challenging diagnosis; (ii) cultural and social taboos; (iii) education and knowledge gaps; (iv) feelings and attitudes; (v) inadequate health systems; and (vi) challenges in female genital examination. CONCLUSIONS: This review highlights obstacles for women in achieving a diagnosis of VLS. Education and knowledge gaps were reported by clinicians and patients. Clinicians lack knowledge of vulval skin disease and patients lack knowledge of vulval anatomy. Targeted, comprehensive education for clinicians could expedite diagnosis. Dismissive clinician attitudes compound patient feelings of anxiety and embarrassment, reinforcing taboos and stigma. Acknowledgement of embarrassment and stigma validates feelings, improving patient interactions. Future research priorities should include the development of a diagnostic tool and implementation of a complex intervention to expedite diagnosis.
27 May 2026
Read appraisal →Scientific reports
Impact of a structured case report on self-reported responses to simulated emergency scenarios: a randomized survey-based study
Case reports are a long-standing component of medical research, but their association with self-reported responses to simulated clinical scenarios remains underexplored. This study investigated whether exposure to a structured case report influences simulated emergency medical decisions. This randomized survey-based study was conducted among licensed physicians between March and May 2025. Participants were randomly assigned to an intervention group, which received a structured case report on blunt neck trauma, or a control group, which did not. Both groups subsequently provided self-reported Likert-scale responses to identical simulated emergency scenarios, covering five domains: local trauma consequences, accompanying injuries, diagnostic methods, airway management strategies, and hospital selection. Responses were collected on Likert scales. Group differences were assessed using Mann-Whitney U tests, t-tests, and chi-squared tests; prespecified exploratory subgroup analyses examined the moderating role of clinical experience. Sixty-three participants completed the study. Baseline demographics and qualifications did not differ significantly between groups. Exposure to the case report was associated with statistically significant differences in self-reported responses to simulated scenarios, with the most pronounced associations in airway management strategies (all five items statistically significant, median effect size r = 0.44). Intervention participants assigned higher ratings to maintaining spontaneous breathing and supraglottic airway use, while assigning lower appropriateness to endotracheal intubation and cricothyrotomy. Moderate associations were observed in diagnostic choices (e.g., pathological breath sounds, ultrasound use) and hospital selection (e.g., ECMO availability). No consistent effects were found for local or accompanying injuries. Exploratory stratified analyses revealed that junior physicians (≤ 5 years of practice) appeared more responsive, with significant differences across multiple domains and larger effect sizes (median r > 0.6). In contrast, no statistically significant between-group differences were detected in the senior (> 15 years) subgroup, although this exploratory analysis was limited by small subgroup size. Structured case reports may influence self-reported responses to simulated emergency scenarios, particularly among less experienced clinicians. These findings suggest that the educational impact of case-based learning formats may vary depending on the level of clinical experience, but do not allow conclusions about real-world clinical behavior or patient outcomes. Future work should further investigate adaptive case report formats and their potential integration into emergency medicine training.Trial registration: German Clinical Trials Register (DRKS00038961), registered von 13 January 2026.
27 May 2026
Read appraisal →Journal of medical Internet research
Training Clinicians in Private Practice in Family-Based Treatment for Anorexia Nervosa: Randomized Controlled Trial Comparing Two Online Approaches
BACKGROUND: There is a critical need to disseminate efficacious psychosocial treatments for mental disorders because there is a significant gap between evidence-based treatment (EBT) approaches and usual clinical practice. To address this gap, cost-effective, efficient, and scalable methods of training mental health clinicians in EBT are needed. One example of the need to improve dissemination and implementation of psychosocial treatments is for adolescents with anorexia nervosa (AN), a serious mental disorder with an incidence rate of about 1% that can become life-threatening. Based on outcomes from a series of randomized controlled trials (RCTs), an EBT for adolescents with AN is family-based treatment (FBT); however, few therapists are trained in the approach. Some studies suggest that online training is feasible for training clinicians treating eating disorders, including pilot data related to FBT specifically, but RCTs examining different training formats for FBT to improve fidelity and patient outcomes are needed. OBJECTIVE: This study compared 2 different formats for delivering online training in FBT to therapists treating adolescents with AN and planned to assess the feasibility of the 2 training formats, as well as to examine whether either approach was superior in improving fidelity to FBT or patient outcomes. METHODS: Participants were 123 mental health therapists licensed in the United States in private practice with no previous FBT training. Therapists were randomized to either (1) a webinar training lecture series or (2) an interactive e-training on-demand program (ET-FBT) with an additional focus on key FBT interventions. Both groups were offered up to 12 one-hour group-based clinical case consultation (CCC) sessions posttraining. We examined the feasibility and acceptability of the online training programs and posttraining outcomes in fidelity to key components of FBT, self-efficacy, and working alliance. We explored rates of patient early response (weight gain of 2.4 kg at session 4) in adolescent patients with AN treated after FBT training during CCC. RESULTS: Both online trainings had a high completion rate of 95% (117/123), with CCC completion at 38% (47/123). Both programs showed significant improvements within randomized groups in therapists' fidelity, self-efficacy, and working alliance. Working alliance improved significantly more in the ET-FBT group, but there were no other significant differences between training groups. Early response rates doubled posttraining and CCC (16%-34%), regardless of randomized training format, a rate that is similar to that achieved by therapists in RCTs examining FBT treatment outcomes. CONCLUSIONS: It is feasible to deliver online training in FBT to clinicians in private practice in 2 different formats, and both trainings led to significant improvements in fidelity, self-efficacy, working alliance, and patient outcomes. Future studies should address challenges in patient recruitment for posttraining CCC and refine CCC implementation to maximize training effects and efficiency.
26 May 2026
Read appraisal →Journal of robotic surgery
Extended reality and emerging artificial intelligence in orthopedic surgical training: a scoping review of educational outcomes
Immersive technologies have gained increasing relevance in orthopedic surgical education; however, the scope, outcomes, and maturity of extended reality (XR) and artificial intelligence (AI) applications remain heterogeneous. To map the educational applications, learner populations, outcome measures, and research gaps related to the use of XR and emerging AI tools in orthopedic surgical training. A scoping review was conducted following Joanna Briggs Institute methodology and reported according to PRISMA-ScR guidelines. PubMed, Scopus, and ScienceDirect were searched for English and Spanish studies published between 2015 and 2025. Fifty-four studies involving 3,066 participants were included. Virtual reality (VR) was the predominant modality (83.3%), followed by augmented reality (31.4%), while AI-based applications were infrequently reported. XR-based training was most commonly evaluated in trauma surgery, arthroscopy, and arthroplasty, primarily among medical students and residents. Most studies reported improvements in simulation-based technical performance metrics, whereas evidence on clinical outcomes, long-term skill retention, and cost-effectiveness was limited. XR-particularly VR-represents the most mature immersive technology in orthopedic surgical education. AI applications remain emergent and primarily supportive. Future research should prioritize standardized outcome measures, multicenter designs, and evaluation of long-term educational and clinical impact.
25 May 2026
Read appraisal →BMJ health & care informatics
Beyond the digital health tsunami: reaffirming biomedical and health informatics as the scientific foundation of digital healthcare transformation
Digital health (DH) has emerged as the dominant terminology for technology-enabled healthcare, reshaping institutional discourse, educational programmes and policy agendas. DH is often portrayed as a novel discipline that could supersede Biomedical and Health Informatics (BMHI), creating conceptual ambiguity and the risk of weakening scientific rigour in the design, evaluation and governance of digital interventions. This paper clarifies BMHI's disciplinary identity, characterises DH as a practice-oriented and implementation-oriented domain, and establishes the epistemic relationship between the two in order to inform academic strategy, curricula and professional identity. A comparative conceptual analysis examined scope, theoretical foundations, methodological approaches, educational frameworks, professional structures and stakeholder ecosystems in both domains, informed by recent debates on degree programmes and workforce training. We found that BMHI is a mature scientific discipline with explicit theoretical foundations encompassing data representation, knowledge modelling, clinical reasoning, decision support, interoperability, sociotechnical analysis, evaluation science, safety, ethics and governance. DH, by contrast, represents an implementation-oriented translational domain that operationalises BMHI through products, services and organisational transformation (eg, telehealth, mobile applications, artificial intelligence-enabled clinical services). While DH has amplified visibility and accelerated adoption, it lacks autonomous theoretical foundations and depends on BMHI for scientific validity, safety and sustainability. Three evolutionary scenarios are examined: DH absorbing BMHI (epistemically incoherent), convergence as parallel disciplines (conceptually flawed), and reintegration of DH within BMHI as its applied layer (scientifically coherent and strategically sustainable) but requiring disciplinary communication, curricular alignment and institutional leadership explicitly positioning DH as a translational layer of BMHI.
24 May 2026
Read appraisal →Studies in health technology and informatics
Interoperability Skills for Digital Health: A Reference Model from the XiA Project
As healthcare systems advance through digital transformation, achieving interoperability across Health Information Systems (HIS) relies on skilled professionals who enable effective integration and data exchange. Under the scope of the Xpanding Innovative Alliance (XiA) project, this article introduces a Reference Model for Interoperability Skills that defines the core skills needed by professionals to support interoperable digital health ecosystems. Through a systematic literature review, the model provides a structured view of competencies across professional profiles, grounded in international best practices. The proposed model serves as a strategic tool for workforce development, curriculum design, and organizational capability assessment. By promoting a shared understanding of interoperability, it supports the creation of a skilled, adaptable, and collaborative workforce capable of advancing integrated, data-driven healthcare across Europe.
24 May 2026
Read appraisal →Studies in health technology and informatics
Training Future Health and Information Technologies Professionals on the European Health Data Space.
The European Health Data Space (EHDS) furthers the EU's digital health transformation by enabling secure access to electronic health data by facilitating environments for health data sharing. The topic of EHDS is relatively new and remains underrepresented in most academic curricula in both medical and informatics fields. This study evaluates the impact of a structured educational intervention to improve awareness, understanding, and preparedness among future health and information technology professionals to engage with EHDS-related systems and policies. Conducted at the University of Oulu, the intervention included training sessions, practical examples, and interactive discussions on topics such as the primary and secondary uses of health data, legal frameworks, and technical infrastructure. The survey's results showed significant gains in students' conceptual understanding of EHDS, particularly in distinguishing between primary and secondary uses of health data. We found that students with a European background reported slightly higher familiarity with EHDS-related rights and frameworks. The findings underscore the importance of embedding EHDS education in academic programs to build a digitally competent, informed workforce capable of supporting EHDS implementation. This intervention contributes to the portfolio of learning materials, developed by the SUSA project to integrate digital health policy and governance into multidisciplinary higher education curricula across the EU.
24 May 2026
Read appraisal →Prehospital and disaster medicine
Evaluating Nursing Students' Performance and Retention of BLS/AED Knowledge and Skills One Year After Training: A Randomized Controlled Trial
INTRODUCTION: Nurses often serve as the initial responders in cases of cardiac arrest, making cardiopulmonary resuscitation (CPR) competence essential to effective resuscitation. It is therefore important for nursing students to possess sufficient CPR knowledge and skills for future clinical practice. OBJECTIVE: The aim of this study was to examine whether CPR post-qualification training is needed in maintaining knowledge and skills and if face-to-face or online training is more effective as an educational method in preserving CPR knowledge and skills in nursing students. METHODS: A three-group, parallel randomized-controlled, single-blind design was used. The participants were 133 nursing students, randomly assigned to the face-to-face group (n = 43), the e-learning group (n = 43), and the control group (n = 47). Before randomization, all participants (n = 133) successfully completed the European Resuscitation Council (ERC) standard five-hour Basic Life Support/Automated External Defibrillation (BLS/AED) course (t0) and a questionnaire based on the 2021 ERC Guidelines to assess their knowledge. Six months later, Group A received face-to-face training, Group B received e-learning training, and Group C had no intervention. Six months after interventions, all participants (n = 133) were re-assessed on the same questionnaire, and they were given the same scenario of cardiopulmonary arrest that was used during the initial BLS course to assess the skills that they retained (t1) with the use of the ERC CPR/AED 11-item checklist. The collected data were analyzed with inferential "among group" analysis involving Kruskal-Wallis's and Pearson's Chi-Squared test and inferential "within group" analysis including Wilcoxon's Signed-Rank and McNemar's test. Multiple linear regression was used for adjusting demographic characteristics. RESULTS: Based on pairwise differences between independent groups, both intervention groups presented higher scores in knowledge at t1 (P < 0.001) and in skills at t1 (P < 0.001) compared to the control group. Moreover, both training methods demonstrated comparable effectiveness. Based on comparisons between paired groups, there was also a statistically significant decrease in the Skill Score in the control group after one year (P < 0.001). Most skills were notably higher, primarily in the e-learning group, and to a lesser extent in the face-to-face group. In specific, intervention groups demonstrated statistically significant improvement in nine of the eleven assessed skills (all P < 0.05). CONCLUSION: The current study showed that post-qualification training is needed to retain CPR knowledge and skills of nursing students, and that face-to-face and e-learning training had similar outcomes.
23 May 2026
Read appraisal →Journal of radiological protection : official journal of the Society for Radiological Protection
The integration of artificial intelligence in radiation medical physics: insights from an international survey with regional variability
Artificial intelligence (AI) is considered to be a leading technology in radiation medical physics, which has the potential for improving efficiency and precision in imaging, radiotherapy, and nuclear medicine. Nonetheless, its application in the clinical setting is hindered by education, regulation, and ethical issues. To evaluate the views of medical physicists on AI adoption, potential issues, perceived advantages, ethical issues, and training needs. A cross-sectional survey in the form of an online questionnaire was distributed internationally to practicing medical physicists, representing specialties in radiation therapy, diagnostic imaging, and nuclear medicine. The instrument was used to capture demographic variables and AI familiarity, perceived benefits and barriers, ethical issues, training preferences, and future expectations. Descriptive statistics, chi-square tests, and binary logistic regression were performed. Open-ended responses were analyzed using thematic analysis. Most respondents were moderately familiar with AI, but nearly half had not incorporated AI into their practice despite being interested. Adoption patterns differed significantly across geographic regions, with higher usage reported in developed countries. AI familiarity was strongly associated with adoption. The most prominent benefits noted were dose calculation accuracy, patient safety, and workflow efficiency. In contrast, the main obstacles were inadequate training, high implementation costs, absence of standardized protocols, and low availability of advanced equipment. Ethical apprehensions focused on accountability and reduced human oversight. Preferred educational strategies included hands-on workshops and on-the-job training. Regional analysis and modeling revealed variability in AI adoption and identified key predictors, including AI familiarity and specialization. Results indicate that AI is considered an important technology in radiation medical physics. However, implementation was influenced by regional and professional differences. These findings highlight the necessity to expand AI education, create standard training programs, improve infrastructure, and provide clearer governance frameworks to support safe and responsible AI integration.
22 May 2026
Read appraisal →Postgraduate medical journal
Peer review in the age of artificial intelligence: a comparative study of human and AI-generated review reports
BACKGROUND: Peer review is central to maintaining scientific quality and helps editors make decisions. However, the volume of scientific publications continues to rise, placing pressure on the peer review system. With the rise of generative AI, its role in supporting peer review is gaining attention. This study aims to compare human-written and AI-generated peer review reports. METHODS: We analysed 398 peer review reports linked to 119 research articles published in BMJ Open in 2024. Publicly available reports and manuscripts were included. Editorials, corrections, and protocols were excluded. AI reports were generated using ChatGPT. All reports were anonymized and assessed by two independent reviewers. We conducted a hybrid thematic analysis. Frequencies of themes were calculated and compared by reviewer type. For quantitative comparison, we used the Mann-Whitney U test to assess differences in review quality scores and Fisher's exact test to compare the distribution of themes. All analyses were conducted using R software. RESULTS: Human reviewers gave more detailed and diverse comments. They addressed deeper issues like interpretation, originality, and applicability. AI reviews covered more sections but focused on routine or structural elements. AI outperformed slightly in format-related domains. Co-occurrence analysis showed human reviews linked diverse themes, while AI comments were structurally clustered. Shannon Index confirmed that human reviews were more thematically diverse. CONCLUSIONS: AI can support peer review by screening for basic errors. However, it lacks insight, critical judgment, and contextual awareness. Human input remains essential for meaningful review. Review-specific AI tools that preserve confidentiality are needed for future integration.
22 May 2026
Read appraisal →JMIR medical education
A Competency Framework for Medical AI Education: Mixed Methods Study
BACKGROUND: Although artificial intelligence (AI) is increasingly adopted in health care, clinicians face barriers, including insufficient understanding, limited trust, and challenges in interpreting AI outputs. Existing frameworks, such as the United Nations Educational, Scientific and Cultural Organization (UNESCO) AI competency framework, lack clinical specificity. Additionally, there remains limited evidence on framework-based training programs for medical professionals. OBJECTIVE: This study aimed to (1) develop a medical AI competency framework and (2) apply the framework to design an AI training program and pilot 1 module. METHODS: We conducted a mixed methods study comprising 2 phases. In Study 1, we developed a medical AI competency framework by integrating the UNESCO AI framework with the Miller pyramid model. The framework was refined through expert input from 24 stakeholders (6 hospital administrators, 8 medical professionals, and 10 university instructors). Expert responses were analyzed using deductive content analysis based on predefined codebooks. In study 2, we designed an AI training program based on the framework, and evaluated it using a 2-round Delphi process. Nine educators with expertise in instructional design, medical education, and AI participated in the Delphi study. Consensus in round 1 was defined as an IQR≤1, agreement score proportion >75%, and full-score frequency >49.23%; in round 2, consensus was defined as agreement score proportion >80%. A pilot workshop with 28 participants and 4 instructors assessed the feasibility of 1 module using self-reported measures of satisfaction, engagement, and confidence. RESULTS: A 6D 4-level medical AI competency framework was developed. Among the 24 experts, 19 (79.17%) mentioned competencies related to AI foundations, and 23 (95.83%) mentioned competencies related to application skills. The framework was translated into a 5-module training program, covering patient-centered and ethical AI, privacy and security, medical AI applications, bias and health equity, and generative AI in health care. Each module included 5 elements: content, learning goals, teaching activities, learning resources, and assessment. The Delphi process achieved complete consensus across all 25 elements of the training program. The pilot workshop indicated high participant satisfaction (mean 4.00, SD 0.52), good engagement (mean 3.80, SD 0.71-mean 4.05, SD 0.51), and moderate self-reported confidence (mean 3.63, SD 0.53). These findings suggest that the module was feasible, although outcomes should be interpreted cautiously given the self-reported and short-term nature of the evaluation. CONCLUSIONS: The framework provides a structured reference for AI training program design in medical education. The workshop findings provide preliminary support for the feasibility of the program's technical module, while also highlighting the need for broader and longer-term evaluations. Future work should expand the framework and training program to new regions and delivery formats (eg, semester-long courses and continuing medical education) and evaluate their long-term impact.
21 May 2026
Read appraisal →PloS one
Investigating ChatGPT-mediated mind mapping to facilitate EFL learners' reading comprehension
Mastering Reading Comprehension (RC) is a significant challenge for English as a Foreign Language (EFL) learners. This quasi-experimental mixed-methods study examined the potential effectiveness of a ChatGPT-mediated mind mapping technique in enhancing RC among EFL students at a public university in Saudi Arabia. Sixty male preparatory-year students were assigned to two groups: an experimental group (n = 30), which took part in a 10-week intervention in ChatGPT-mediated mind mapping, and a control group (n = 30), which was taught mind mapping through conventional methods. Data were gathered through pre- and post-tests of RC together with semi-structured interviews. Post-test RC scores were significantly higher in the experimental group than in the control group (U = 180.00, p < .001), with a medium-to-large effect size (r = 0.52). The qualitative data showed that students found the technique useful for breaking down complex ideas and for making the relationships between concepts in the text visible. At the same time, they reported difficulties with the accuracy of the AI output, with comprehending dense content, and with technology access. Read through the lenses of Sociocultural Theory and Cognitive Load Theory, the findings suggest that ChatGPT-mediated mind mapping can serve as a useful pedagogical tool for supporting RC. Teachers are therefore encouraged to incorporate the technique into their instructional practice while offering the support needed to address the challenges identified here.
21 May 2026
Read appraisal →JMIR formative research
Metaverse-Based Virtual Reality for Remote Anatomy Education: Pilot Randomized Controlled Trial
BACKGROUND: Traditional anatomy teaching relies on cadaveric dissection and 2D resources, which often require in-person attendance and may limit spatial understanding. Virtual reality (VR) provides an immersive, remote alternative that supports 3D visualization from home. Recent evidence suggests that while VR may yield comparable factual knowledge gains to 2D methods, its primary value lies in enhancing learner engagement, motivation, and perceived educational value. OBJECTIVE: This pilot randomized controlled trial compares remote synchronized VR with didactic animated anatomy lectures for the teaching of tracheostomy anatomy. METHODS: Participants were recruited via convenience sampling through the VRiMS (Virtual Reality in Medicine and Surgery) Surgical Society network. All participants first attended a synchronous 20-minute online lecture delivered by a consultant surgeon. They were then individually randomized to one of 2 groups using a computer-generated sequence. Allocation was concealed until the intervention; however, participants and researchers were unblinded. The intervention group completed a 10-minute metaverse-based VR session, delivered by a consultant surgeon via 3D Organon's Medverse platform on the PICO 4 Ultra headset. The control group completed a 10-minute prerecorded 2D animated lecture, accessed on their personal device. Participants then swapped to the other modality. Data were collected via Google Forms at 3 intervals (baseline, postintervention, and postcrossover) to assess confidence, spatial understanding, and knowledge (10-item multiple-choice questions). The analysis of nonparametric data utilized Wilcoxon signed-rank tests for within-group changes and Mann-Whitney U tests for between-group differences. RESULTS: Twenty-four medical students from 11 United Kingdom and Irish medical schools participated. Adherence was 100%, with all participants completing their assigned 10-minute intervention and all assessment points. Ninety-two percent of participants (n=22) reported no prior tracheostomy anatomy teaching. Additionally, 83% (n=20) had no prior remote-synchronized VR anatomy teaching experience. Anatomical confidence improved significantly in the VR group compared with animation (mean change 1.58, SD 1.00 vs mean 0.50, SD 0.80, P=.01). Knowledge scores improved significantly in both groups (VR: mean 1.75, SD 1.54, P=.007; animation: mean 2.83, SD 1.70, P=.003), with no significant postintervention difference between groups (P=.46). VR participants reported significantly superior spatial understanding across all measured domains (all P≤.009). These included depth perception (3.75 vs 2.58, P=.009), appreciation of anatomy from different viewpoints (4.25 vs 2.33, P=.001), mental reconstruction from varying angles (3.83 vs 2.08, P=.002), and spatial depth supporting anatomical understanding (4.08 vs 2.08, P=.001). Following the completion of both modalities, participants rated VR as more engaging (mean 4.54, SD 0.78) and more educationally effective (mean 4.29, SD 0.95) than animation. CONCLUSIONS: Remote VR teaching is feasible and engaging and enhances spatial understanding compared to animation. While knowledge gains were comparable between modalities, VR improved learner confidence and perceived 3D comprehension. Hence, VR may represent a scalable adjunct or alternative to traditional anatomy teaching.
20 May 2026
Read appraisal →JMIR formative research
Feasibility of Large Language Model-Based Standardized Virtual Patients to Support Clinical Decision-Making Training in Operative Dentistry: Mixed Methods Study
BACKGROUND: Clinical decision-making training in operative dentistry commonly relies on real or standardized patients to develop undergraduate students' ability to deliver safe, effective, and patient-centered care. However, training with real or standardized patients can be limited in scalability, cost-effectiveness, and accessibility. Large language models, with their human-like language capabilities, may have the potential to simulate patients in clinical encounters and help overcome some limitations associated with traditional training approaches. OBJECTIVE: This study aimed to evaluate the feasibility of using large language model-based standardized virtual patients to support undergraduate dental students' clinical decision-making training in operative dentistry. METHODS: This mixed methods cross-sectional feasibility study was conducted during a simulation-based clinical decision-making training session in the Operative Dentistry and Cariology course at the College of Dentistry, King Saud bin Abdulaziz University for Health Sciences, Riyadh, Saudi Arabia. Eligible participants were second-year undergraduate dental students enrolled in the course. A convenience sampling approach was used, with all eligible students (N=50) invited to participate. A total of 41 students completed the study, 23 (56%) of whom were male. The students were divided into 8 groups. Each group interacted with 2 standardized virtual patients powered by ChatGPT-4o (OpenAI) through the Chatbase platform to complete comprehensive history-taking and then reviewed the standardized virtual patients' intraoral photographs and bitewing radiographs. For each standardized virtual patient, students as a group recorded diagnoses, performed a risk assessment, and formulated a treatment plan. Students then completed the Student Satisfaction and Self-Confidence in Learning questionnaire. The quality of the standardized virtual patient responses and overall dialogue realism were evaluated using the Dialogue Authenticity Scale. The dialogues were also thematically analyzed to identify authenticity-undermining response features and explore their context and underlying causes. RESULTS: Students perceived the simulation-based training session positively, with all questionnaire items showing high median scores (4.00-5.00 on a 5-point scale), and both item-level IQRs and 95% CIs spanning no more than 1.0 scale point. In addition, standardized virtual patient responses were largely authentic, with an overall median authenticity rating of 4.50 (IQR 4.00-5.00; 95% CI 4.00-5.00) on a 6-point scale across all interactions. However, several authenticity-undermining response features were identified, including responses that were inconsistent with typical human behavior, contained information beyond a patient's likely knowledge, or were factually incorrect. CONCLUSIONS: This proof-of-concept study supports the feasibility of implementing large language model-based standardized virtual patients in undergraduate simulation-based clinical decision-making training in operative dentistry. In a dental context where this application has been only minimally evaluated, this study provides early evidence of positive student perceptions, acceptability, and largely authentic dialogue, while also identifying important performance limitations. Further research is warranted to optimize performance and to evaluate the educational effectiveness of this approach in improving undergraduate students' clinical skills and knowledge.
20 May 2026
Read appraisal →JMIR medical informatics
The Impact of Electronic Health Records on Family Physicians During Simulated Virtual Encounters: Exploratory Mixed Methods Study
BACKGROUND: This exploratory study investigated the impact of computer use on physician performance during clinical simulations. Standardized patient (SP) scenarios used in family practice certification examinations were adapted to include the use of the electronic health record (EHR). OBJECTIVE: The goal was to compare the impact of EHR use during simulated virtual patient encounters on resident physicians' and staff physicians' patient-centeredness (PC) and overall clinical performance, as well as to measure the cognitive load (CL) imposed by EHR use. METHODS: Sixteen participants each completed 2 video telemedicine simulations with SPs. One simulation case included limited past medical history for the SP in the EHR, while the other did not. Participants were instructed to completely document the encounter using the EHR. Participants' self-perceived CL was measured using the raw National Aeronautics and Space Administration Task Load Index (NASA-TLX). Video recordings were analyzed for participant PC and overall clinical performance. In addition to interacting with the EHR, multiple participants also conducted internet searches. The proportion of time that participants spent interacting with the computer, either using the EHR or searching the internet, was calculated. Inductive qualitative coding of a subset of video recordings (18 of 32 encounters) was performed, with a focus on signs of stress/CL. All videos were assessed for usability problems. RESULTS: Staff physicians (n=6) scored higher on PC compared to resident physicians (n=10) for both cases, though differences were not statistically significant after correction for multiple comparisons (family-wise error rate). Physicians' overall CL, as measured by the raw NASA-TLX, was not significantly correlated with computer use. Exploratory qualitative data analysis found both verbal and nonverbal signs of stress/CL due to computer use while interacting with the SPs. The proportion of time displaying nonverbal signs of stress/CL was calculated for a subset of participants (6 resident physicians and 3 staff physicians). Participant interpretations of instructions to completely document the encounter using the EHR varied widely. It is likely that participants' usual style of documenting, either primarily during or after patient encounters, impacted their use of the EHR while SPs were present. CONCLUSIONS: Use of the computer during video telemedicine appointments may negatively impact physician PC and overall clinical performance. Exploratory qualitative coding identified both verbal and nonverbal signs of stress/CL when participants interacted with the computer and the patient simultaneously. Increased clinical experience helped to mitigate the negative impact of computer use. If the use of the EHR is included in physician certification examinations, clear instructions regarding which tasks must be completed in the EHR during interactions with SPs should be provided.
20 May 2026
Read appraisal →JMIR medical education
Experiences and Perceptions of Clinical and Graduate Medical Students Regarding AI in Syria: Cross-Sectional Study
BACKGROUND: Artificial intelligence (AI) tools have revolutionized various aspects of education and health care in recent years. Their influence extends across multiple domains of medical education, from traditional learning to research and foreign language acquisition. OBJECTIVE: This study aims to evaluate the experiences and perceptions of AI tools usage in a low-resource setting and identify the factors influencing their adoption. METHODS: A cross-sectional study was conducted to evaluate the experiences with AI tools and perceptions regarding their future applications in education and health care among medical students in Syria. The sample was equally divided between clinical-year students and graduates. Chi-square tests analyzed differences based on demographics and experience, while Mann-Whitney U tests compared group perceptions of AI's future role. Factors studied included academic year, gender, German language learning, computer access, and research experience. RESULTS: Among 400 participants, AI tools were widely used for study preparation (228/400, 57% of participants), assignments (160/400, 40% of participants), and research. Clinical students used AI more than graduates for examination preparation (P<.001), creating cases (P=.03), and writing tasks (P<.001). Males used AI more for research (P=.004) or anatomy (P=.02); German learners relied on AI for language tasks. Despite 76% (304/400) of students believing AI would enhance residency training and 71.8% (287/400) of students supporting institutional policies, only 25.5% (102/400) of students expected career benefits. Ethical concerns were higher among females and researchers. CONCLUSIONS: This study highlights the increasing reliance on AI tools among medical students and graduates for academic and clinical purposes. The highest usage was reported in study preparation, writing tasks, and clinical simulations. Significant differences in AI usage were observed based on academic level, gender, access to technology, and research experience. While perceptions were largely positive, concerns remained around ethical use, potential job displacement, and diminished human interaction in medicine. These findings underscore the importance of developing institutional policies to guide the ethical and effective integration of AI in medical education.
20 May 2026
Read appraisal →JAMA
Using Serious Games to Increase the Implementation of Trauma Triage Guidelines: A Randomized Clinical Trial
IMPORTANCE: Low-cost methods that improve physician adherence to clinical guidelines are lacking. Trauma triage exemplifies time-sensitive conditions where guideline adherence remains at 50% or less despite stakeholder efforts, particularly when treating older adults. OBJECTIVE: To determine whether a theory-based serious game (a purpose-driven video game) improves emergency physician adherence to trauma triage guidelines for older adults. DESIGN, SETTING, AND PARTICIPANTS: This randomized clinical trial recruited 800 emergency physicians responsible for the triage of Medicare fee-for-service injured patients (≥65 years of age) at emergency departments within nontrauma centers in the US. Physician enrollment began November 27, 2023, and concluded February 7, 2024. Data collection began January 1, 2024 (or the date of enrollment), and ended February 6, 2025. The patients were treated during the 1 year after physician enrollment. INTERVENTIONS: Game-based training on a tablet for an initial session of 2 hours and then a 20-minute session each quarter (4 doses; n = 400 physicians) vs usual education (n = 400 physicians). MAIN OUTCOMES AND MEASURES: The primary outcome was undertriage (defined as the proportion of severely injured patients not transferred to trauma centers) during the year after randomization. The secondary outcomes were overtriage (defined as the proportion of transferred patients with minor injuries) and a composite clinical outcome of 30-day mortality or hospital readmission. Medicare fee-for-service claims were analyzed using mixed-effects regression models. RESULTS: Of the 800 physicians, the length of experience was a median of 10 (IQR, 6-17) years in practice, 71% were male (563/789), and 750 (94%) had completed Advanced Trauma Life Support. The physicians worked at 1147 hospitals and treated 41 073 injured Medicare patients, of whom 1738 (4.2%) had severe injuries. Of the physicians in the game-based training (intervention) group, 99% (397/399) received 1 dose and 67% (268/399) received 4 doses. Physicians in the game-based training group had a lower proportion of severely injured older adults who were undertriaged (49%; 402/819) compared with the usual education (control) group (57%; 527/919) (model-adjusted difference, -7% [95% CI, -13% to -0.8%]; P = .02). The model-adjusted difference did not differ for the outcomes of overtriage (-3% [95% CI, -6% to 1%]; P = .14) and the composite outcome (-0.4% [95% CI, -5% to 4%]; P = .87). CONCLUSIONS AND RELEVANCE: Among physicians responsible for the triage of patients in emergency departments of nontrauma centers, use of a theory-based serious game decreased the proportion of severely injured patients who were undertriaged. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT06063434.
20 May 2026
Read appraisal →World journal of urology
Comparative study on the efficacy of large language models (LLMs) in health management for patients with urological and andrological diseases: a multidimensional quality evaluation and applicability analysis
PURPOSE: This study aims to evaluate the efficacy of large language models (LLMs) in health management for urological and andrological conditions by comparing two Chinese LLMs: DeepSeek and Kimi. METHODS: The responses of DeepSeek and Kimi to 30 questions on six urological and andrological diseases were quantitatively assessed using quality assessment tools, expert assessments, and readability metrics. RESULTS: In quality assessments, DeepSeek outperformed Kimi in only two instances: responses to "What are the surgical options for kidney stones?" (PEMAT-AI: P = 0.012; DISCERN-AI: P = 0.024) and "What are the treatment modalities for bladder cancer?" (PEMAT-AI and DISCERN-AI: P < 0.001). Expert assessments revealed that DeepSeek demonstrated superior accuracy and safety compared to Kimi only in addressing "Dietary considerations for kidney stone patients" (accuracy: P < 0.001; safety: P = 0.02). No statistically significant differences were found in quality assessments or expert assessments between the models for disease-specific categories. However, Kimi outperformed DeepSeek in readability evaluations. CONCLUSION: Both DeepSeek and Kimi exhibit substantial efficacy and clinical applicability in managing urological and andrological diseases. To enhance their practical use, Kimi requires improvements in accuracy and safety, while DeepSeek should focus on improving readability.
18 May 2026
Read appraisal →Scandinavian journal of primary health care
Shoulder-to-shoulder: healthcare professionals' experiences of learning during electronic health record implementation in municipal primary care.
BACKGROUND: Formal training is commonly used in electronic health record (EHR) implementation, but often fails to address healthcare professionals' ongoing, context-specific learning needs. There is limited knowledge of how learning unfolds in practice when such training is experienced as insufficient, particularly in municipal healthcare services. METHODS: This qualitative study examined learning processes during the implementation of a new EHR system in a municipal healthcare institution in Central Norway. Data was generated through interviews and observation, and was analyzed thematically. RESULTS: Participants experienced formal training as poorly aligned with their digital competencies and everyday clinical work. Limited time and staffing further constrained participation in formal training and follow-up. Alongside formal training, employees engaged in peer-based learning practices embedded in everyday work, described as 'shoulder-to-shoulder' learning. These practices became particularly important due to limited time and staffing, enabling rapid problem-solving and mutual support, while also reinforcing shared responsibility for learning. Rather than merely compensating for inadequate training, shoulder-to-shoulder learning emerged as an important adaptive practice that supported problem-solving and collaboration during EHR implementation. CONCLUSION: Learning to use EHR systems in municipal primary care should be understood as a socially embedded and ongoing process. While formal training may provide initial orientation, implementation strategies should also recognize and support peer-based learning practices that support ongoing learning and collaboration during periods of organizational change.
18 May 2026
Read appraisal →Philosophical transactions. Series A, Mathematical, physical, and engineering sciences
Revisiting Rogers' Paradox in the context of human-AI interaction
People learn about the world in many ways: from conducting experiments to copying others' behaviour. The choices we make about how to learn can impact the collective understanding of a whole population, were others to learn from us. Alan Rogers developed simulations to study these phenomena-where agents could individually or socially learn amidst a dynamic, uncertain world-and uncovered a surprising result: the availability of cheap social learning yielded no benefit to population fitness over individual learning. Rogers' Paradox spawned decades of work to understand factors that favour social learning and better model human cultural development. But what happens when humans can learn from artificial intelligence (AI) systems that are themselves learning from us? We revisit Rogers' Paradox in the context of human-AI interaction and extend the simulations towards a simplified network of humans and AIs learning together about an uncertain world. We examine the impact of several learning strategies on the equilibrium of a society's 'collective world model' and assess levers available to stakeholders in human-AI interactions to change network dynamics. We then model negative feedback loops that may arise from humans learning socially from AI, and consider other open questions that could be explored in our simulation framework. This article is part of the theme issue 'World models in natural and artificial intelligence'.
17 May 2026
Read appraisal →The British journal of general practice : the journal of the Royal College of General Practitioners
Perinatal mental health training and supervision for primary care and community-based staff: a systematic review
BACKGROUND: Perinatal mental health problems are common yet often under-detected and under-treated in primary care and community services. International guidelines call for integration of mental health into perinatal care, but clarity is lacking on how best to equip non-specialist providers. Training and supervision programmes exist but vary widely in content and delivery, and their effectiveness and feasibility across settings are not comprehensively synthesised. AIM: To evaluate the effectiveness of perinatal mental health training for primary care and community-based providers on provider competence, maternal outcomes, and implementation in routine care. METHOD: Seven databases and grey literature were systematically searched to September 2025. Eligible studies evaluated training delivered to health or community providers involved in perinatal care. Due to heterogeneity, findings were narratively synthesised. Risk of bias was assessed using RoB-2 and ROBINS-I; certainty of evidence appraised using GRADE. RESULTS: Of 707 citations screened, 39 studies were included, spanning high- and low-income countries and involving over 10,000 providers. Interventions varied in intensity and modality, including novel approaches such as extended reality simulation and cascade 'train-the-trainer' models. Training consistently improved provider knowledge, skills, attitudes, and confidence, and was associated with increased screening and referral, particularly when supported by supervision or system-level integration. Patient outcomes were less frequently assessed; where reported, some studies showed reductions in depressive symptoms and improvements in broader maternal outcomes, though findings were mixed. CONCLUSION: Training enhances provider capacity in perinatal mental health, but evidence on patient impact, sustainability, cost-effectiveness, and equity remains limited, highlighting priorities for future research and policy.
16 May 2026
Read appraisal →BMJ open
Performance of large language models (GPT-5.2, Gemini 3 Pro, Claude Sonnet 4.6 and Grok 4.1) on the Fellowship of The Royal College of Surgeons Urology Part A examination.
OBJECTIVES: To assess and compare the performance of four contemporary frontier large language models (LLMs)-GPT-5.2 (OpenAI), Gemini 3 Pro (Google DeepMind), Claude Sonnet 4.6 (Anthropic) and Grok 4.1 (xAI)-on a simulated Fellowship of The Royal College of Surgeons Urology (FRCS(Urol)) Part A examination, evaluating overall accuracy, subspecialty-level performance, output consistency and response time. DESIGN: Controlled comparative evaluation study using a standardised simulation framework with repeated independent testing runs per model. SETTING: All models were accessed via their respective consumer-facing interfaces. No clinical setting or patient data were involved. Testing was conducted under uniform conditions with conversational memory disabled across all sessions. PARTICIPANTS: Four large language models were evaluated. No human participants were involved. Models were selected to represent the current frontier of publicly accessible LLMs from four distinct commercial developers. No models were excluded following selection. INTERVENTIONS: Each model was presented with 240 FRCS (Urol) Part A single best answer questions, mapped to the Joint Committee on Intercollegiate Examinations' Urology Syllabus Blueprint (2023). A standardised prompt was delivered at the start of each session. Each model completed five independent examination runs. No fine-tuning or system-level modification was applied to any model. PRIMARY AND SECONDARY OUTCOME MEASURES: The primary outcome was overall examination accuracy for each model, benchmarked against an indicative pass threshold for the FRCS (Urol) Part A examination. Secondary outcomes were performance across 18 individual urology subspecialty topics; response time reported as mean total and per-question elapsed time; and consistency of performance quantified by SD and 95% CIs derived from a sequential Monte Carlo sampling procedure. All outcomes were prospectively planned and fully measured as specified. RESULTS: Three of four models exceeded the indicative 74% pass threshold: Gemini 3 Pro (82.4%±0.9%; 95% CI 81.3 to 83.6%), Claude Sonnet 4.6 (79.3%±1.1%; 95% CI 77.9 to 80.6%) and GPT-5.2 (76.1%±2.4%; 95% CI 73.1 to 79.1%). Grok 4.1 failed (70.4%±0.6%; 95% CI 69.6 to 71.2%), with its entire CI below 74%. All models completed the assessment in under 3 min. Strong performance was observed in research methodology (90-98%) and andrology (92-98%), with the weakest results in paediatric urology (38.7-54.7%) and testicular cancer (48.2-67.3%). Substantial within-model output instability was identified across several domains, most notably GPT-5.2 in female urology (SD±22.8%) and anatomy (SD±14.2%). CONCLUSIONS: Three of four frontier LLMs achieved scores consistent with passing the FRCS (Urol) Part A examination, representing a substantial advance since ChatGPT-3.5. Aggregate accuracy alone, however, obscures important subspecialty weaknesses and output instability. LLMs should be regarded as adjunctive revision aids rather than authoritative knowledge sources and always used alongside expert-led teaching. Future work should evaluate performance on Part B and viva-style assessments.
15 May 2026
Read appraisal →PLoS computational biology
Teaching artificial intelligence through drug-drug interaction clustering analysis: Integrating project-based learning and large language models.
In recent years, artificial intelligence (AI) has increasingly influenced daily life and scientific research. Traditionally, AI-related courses have targeted computer science majors, while systematic instructional opportunities for early-stage undergraduates from non-computing backgrounds remain limited. To bridge this gap, we developed an AI course that integrates project-based learning with large language models (LLMs). Specifically, we designed four progressive assignments based on our research project (i.e., drug-drug interaction network clustering analysis). The course does not require prior knowledge of pharmacology or programming. Instead, LLMs are used as assistive tools to support programming, data analysis, and result interpretation. Students engage in a complete workflow, including data curation, algorithm implementation, and critical evaluation of results. Preliminary feedback shows that this approach supports the development of problem-solving skills and increases student engagement. This study provides a framework for integrating LLMs into project-based learning. We believe that this teaching proposal will be valuable and inspiring for educators seeking to design or enrich similar courses.
15 May 2026
Read appraisal →Proceedings of the National Academy of Sciences of the United States of America
Speed and quality of complex strategic decisions
Many strategic decisions involve both substantial complexity and time pressure, but the association between decision speed and decision quality of cognitively demanding strategic decisions is not well understood. This paper presents evidence on this question using a setting with exceptionally detailed and precise information about decision times and decision quality-it analyses move-by-move data from in-person professional chess tournaments. Decision quality is measured by comparing actual moves to a computational benchmark of best moves constructed using the artificial intelligence of a chess engine. The results show that faster decisions are associated with higher decision quality, even after accounting for computational complexity, distinctiveness between alternatives, and time pressure. Greater computational complexity and lower distinctiveness between move alternatives are associated with longer decision times, whereas greater time pressure is associated with shorter decision times. All three factors are associated with lower decision quality. We discuss the findings against the predictions of different decision models in which individuals sequentially acquire information about alternatives with uncertain valuations, extending theories originally developed in the context of nonstrategic decisions to a strategic environment.
15 May 2026
Read appraisal →PloS one
Framing artificial intelligence in Chilean digital press before and after the launch of ChatGPT: From concern to optimism
This article examines the evolution of AI framing in Chilean national digital media before and after the launch of ChatGPT in 2022. Through topic modeling and emotion analysis of 1,466 articles published by six media outlets over periods that begin between 2000 and 2014, depending on the outlet, and extend in all cases until 2024, this study identifies significant thematic and affective changes. In the pre-ChatGPT period, coverage combined recognition of AI's capabilities with concerns regarding labor displacement, governance, and human identity, frequently referencing global corporations and state institutions. In the post-ChatGPT period, topics became narrower in scope, with fewer actors and greater emphasis on universities and cultural organizations implementing AI. The focus shifted from the development of AI systems to their applications, predominantly framed in positive terms. At the same time, negative sentiment was largely confined to epistemological uncertainty. This transformation aligns with national surveys indicating growing public optimism, diverges from Global North debates centered on regulation and privacy, and converges with East Asian framings that are oriented toward innovation and creativity. These findings suggest that the launch of ChatGPT coincided with a reinforcement of a socio-technical imaginary of AI as inevitable and beneficial, yet potentially limiting the diversity of public debate.
14 May 2026
Read appraisal →Journal of medical systems
Clinical Plausibility in Large Language Model Robustness Testing for Medicine: A Scoping Review
Large language models (LLMs) show promise in medical applications, yet their translation into clinical practice requires rigorous validation. Current robustness testing often employs adversarial approaches borrowed from AI safety, raising questions about their alignment with authentic clinical scenarios. To systematically map methodologies used for robustness testing of LLMs in medical contexts and assess their clinical plausibility. A scoping review was conducted following PRISMA-ScR guidelines, searching PubMed, Embase, Web of Science, IEEE Xplore, ACM Digital Library, arXiv, and MedRxiv from January 2023 to September 2025. Two independent physician reviewers screened 5,331 articles, extracting data on testing methodologies, medical domains, expert involvement, and clinical plausibility. Thirty-three studies met inclusion criteria, predominantly from 2025 (82%). The most common robustness testing approaches were misleading prompts (49%) and adversarial prompts (39%). Only 33% of studies designed tests clearly mimicking plausible clinical scenarios. While 58% reported expert involvement, the depth of integration varied considerably. Studies predominantly addressed mixed medical domains (73%) rather than specialized fields. The emerging literature suggests that LLM robustness testing in medicine often emphasizes technical vulnerability detection, with fewer studies examining clinically plausible scenarios of routine use. Future frameworks should complement adversarial testing with clinically grounded, longitudinal, and specialty focused evaluations to support deployment-relevant inference.
13 May 2026
Read appraisal →Medical education online
Using randomization to compare AI and expert-generated formative assessment questions in medical education
BACKGROUND: AI-generated content is being used across the education spectrum and is beneficial for creating complex multiple-choice questions, such as those used in medical education. However, evaluating AI-generated content is challenging, and existing testing and evaluation methods are falling short. This study uses randomization to compare medical students' performance on and subjective evaluation of AI versus expert-generated questions. We hypothesized that there would be no difference in student performance or subjective evaluation of AI vs expert-generated questions. METHODS: We designed a single-center, randomized study where medical student participants received either one AI- or expert-generated question per day over four weeks. RESULTS: Our study showed that participants had similar perceptions of AI versus expert-generated questions (p = 0.18), with no significant difference between the distributions of the proportion of correct responses. The cumulative proportion of questions answered correctly over 28 days was consistent across the two question sets. However, participants rated 53% of AI-generated questions as very easy or easy compared with only 31% of the expert-generated questions. DISCUSSION: Randomization was crucial to show that AI-generated questions were nearly imperceptible from expert-generated questions, demonstrating the need for additional evaluation methods to compare AI- and expert-generated medical education content.
12 May 2026
Read appraisal →Current oncology reports
Physicians' Knowledge and Experiences of Counseling on Complementary, Alternative, and Integrative Medicine in Cancer Care: a Qualitative Systematic Review
PURPOSE OF REVIEW: The increasing use of complementary, alternative, and integrative medicine (CAIM) among patients with cancer raises questions about physicians' knowledge and counseling practices in this area. This qualitative systematic review used a narrative synthesis approach to explore physicians' understanding and experiences with CAIM counseling in cancer care. RECENT FINDINGS: A systematic search of MEDLINE, EMBASE, and AMED, supplemented by hand-searching reference lists, identified 35 eligible studies. Analysis revealed four key themes: limited knowledge and training on CAIM; concerns about CAIM safety and efficacy; recognition of CAIM's role in holistic cancer care; and challenges in patient-physician communication regarding CAIM. Physicians acknowledge the importance of CAIM in person-centered cancer care but express concerns about its safety and effectiveness, underscoring the need for improved CAIM education and training. Future research should include perspectives from medical trainees and other healthcare providers to enhance counseling practices and support integrative cancer care.
12 May 2026
Read appraisal →The New Zealand medical journal
The impact of cultural concordance between health professionals and patients: a narrative review
AIM: The aim of this article is to summarise international evidence on the impacts of cultural/ethnic concordance between patients and health professionals and to discuss the implications for New Zealand. METHOD: Database searches were conducted from August to September 2025 using Scopus, Embase and PubMed, using key terms related to health outcomes and cultural/ethnic concordance. RESULTS: A total of 25 relevant systematic reviews, meta-analyses and research studies were included for analysis. Overall, evidence is predominately from the United States of America and findings are variable. Cultural concordance is associated with improved communication quality, trust, satisfaction and perceived respect. Concordance is also associated with improved healthcare utilisation, medication adherence and uptake of preventative interventions. Some studies found concordance was associated with differences in clinical decision-making. Impact on clinical outcomes is mixed, with some studies finding concordance has a positive impact on caesarean section rates, diabetes management, surgical outcomes and addiction treatment, while others found no impact. CONCLUSION: Cultural concordance between patients and their health professionals matters, with evidence of impact on patient experience, communication quality, engagement and adherence, clinical decision-making and some clinical outcomes. Findings are inconsistent: the strength of association and groups which see the greatest benefit vary between studies. To reduce health inequities, we need to increase the diversity of the workforce and train all health professionals to provide non-racist, equitable care.
12 May 2026
Read appraisal →Journal of medical Internet research
GenAI-Supported Virtual Patients in Health Care Education: Systematic Review
BACKGROUND: Generative artificial intelligence (GenAI) is enhancing virtual patient simulations in health care education by enabling dynamic, adaptive interactions, reshaping how clinical skills are taught. A synthesis of the current evidence is needed to guide implementation and future research, given the pace of technological advancement. OBJECTIVE: This systematic review aims to synthesize empirical research on the design, implementation, and educational impact of GenAI-supported virtual patients in health care education. METHODS: A systematic search was conducted across 5 databases (CINAHL, Medline, Embase, Scopus, and Web of Science) from their inception to March 19, 2026. Reference lists of included studies and relevant systematic reviews were also screened. Peer-reviewed studies in English that evaluated GenAI-supported virtual patients using quantitative or mixed methods were included. Two reviewers independently screened studies and extracted data. Study quality and risk of bias were assessed critically using JBI (Joanna Briggs Institute) checklists, with disagreements resolved by consensus. RESULTS: A total of 15 studies met the inclusion criteria (total participants N=645), spanning health care disciplines, including nursing, medicine, pharmacy, radiography, and medical first-responder training. The virtual patients varied in design; input modalities included text (9 studies), voice (5 studies), or hybrid (1 study); output was text (9 studies), speech (5 studies), or both (1 study); 6 studies used 3D-embodied avatars, while 9 used nonembodied interfaces. A total of 13 studies used OpenAI GPT models (eg, ChatGPT), 1 used a fine-tuned model from a different provider, and 1 evaluated multiple model families (Claude, GPT, and open-source). Further, 6 studies used controlled experimental designs, including 3 randomized controlled trials (RCTs); the remainder were cross-sectional or prepost evaluations. Primary outcomes included user perceptions (14 studies), communication skills (4 studies), clinical reasoning (3 studies), and performance (7 studies). In controlled comparisons, GenAI-supported virtual patients consistently improved outcomes relative to control conditions: for example, enhanced clinical decision-making (RCT, n=21), ophthalmology history-taking skills (RCT, n=26), and medical history-taking performance (crossover RCT, n=20). The evidence base is characterized by brief intervention durations, a predominant reliance on single-session interactions, and a general lack of underpinning educational theory. No meta-analysis was performed due to the limited number of studies and significant heterogeneity in designs, interventions, and outcome measures. CONCLUSIONS: The evidence supports the feasibility and acceptability of GenAI-supported virtual patients, with positive learner perceptions and promising outcomes for skills development. However, critical limitations remain in emotional-behavioral complexity, simulation adaptability, and research design rigor (eg, limited use of control groups and validated instruments). The review offers educators, instructional designers, and policymakers actionable insights for integrating dynamic, artificial intelligence-driven simulations while identifying crucial gaps-such as the need for theoretical grounding, longitudinal studies, and standardized design protocols-that must be addressed for safe and effective implementation.
11 May 2026
Read appraisal →World journal of urology
Quantifying ergonomic challenges for urologists operating flexible ureteroscopes through artificial intelligence-based posture estimation
PURPOSE: The ergonomic challenges faced by surgeons during flexible ureteroscopy have yet to be thoroughly evaluated using objective methods. However, robot-assisted ureteroscopy has emerged as a promising treatment for urinary stones. The present study quantitatively assesses operative posture during transurethral ureteroscopy via an artificial intelligence-based posture estimation framework, and identifies kinematic differences associated with surgical expertise. METHODS: Expert and novice urologists performed standardized flexible ureteroscopic tasks in a simulated transurethral ureteroscopy environment using kidney phantoms containing artificial stones. Upper-body movements were continuously video-recorded and joint coordinates of the shoulders, elbows, and wrists were extracted using an artificial intelligence-based pose estimation system. Kinematic parameters were quantitatively analyzed and compared between groups. RESULTS: Experts completed observation of the entire renal pelvis significantly faster than novices (median 58 vs. 102 s, p < 0.001). Accumulated travel distance was markedly less in experts for the left shoulder (125 vs. 300 cm, p < 0.001), right elbow (324 vs. 1035 cm, p = 0.028), left elbow (349 vs. 772 cm, p = 0.019), and left wrist (729 vs. 3798 cm, p < 0.001). Experts had smaller movement areas at the left shoulder (6.29 vs. 40.5 cm2, p < 0.001) and right elbow (17.3 vs. 281 cm2, p = 0.040), and reduced movement ranges across multiple joints. Their angle fluctuation ranges were also narrower for the right shoulder (32.0 vs. 76.3°, p = 0.028) and left elbow (70.4 vs. 122.4°, p < 0.001). CONCLUSIONS: The artificial intelligence-based posture analysis objectively demonstrated ergonomic advantages associated with surgical expertise during flexible ureteroscopy and revealed persistent ergonomic risks to the wrist and elbow.
11 May 2026
Read appraisal →Journal of bronchology & interventional pulmonology
AIBAN-AI Bronchial Detection and Airway Navigation System
BACKGROUND: Accurate navigation within the lungs is critical for bronchoscopy procedures but remains challenging due to the complex airway anatomy. Artificial intelligence (AI) integrating real-time landmark detection and navigation guidance may enhance precision and safety. METHODS: We developed an AI Bronchial detection and Airway Navigation system (AIBAN) for bronchoscopy, combining airway lumen detection, anatomic localization, and navigation guidance. A YOLOv8-based detection module was used to identify 34 airway landmarks in real time. Next, an airway-level localization module estimated the bronchoscope's position using a hierarchical anatomic graph, identifying the deepest branch compatible with all coherent detections in each frame. A navigation module then recommended the next airway to follow along predefined anatomic paths, providing directional cues to perform a complete and systematic bronchoscopy. RESULTS: AIBAN was developed on a data set of 18 bronchoscopy videos, using 15 for training and 3 for validation. In validation, the framework correctly identified the bronchoscope's location in 91.1% of the frames. In addition, 92.6% of predictions were within one airway branch of the true location, and 94.5% were within 2 branches. The navigation guidance performance was also promising, with the system following the correct anatomic pathway in 96.2% of test videos, demonstrating reliable guidance through the lungs. CONCLUSION: AIBAN enables accurate airway detection, localization, and navigation guidance in a simulation-based setting. It can provide reliable guidance along predefined paths and precise spatial positioning and is a promising tool for medical training and has potential for future clinical implementation.
11 May 2026
Read appraisal →European journal of pediatrics
Metaphorical perceptions of secondary school students regarding the concept of generative artificial intelligence
UNLABELLED: The rapid integration of generative artificial intelligence (GenAI) tools, such as ChatGPT, into educational contexts has raised important questions regarding how adolescents conceptualize and make sense of these technologies. Understanding students' perceptions is essential for developing age-appropriate, ethical, and pedagogically sound approaches to AI use in secondary education. This descriptive qualitative study employed a phenomenological approach and metaphor analysis to explore secondary school students' perceptions of generative artificial intelligence. The study sample consisted of 332 students aged 14-18 years from four secondary schools in Türkiye. Data were collected using an open-ended prompt ("Generative artificial intelligence is like … because …") and analyzed through content analysis. Metaphors were categorized based on shared semantic and conceptual features, and inter-rater reliability was established using Cohen's kappa (κ = 0.92). Analysis revealed ten metaphor categories clustered under five overarching themes: generative artificial intelligence as (1) a source of knowledge, (2) a teaching and guiding entity, (3) a supportive and assisting tool, (4) a reflection of human intelligence, and (5) a dual-purpose (beneficial-risky) technology. Students most frequently conceptualized GenAI as a comprehensive knowledge source (e.g., book, encyclopedia) and as a human-like cognitive entity (e.g., brain, wise person). At the same time, metaphors reflecting ethical awareness and potential risks, such as misuse and overreliance, were also identified. The findings indicate that secondary school students hold multifaceted and nuanced perceptions of generative artificial intelligence, encompassing both educational opportunities and ethical concerns. These results highlight the importance of integrating AI literacy into secondary education in ways that promote critical thinking, responsible use, and awareness of GenAI's limitations alongside its potential benefits. CONCLUSION: It was determined that secondary school students perceive generative artificial intelligence ambivalently as both a useful tool and a source of ethical and emotional concern, highlighting the need for developmentally appropriate artificial intelligence literacy approaches. WHAT IS KNOWN: • GenAI tools such as ChatGPT are increasingly integrated into educational contexts and have the potential to support personalized learning, information access, and student engagement. • Existing research has primarily focused on educators' perspectives or higher education settings, while studies examining adolescents' perceptions of GenAI remain limited. WHAT IS NEW: • This study provides empirical evidence on secondary school students' metaphorical perceptions of generative artificial intelligence within a K-12 context. • Findings reveal that adolescents conceptualize GenAI in multifaceted ways, including as a knowledge source, teaching and guiding entity, supportive tool, reflection of human intelligence, and a dual-purpose (beneficial-risky) technology.
10 May 2026
Read appraisal →Annals of laboratory medicine
Evaluation of the Performance of Advanced Large Language Models in Laboratory Medicine Using Residency Examinations
BACKGROUND: Recent advancements in large language models (LLMs) have accelerated their integration into clinical domains, including laboratory medicine. The performance of LLMs in answering board-level laboratory medicine questions has not been comprehensively evaluated. Given the importance of diagnostic accuracy in this field, rigorous and objective evaluations of LLM capabilities are essential. METHODS: We assessed 12 LLMs from OpenAI, Anthropic, and Google using 320 Korean Residency Examination questions (2021-2024) spanning six laboratory medicine subspecialties. Standardized prompts were provided via their application programming interfaces under deterministic settings (temperature=0). Questions were administered thrice to assess response reproducibility. Outputs were compared with validated answers and analyzed for accuracy, reasoning quality, and error typology. RESULTS: Google's Gemini 2.0 Pro achieved the highest accuracy (80.0%), followed by OpenAI's GPT-4.5 (77.2%) and Anthropic's Claude 3.7 Sonnet (74.1%). Accuracy decreased as the difficulty of questions increased (78.0% for easy vs. 45.1% for challenging). Subspecialty performance varied. Al models underperformed on questions on transfusion medicine (mean accuracy: 38.8%), primarily because of limitations in domain-specific and regional knowledge representations. Incorrect answers primarily resulted from reasoning errors. Reproducibility exceeded 95% for most models; however, some residual non-determinism appeared even with greedy decoding (temperature=0). CONCLUSIONS: LLMs demonstrated substantial potential for integration into laboratory medicine, particularly in clinical chemistry and immunology. Performance inconsistencies (particularly for high-difficulty questions) and knowledge gaps (notably for transfusion medicine) highlight the necessity for further development-potentially including domain-specific fine-tuning and retrieval-augmented generation integration-and robust expert oversight before clinical application.
6 May 2026
Read appraisal →European journal of dental education : official journal of the Association for Dental Education in Europe
Assessment of the Large Language Models in Creating Dental Board-Style Questions: A Prospective Cross-Sectional Study
INTRODUCTION: Although some studies have investigated the application of large language models (LLMs) in generating dental-related multiple-choice questions (MCQs), they have primarily focused on ChatGPT and Gemini. This study aims to evaluate and compare the performance of five of the LLMs in generating dental board-style questions. MATERIALS AND METHODS: This prospective cross-sectional study evaluated five of the advanced LLMs as of August 2024, including ChatGPT-4o (OpenAI), Claude 3.5 Sonnet (Anthropic), Copilot Pro (Microsoft), Gemini 1.5 Pro (Google) and Mistral Large 2 (Mistral AI). The five most recent clinical guidelines published by The Journal of the American Dental Association were used to generate a total of 350 questions (70 questions per LLM). Each question was independently evaluated by two investigators based on five criteria: clarity, relevance, suitability, distractor and rationale, using a 10-point Likert scale. RESULT: Inter-rater reliability was substantial (kappa score: 0.7-0.8). Median scores for clarity, relevance and rationale were above 9 across all five LLMs. Suitability and distractor had median scores ranging from 8 to 9. Within each LLM, clarity and relevance scored higher than other criteria (p < 0.05). No significant difference was observed between models regarding clarity, relevance and suitability (p > 0.05). Claude 3.5 Sonnet outperformed other models in providing rationales for answers (p < 0.01). CONCLUSION: LLMs demonstrate strong capabilities in generating high-quality, clinically relevant dental board-style questions. Among them, Claude 3.5 Sonnet exhibited the best performance in providing rationales for answers.
6 May 2026
Read appraisal →Journal of surgical education
Non-Invasive Assessment of Continuous Real-Time Workplace Stress Among Surgeons and Surgical Trainees: A Scoping Review
OBJECTIVES: To describe how physiological parameters were used to characterize continuous, real-time workplace stress among surgeons and surgical trainees, and to identify the advantages and disadvantages of using wearable devices. DESIGN: We conducted a scoping review to examine how wearable devices were used to objectively measure surgeons' and trainees' physiological stress in the workplace. Peer-reviewed English articles published up to September 2023 in Medline (Ovid), Cochrane Library (Wiley), Embase (Elsevier), and PsycINFO (Ebsco) databases using wearable devices used to measure continuous, real-time physiological parameters representing workplace stress among surgeons and surgical trainees were included in the review. SETTING: We included studies that assessed physiological stress in the workplace (e.g., operating room and other clinical environments). PARTICIPANTS: Surgeons and surgical trainees. RESULTS: A review of 61 articles that met inclusion criteria revealed that the most commonly used wearable devices were Polar 13 (21.3%), Medilog: 6 (9.8%), Holter ECG device: 7 (11.5%), and WHOOP! : 6 (9.8%). Physiological parameters used to measure continuous, real-time workplace stress were heart rate, heart rate variability, blood pressure, respiratory rate, and electrodermal activity. Physiological parameters indicated that surgeons were more stressed in the operating room than in other clinical environments. Intraoperative surgeons' stress increased with performing critical steps of the operation, teaching a trainee, the number of intraoperative events, e.g., bleeding, and decreased with years of experience. There was a negative relationship between stress and the surgeon's intraoperative performance. The advantages of using wearable devices' physiologic parameters were objectivity, longitudinal measurement, and minimally obtrusive. The disadvantages were short battery life, inadequate data capture, artifacts, and data loss. CONCLUSIONS: Wearable devices can measure a range of physiological parameters that represent workplace stress continuously among surgeons and surgical trainees.
5 May 2026
Read appraisal →The Journal of nursing education
Enhancing Nursing Students' Interdisciplinary Competence via ARCS-Based Digital Health Care Design
BACKGROUND: Digital literacy is increasingly essential in modern nursing education, yet many students lack confidence and prior exposure to digital tools. METHOD: A 6-week project-based course, guided by the ARCS motivational model comprising Attention, Relevance, Confidence, and Satisfaction, engaged 40 first-year nursing students in designing health care applications using the Figma digital platform. The instructional process was organized into three progressive phases: motivational induction, design implementation, and final presentation. RESULTS: Students demonstrated a significant increase in learning motivation (t = 15.784, p < .001) and rated Figma's usability as excellent (System Usability Scale = 84.87). Reflections indicated enhanced digital confidence, interdisciplinary collaboration, and the ability to translate nursing knowledge into practical applications. CONCLUSION: Integrating motivational strategies with project-based learning and an intuitive digital platform effectively promoted student engagement, skill acquisition, and meaningful learning. This model offers a scalable approach for embedding digital competence into nursing curricula.
5 May 2026
Read appraisal →JMIR medical education
Health Professional Students' Use of Generative Artificial Intelligence During Clinical Placements: Cross-Sectional Online Survey Study
BACKGROUND: Generative artificial intelligence (GenAI) is rapidly expanding in higher education and clinical practice. However, its use during clinical placements, where cognitive demands and responsibility for patient care increase, remains insufficiently documented. OBJECTIVE: This study aimed to characterize self-reported GenAI use during clinical placements, perceived benefits and risks, and related training and governance needs. METHODS: We conducted a cross-sectional online survey at a French university (July 17 to September 30, 2025). Eligible participants were students in medicine, pharmacy, nursing, midwifery, or physiotherapy who were currently in, or had completed within the past 18 months, a clinical placement. A 61-item questionnaire (comprising closed- and open-ended items) assessed GenAI use, task patterns, perceived benefits or risks, and training or governance needs. A composite index classified self-perceived GenAI maturity as minimal, limited, moderate, or high. Group comparisons used χ2 tests; maturity gradients used trend tests. RESULTS: A total of 388 students responded (n=308, 79.4% women), mainly nursing students (n=217, 55.9%). Overall, 204 (52.6%) students reported using GenAI during clinical placements. Use differed across disciplines (χ24=10.71; P=.03), with lower uptake in midwifery (6/23, 26%; odds ratio 0.30, 95% CI 0.11-0.77). Adoption increased markedly with self-perceived maturity (minimal: 2/22, 9% vs high: 22/29, 76%; trend P<.001). Among the 204 users, the most commonly reported uses were information retrieval (n=159, 77.9%), bibliographic search (n=152, 74.5%), and translation or rephrasing (n=145, 71.1%); patient-facing activities were less frequently reported (eg, patient-document drafting or communication preparation: n=78, 38.2%). Although most users reported never entering direct patient identifiers, 48 (23.5%) reported at least 1 disclosure of patient-identifying information, and 96 (47.1%) reported processing real medical content perceived as anonymized. The most endorsed perceived benefits among the 388 students were documentation support (n=315, 81.2%) and improved access to information (n=266, 68.5%). The most endorsed risks were dependency (n=353, 90.9%), skill erosion (n=329, 84.8%), and confidentiality breaches (n=339, 87.4%). Training needs were highest for ethics or regulatory training (294/378, 77.7%) and a best-practice clinical guide (292/373, 78.3%). CONCLUSIONS: GenAI is already used by a substantial proportion of French students in health professions during clinical placements, predominantly for information and documentation support rather than patient-facing activities. Self-perceived readiness is strongly associated with adoption. Reported disclosures and concurrent concerns about dependency, skill erosion, and confidentiality support the need for structured curricula and clear governance frameworks to enable responsible, patient-centered integration of GenAI into clinical education.
3 May 2026
Read appraisal →European journal of pediatrics
Evaluating the impact of simulation on patient outcomes in pediatric and neonatal critical care: a systematic review and critical appraisal of the evidence
UNLABELLED: While the literature widely supports a positive relationship between simulation-based education (SBE) and learning outcomes, its impact on patient outcomes remains less clearly understood. Our aim was to comprehensively survey the landscape of simulation-based research (SBR) that evaluates patient outcomes (Kirkpatrick Level 4) in the context of pediatric and neonatal critical care. A systematic search of MEDLINE, Cochrane Library, CINAHL, and ERIC was conducted through December 2024. We included RCTs, non-RCTs, and before-after studies focusing on Kirkpatrick Level 4 outcomes. Quality was appraised using the RoB 2 and ROBINS-I tools. A total of 2481 articles were screened. Sixteen studies met the inclusion criteria. Most were prospective (63%) and single-center (69%), with only three RCTs (19%). All included studies (100%) reported Level 4 outcomes; however, a critical distinction emerged between system-level and patient-level results. While 75% (12/16) of studies reported positive impacts on Level 4a (system processes), such as protocol adherence or response times, only 50% (8/16) demonstrated significant improvements in Level 4b (direct patient outcomes), such as mortality or complication rates. In addition, all included studies were judged to have a high or critical risk of bias. CONCLUSIONS: Although SBE effectively optimizes clinical processes (Level 4a), a significant evidence gap remains regarding its direct impact on patient health (Level 4b). Current SBR often lacks the methodological rigor-specifically the use of randomized designs-needed to isolate SBE as the primary driver of clinical improvement. Future research must prioritize high-quality, multicenter trials targeting patient-oriented metrics to bridge this translational gap. WHAT IS KNOWN: • SBE has been extensively developed in pediatric and neonatal critical care settings; however, its impact on healthcare professional training and on patient outcomes remains less well understood. WHAT IS NEW: • There is a scarcity of rigorous Level 4 evidence linking SBE to patient outcomes in pediatric and neonatal critical care. • We provide a methodological roadmap advocating for mixed-methods and multicenter designs to bridge this clinical evidence gap.
1 May 2026
Read appraisal →PloS one
Gender disparities in Italian academic medicine: A cross-sectional study of clinicians in the 2024 stanford top 2% scientists database
BACKGROUND: Women remain underrepresented in senior and influential research positions despite gradual improvements over recent decades.The aim of this study was to assess gender representation among highly cited Italian clinical scientists and to examine differences across academic fields, institutions, and geographic regions. METHODS: We conducted a cross-sectional analysis of Italian clinical scientists included in the 2024 Stanford Top 2 Percent Scientists database. Gender was determined from given names, and demographic and academic information was obtained from national physician registries and publicly available curriculum vitae. Characteristics were compared by gender, and a logistic regression model was used to examine factors associated with female representation. RESULTS: A total of 3389 clinical scientists were identified, of whom 824 were women. Women represented approximately one quarter of highly cited Italian clinical researchers. They were younger and had more recent years of first publication compared with men. No significant gender differences were observed in academic affiliation or geographic distribution. Representation varied across fields, with surgical specialties demonstrating the lowest proportions of women and toxicology the highest. However, in most disciplines, representation converged toward the overall average when sample sizes increased, indicating that academic fields alone contributed minimally to gender representation. In the multivariable model, only toxicology showed significantly greater female representation, while more recent year of first publication was independently associated with being a woman.. CONCLUSIONS: Women remain underrepresented among highly cited Italian clinical scientists, despite evidence of gradual improvement in representation over time. The limited influence of academic fields suggests that broader structural and cultural factors likely contribute to these gaps. These findings highlight the need for targeted strategies to promote equal representation and support the career advancement of women in academic medicine.
28 Apr 2026
Read appraisal →BMJ open
Do studies of interventions to improve laypeople's critical thinking about health choices assess potential harms? A systematic review.
OBJECTIVES: To make informed health choices, and avoid waste and unnecessary suffering, people need critical thinking skills. However, like health interventions, educational interventions can have adverse effects. In this systematic review, the objective was to assess the extent to which researchers have included potential adverse effects in studies of interventions intended to improve the critical thinking of laypeople about health choices. DESIGN: This study was a systematic review, in which we updated the search for an earlier systematic review of intended effects of relevant interventions. The earlier review did not address potential adverse effects. We did not update the analysis of intended effects. DATA SOURCES: We searched Cochrane Central Register of Controlled Trials (CENTRAL), Cumulative Index to Nursing and Allied Health Literature (CINAHL), Embase, Epistemonikos, Medical Literature Analysis and Retrieval System Online (MEDLINE), Education Resources Information Center (ERIC) and Web of Science up to March 2025. In addition to studies from the original review and updated search, we included any additional studies included in a similar, even earlier review. Our unit of analysis was study report (eg, journal article). ELIGIBILITY CRITERIA: We included all studies from the original review. We applied the same inclusion criteria to the results of the updated search: the study included a comparison, the population was laypeople and the intervention was intended to improve understanding of ≥1 key concept for informed health choices. DATA EXTRACTION AND SYNTHESIS: We extracted data about study design (randomised trial or other), participants (children, adolescents or adults), study setting (countries), main intervention (resources delivered to participants) and comparator (usual/no intervention or other). For the analysis, we extracted verbatim text describing any assessment of a potential adverse effect of the intervention. We conducted a narrative synthesis of the extracted data. RESULTS: We included 35 reports of quantitative studies (including multi-method and mixed-methods studies). Most often, the study was a randomised trial, the setting was a high-income country, the population included adults (including university students) and the intervention was school-based (including university). In one of the 35 reports, authors described assessing a potential adverse effect. CONCLUSION: To our knowledge, this is the first systematic review assessing the extent to which researchers have assessed adverse effects of any category of educational interventions. Our review shows that researchers generally have not assessed potential adverse effects of interventions to improve critical thinking about health choices. Researchers should pay more attention to such effects, while policymakers and educators making decisions about implementing relevant interventions should consider the lack of evidence. The findings of this study suggest a need for research that facilitates assessing potential adverse effects of interventions to improve critical thinking about health choices.
27 Apr 2026
Read appraisal →PloS one
The application of large language models in meteorology graduate research: current status, impact, and prospects
With the rapid development of generative artificial intelligence, large language models (LLMs) have gradually integrated into various fields, demonstrating significant potential, particularly in meteorological research. This study explores the current application, advantages, challenges, and future development trends of LLMs in the scientific work of meteorology graduate students at NUIST. Through surveys and case analysis, the study finds that LLMs are primarily applied in literature review, data processing, code development, and academic writing in meteorological research. The results show that LLMs significantly enhance research efficiency, particularly in code development and literature translation, saving considerable time for graduate students. However, challenges remain in areas such as the accuracy of professional knowledge, creative inspiration, and interdisciplinary integration. The study also reveals concerns over data security, academic integrity, and model limitations when using LLMs. Future applications of LLMs in meteorology need further optimization in terms of professional knowledge accuracy and data processing capabilities. This paper provides both theoretical support and practical guidance for the responsible integration of LLMs into meteorological research and education.
27 Apr 2026
Read appraisal →JMIR mental health
Expected Competencies and Personal Attributes of Digital Health Navigators to Support Digital Mental Health Care: Focus Group and Interview Study With Patients and Health Care Professionals
BACKGROUND: Digital mental health apps (DMHAs), and in particular digital therapeutics (DTx), offer promising opportunities to support mental health care. However, their effective use in outpatient settings in Germany remains limited. To overcome this gap, the role of digital health navigators (DHNs) has been introduced. DHNs are trained individuals who support patients and health care professionals in selecting, using, and integrating DMHAs into care. Despite increasing interest in this role, there is limited evidence on the competencies, knowledge, and personal attributes required for DHNs to work effectively in mental health settings. OBJECTIVE: The study aims to explore the expected competencies, knowledge areas, and personal attributes that DHNs need to effectively support the implementation and use of DTx in outpatient mental health care. METHODS: As part of the prestudy of the Digital Navigators for Acceptance and Competence Development with Mental Health Apps (DigiNavi) study, a qualitative study was conducted involving 35 participants (7 general practitioners, 8 patients in general practice, 11 outpatient psychiatrists/psychologists, and 9 patients in psychiatric outpatient clinics) from different general practices and psychiatric outpatient clinics in Germany. A total of 17 semistructured interviews and 4 focus groups were conducted to explore expectations of DHNs. Data were analyzed using qualitative content analysis. RESULTS: Participants emphasized that DHNs should combine strong interpersonal skills (empathy, patience, and sensitive communication) with technical and basic clinical competencies. Most favored DHNs as integrated clinical team members (eg, medical assistants), citing their existing patient relationships, but noted time and training constraints. Key expectations included the ability to support patients with DTx use, adapt communication to individual needs, and convey data privacy information clearly. Foundational knowledge of mental health conditions and sensitivity to crises were considered important for identifying warning signs and escalating concerns. While DHNs were seen as essential intermediaries between patients, health care professionals, and DTx, participants highlighted the necessity for clearly defined roles, structured training, and realistic expectations to prevent role overload and enable sustainable implementation in outpatient mental health care. CONCLUSIONS: DHNs require a specialized skill set that bridges clinical understanding, digital expertise, and interpersonal competence. Our results lay the groundwork for developing training curricula and implementation strategies that align with real-world expectations for the DHN role. Defining these core competencies is essential for supporting the sustainable and effective integration of DMHAs into mental health care.
26 Apr 2026
Read appraisal →The pharmacogenomics journal
A randomized trial to evaluate attitudes regarding pharmacogenomics among pregnant and pediatric populations: design and baseline characteristics.
Pharmacogenomics (PGx) is a key component of precision medicine, yet most PGx studies exclude pregnant people and children. The VICE (Vanderbilt Integrated Center of Excellence)-MPRINT (Maternal and Pediatric Precision in Therapeutics): Maternal and Pediatric Pharmacogenetics Trial is a single-center, randomized control trial to assess how PGx testing and return of results influence patients' understanding and perceived utility of PGx testing in a pregnancy and pediatric cohort. Pregnant individuals and families or guardians of children with a chronic health condition aged 0-16 were recruited. We assessed participants' knowledge and attitudes regarding PGx testing at baseline and after receiving results with patient-friendly interpretations. Cases received an educational video about PGx testing with return of results. Controls received PGx test results alone. We aimed to determine perspectives regarding PGx in these understudied populations with the goal of promoting research and clinical implementation of PGx for pregnant women and children.
26 Apr 2026
Read appraisal →PloS one
Cognitive load and pedagogical tension in multi-platform online learning: Evidence from Chinese higher education
The proliferation of digital tools has transformed higher education into a complex, multi-platform online learning environment. This study investigates the paradoxical effects of this multi-platform environment on the student experience within Chinese higher education. Through the qualitative and quantitative data from a cross-sectional survey of 8,616 university students, we analyzed platform usage patterns, perceived benefits and challenges. The findings reveal a significant paradox: while students express positive attitudes towards platforms' educational value, acknowledging benefits like enhanced self-directed learning and improved teacher-student interaction, they concurrently report substantial practical burdens. A serial mediation model confirmed that platform multiplicity increases extraneous cognitive load, which in turn elevates tool fatigue, ultimately leading to a more negative perception of the learning experience. This study identifies a core "pedagogical tension" between the intended benefits of educational technology and the lived reality of a fragmented, high-friction user experience that encourages instrumental engagement over deep learning. These findings underscore the urgent need for institutions and instructors to adopt a more strategic, integrated approach to educational technology to reduce fragmentation and prioritize a seamless student learning experience.
25 Apr 2026
Read appraisal →PloS one
Evaluation of large language models in medical examinations: A scoping review protocol
INTRODUCTION: Standardized medical examinations, used to assess trainee clinical competencies, provide a rigorous means to verify LLM accuracy and reliability in medical contexts. Although current evaluations use these exams to test LLMs' clinical reasoning, significant performance variations occur across different clinical scenarios. Existing methods struggle to adapt to evolving research needs. This study synthesizes prior research on LLMs in medical exams, highlighting current limitations and proposing future research directions. METHODS AND ANALYSIS: The formulation of the protocol was guided by the standards set forth in the JBI Manual for Evidence Synthesis. Following the establishment of precise inclusion/exclusion criteria and search strategies, we will execute systematic searches in the PubMed and Web of Science Core Collection databases. The method encompasses literature review, data extraction, analytical frameworks, and process mapping. By employing this method, researchers maintain methodological rigor during the entire research process. ETHICS AND DISSEMINATION: This protocol describes a method for performing a scoping review. The investigation focuses on the organized synthesis and examination of previously published research. It does not include human/animal experimentation or sensitive data collection. Ethical approval is not required for this literature-based study.
24 Apr 2026
Read appraisal →BMJ open
Arts-based empathy education in healthcare: a critical systematic review of pedagogical mechanisms and evidence gaps
OBJECTIVES: To systematically identify and synthesise the pedagogical mechanisms through which arts-based interventions (theatre, poetry, narrative medicine) may support empathy development in healthcare learners, while critically appraising the contextual implementation factors and methodological limitations of the existing evidence base. DESIGN: Systematic review with narrative synthesis, conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. DATA SOURCES: MEDLINE (via PubMed), Embase, PsycINFO, ERIC, Cochrane Central Register of Controlled Trials, Web of Science Core Collection and CINAHL Plus, from inception to 31 August 2025. ELIGIBILITY CRITERIA FOR SELECTING STUDIES: Peer-reviewed empirical studies involving undergraduate or postgraduate healthcare students or professionals. Eligible studies reported on arts-based educational interventions designed to enhance empathy (including theatre, poetry or narrative medicine) and included quantitative or qualitative outcome measures of empathy or related constructs. No restrictions were placed on study design. DATA EXTRACTION AND SYNTHESIS: Two reviewers independently screened records, extracted data on intervention characteristics and outcomes, and assessed methodological quality using the Medical Education Research Study Quality Instrument and Critical Appraisal Skills Programme tools. A narrative synthesis was conducted to examine patterns across intervention modalities. Effect sizes (Cohen's d) were calculated for quantitative pre-post or controlled designs; meta-analysis was precluded due to high heterogeneity in study designs, populations and outcome measures. RESULTS: From 1094 records screened, 17 studies involving 835 participants (median sample size=28) met inclusion criteria. There were eight theatre-based, five poetry-based and four narrative medicine interventions. Theatre interventions, which emphasised embodied learning, showed patterns of large empathy effects (mean d=0.83). Poetry interventions, focusing on reflective practice, showed patterns of moderate effects (mean d=0.49). One study of narrative medicine demonstrated a pattern of sustained gains at 2-year follow-up (d=0.82). Key limitations of the evidence base include small sample sizes, substantial measurement heterogeneity (12 different empathy instruments), geographical bias (88% of studies from high-income, Western countries), and a predominance of pre-post study designs. CONCLUSIONS: Arts-based interventions show mechanism-specific patterns of potential benefit for empathy in healthcare learners. However, significant methodological limitations in the current evidence constrain definitive practice recommendations. Educators may consider piloting brief, facilitator-led interventions based on local resources, while acknowledging the need for more robust evidence. Future research must prioritise standardised outcome measures, rigorous controlled and longitudinal trial designs, and studies in diverse cultural contexts. PROSPERO REGISTRATION NUMBER: CRD42025116174.
24 Apr 2026
Read appraisal →PloS one
Successful student learning outcomes in Moroccan higher education: Causal configurations of pedagogical, motivational, and ICT conditions using fuzzy-set Qualitative Comparative Analysis (fsQCA)
As the demand for better educational quality and improved student performance grows, institutions face increasing challenges in making their teaching methods more effective to ensure successful learning outcomes. Most practical recommendations tend to focus on isolated effects, but learning success usually results from interconnected factors that work together. Drawing on constructivist Learning Theory, this study examines pedagogical and motivational factors that can positively impact learning results in higher education within Moroccan universities. The main goal is to identify and evaluate the nonlinear individual effects and the interactive causal configurations involving multiple conditions, such as teacher motivation, pedagogical leadership, self-efficacy, instructional innovation, ICT use, and student motivation, on learning outcomes. Empirical data were gathered through a questionnaire completed by 349 Moroccan university students, using measurement scales for key variables. The analysis employed the fuzzy-set Qualitative Comparative Analysis (fsQCA) method, which helps identify different combinations and causal pathways that lead to high academic achievement. Findings suggest that excellent learning outcomes are not caused by a single factor but by the interaction of several interdependent conditions. Different "recipes" can produce similar strong results. Certain combinations, especially those with strong teacher motivation, effective leadership, and strategic ICT use, proved to be reliable configurations, showing that technology is most impactful when integrated into supportive pedagogical and motivational environments. These results can help redefine and evaluate integrated educational policies, considering the complex interactions among individual, pedagogical, and technological factors. This approach promotes more effective and equitable learning environments through coherent bundles of mutually reinforcing interventions, instead of isolated efforts. Ultimately, this research enables educators and policymakers to develop more targeted strategies, utilize resources more efficiently, and improve overall educational effectiveness.
23 Apr 2026
Read appraisal →Medical education online
Medical students' attitudes towards older persons - a systematic review and meta-analysis
OBJECTIVE: Ageism negatively affects older people's health, well-being, and quality of care. Identifying ageism and attitudes toward older adults may help identify medical students motivated to work with a growing older population. We conducted a systematic review of interventions to reduce ageism among medical students. METHODS: We conducted a systematic literature retrieval in Medline, the Cochrane Library, Epistemonikos and PubMed via Ovid, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses, from database inception to August 23rd, 2024. We searched for studies examining medical students' attitudes towards older persons, including interventions to influence these attitudes. RESULTS: The systematic review included 21 studies. Study samples ranged between 29 and 415, with a pooled total of 3940 medical students, the majority conducted in the USA. The meta-analysis of students' attitudes before and after all interventions included a total of 2004 students, yielding a non-significant standardized mean difference (SMD) of 0, 12 (95% CI -0, 01 to 0, 26). The meta-analysis of students' attitudes before and after all interventions (35-37, 39, 41, 45, 48, 50), after removing UCLA-GAS and R-GAS, included a total of 1344 students with a standardized mean difference of 0, 23 (95% CI 0, 06 to 0, 40). Analysis of empathy-based teaching interventions included 1652 students, and showed a statistically significant effect, SMD 0, 18 (95% CI 0, 01 to 0, 34). Analysis of 352 students receiving traditional teaching methods yielded no effect on ageism, with an SMD -0, 13 (95% CI -0, 81 to 0, 54). High heterogeneity (I2 75-85%) affects our confidence in the effect estimates. CONCLUSION: Empathy-based interventions seem to improve medical students' attitudes towards older persons. Traditional teaching methods may increase negative attitudes. Considering the high heterogeneity, the results should be interpreted cautiously. Adding empathy-based components to medical curricula could combat ageism. More studies are needed to examine whether the results of studies from North America are valid globally.
23 Apr 2026
Read appraisal →JMIR infodemiology
Cross-Sectional Evaluation of Medical Disinformation Safeguards in Consumer-Facing Large Language Model Platforms
This cross-sectional evaluation of six consumer-facing large language model platforms found significant heterogeneity in safeguard performance against the generation of health disinformation, with Claude and ChatGPT demonstrating complete resistance across all prompt types, while Copilot, Meta AI, Grok, and Gemini exhibited substantial vulnerabilities.
22 Apr 2026
Read appraisal →Journal of medical Internet research
The Real-Time Support Role of Augmented Reality Technology in Shared Decision-Making in Neurosurgery Under the SEGUE Framework: Randomized Controlled Trial
BACKGROUND: Preoperative risk communication is essential for shared decision-making (SDM) in neurosurgery; however, conveying complex neuroanatomy and surgical risks using traditional verbal explanations can limit understanding and contribute to dissatisfaction and medicolegal disputes. Augmented reality (AR) may provide patient-specific, interactive 3D visualization to support these conversations. OBJECTIVE: This study evaluates whether AR-assisted preoperative risk communication improves objective understanding and other SDM-related outcomes, compared with communication supported by a conventional physical anatomical model within a standardized SEGUE-informed protocol. METHODS: A prospective, single-center, randomized controlled trial was conducted with 62 neurosurgery communication recipients (patients when capable; otherwise, a legally authorized representative [LAR]). Patients were stratified by planned surgical approach (frontal, parietal, and occipital) and, within each stratum, were randomized into an experimental AR group and a control physical-model group. The primary outcome was postsession objective understanding, assessed by a multiple-choice knowledge questionnaire. Secondary outcomes were subjective understanding, communication satisfaction, pre-to-post anxiety changes, communication duration, and neurosurgeons' communication skills from video recordings. RESULTS: Of the 67 individuals screened, 62 communication recipients were enrolled and completed all assessments (patients, n=30; LARs, n=32; AR, n=32; and control, n=30). Objective understanding was higher with AR than with the physical model in the prespecified pooled comparison (P=.01). Communication satisfaction was also higher with AR (P<.001). There were no clear between-group differences in subjective understanding (P=.41), anxiety changes (ΔState-Trait Anxiety Inventory [ΔSTAI] Y-1, P=.37; ΔSTAI Y-2, P=.84), in-session face-to-face communication duration (excluding any presession AR technical preparation time; P=.73), or SEGUE scores (P=.60). Exploratory stratified analyses suggested larger comprehension gains with AR in the parietal and occipital approach strata. CONCLUSIONS: In a standardized preoperative SDM conversation, an integrated visualization-support package combining AR, patient-specific modeling, and interactivity improved neurosurgical decision makers' objective understanding and satisfaction without prolonging in-session, face-to-face communication duration. Larger multicenter trials with longer-term outcomes are warranted to confirm effectiveness and to evaluate implementation and cost considerations. TRIAL REGISTRATION: ISRCTN Registry ISRCTN11483487; http://www.isrctn.com/ISRCTN11483487.
20 Apr 2026
Read appraisal →PloS one
AI literacy among basic school teachers in Ghana: A structural equation modelling analysis
Understanding the synergy of Artificial Intelligence (AI) literacy among teachers is imperative for successful integration in educational settings. This study examined basic school teachers' (BSTs) AI literacy based on four key aspects: AI knowledge and understanding (KUAI), AI application (AAI), AI application evaluation (EAIA), and AI ethics (AIE). The study employed a cross-sectional survey design and purposive sampling to collect data from 319 BSTs in Ghana. A variance-based structural equation modelling (VB-SEM) approach was used to explore the relationships between these dimensions and provide insights into their interrelationships. The study found that AAI positively influenced KUAI, EAIA, and AIE. However, AIE did not significantly influence KUAI and EAAI. In addition, KUAI did not influence EAIA. The findings contribute to understanding the current state of AI literacy among BSTs in Ghana and highlight areas for improvement in AI education and professional development programmes.
19 Apr 2026
Read appraisal →Medicine
Integration of the ISO 15189 quality management system in the undergraduate internship teaching of medical laboratory technology
BACKGROUND: The International Organization for Standardization (ISO) 15189 standard is essential for quality management in clinical laboratories, yet its integration into undergraduate medical laboratory technology education remains limited. This study aimed to evaluate the impact of a simulated laboratory teaching model based on the ISO 15189 standard on the quality management competencies of undergraduate interns and to compare it with traditional teaching methods. METHODS: A parallel-group, randomized controlled trial was conducted in the Department of Clinical Laboratory at the Second People's Hospital of Hunan Province (Brain Hospital of Hunan Province). A total of 60 undergraduate medical laboratory technology students scheduled to commence their clinical clerkship between July 2023 and May 2025 were enrolled and randomly allocated to an intervention group (n = 30) or a control group (n = 30). The intervention group received simulated laboratory teaching based on the ISO 15189 standard, including the construction of a quality management system and full-process simulated accreditation practice. The control group received traditional clinical clerkship teaching. Primary outcome measures were comprehensive assessment scores at the end of the internship (covering pre-examination, intra-examination, and post-examination quality control knowledge) and problem-solving ability scores in quality management roles. Secondary outcome measures included understanding of the quality management system, quality improvement awareness, and teaching satisfaction. RESULTS: Compared with the control group, the intervention group showed significantly higher scores in pre-examination quality control, intra-examination quality control, post-examination quality control, understanding of the quality management system, quality improvement awareness, and problem-solving ability in quality management roles (P < .01). Teaching feedback questionnaires also indicated higher satisfaction with the teaching model in the intervention group. CONCLUSION: For undergraduate medical laboratory technology interns, the simulated laboratory teaching model based on the ISO 15189 standard is significantly more effective than traditional teaching methods in enhancing their knowledge, skills, and competency in quality management.
19 Apr 2026
Read appraisal →PloS one
Evidence-based action plan for integrating artificial intelligence in an academic medical centre-a multidisciplinary approach
INTRODUCTION: As the effectiveness of artificial intelligence (AI) in enhancing various facets of healthcare delivery becomes more apparent, it is anticipated that AI will soon find its way into standard clinical practices, even in low and middle-income countries. The objective of this study was to create an action plan for integrating AI into medical education, research, and clinical practices utilizing the SWITCH model of change integrating both rational and emotional aspects. METHODS: This exploratory qualitative study employed reflexive thematic analysis of semi-structured interviews and a co-design workshop, followed by the collaborative development of an action plan. The study was conducted from May 2023 to May 2024, at the Aga Khan University, Karachi, Pakistan. The development of an action plan was informed by interviews, co-design workshop, and discussions with diverse group of academic leaders, healthcare professionals and medical students. All interviews, workshop sessions, and planning meetings were audio recorded, transcribed verbatim, and anonymized. Data management was conducted manually using Microsoft Word and Excel. Findings after thematic analysis of the qualitative interviews and findings from the co-design workshop were gradually, and inductively transformed into the content for the action plan for integrating AI into healthcare. RESULTS: The content analysis of interviews identified following four themes: AI opportunities, apprehensions toward AI-induced changes, pushing change through leadership styles, and importance of AI related capacity building. During the workshop, participants discussed aligning current AI knowledge with future requirements by identifying clear instructions, emotional motivators, and environmental changes required on the path of AI integration. The proposed action plan conceptualized AI integration as multidimensional change process comprising three domains: strategic actions, change pathway enablement and environmental readiness and human motivation operationalized through twenty actionable components. CONCLUSION: The study findings provide a context specific conceptual action plan for healthcare professionals to integrate AI into medical education, clinical service and research, Future work should focus on pilot implementation and empirical validations of the action plan across diverse healthcare settings to assess feasibility, effectiveness and scalability.
18 Apr 2026
Read appraisal →JMIR research protocols
Evaluating the Role of Surgical Telementoring in the Acquisition of Surgical Skills in Laparoscopic Cholecystectomy: Protocol for a Pilot Randomized Controlled Trial
BACKGROUND: Developing surgical skills among residents requires time and resources, often in conflict with the goals of efficiency and hospital economics in surgical practice. Optimizing resident training may prevent a decline in quality. Skilled surgeons are vital to effective and safe surgical performance, yet the training trajectory for surgical residents is often inefficient, particularly in the era of minimally invasive surgery. A framework that efficiently disseminates surgical skills is essential to cultivate skilled future surgeons within an acceptable time frame. Surgical telementoring (ST) aligns well with minimally invasive surgery because the mentee operating in the field shares the telementor's perspective. Despite growing experience with telemedicine, data on educational outcomes remain limited. OBJECTIVE: We aim to conduct a pilot randomized controlled trial (RCT). Data collection will inform a future full-scale RCT evaluating whether real-time ST, combined with structured postoperative coaching, is superior to traditional on-site mentoring in developing laparoscopic cholecystectomy skills among surgical residents. METHODS: Eligible residents will be randomly assigned in a 1:1 ratio to either the intervention group (real-time ST and postoperative coaching) or the control group (traditional intraoperative hands-on teaching). This research adheres to the extended SPIRIT (Standard Protocol Items: Recommendations for Interventional Trials) statements for pilot RCTs and follows the intention-to-treat principle. Residents in both groups will perform 5 consecutive procedures under standardized intraoperative conditions. The primary outcomes are the Global Operative Assessment of Laparoscopic Skills (GOALS) score and the Non-Technical Skills for Surgeons (NOTSS). We hypothesize that the intervention group will show a 3- to 5-point improvement in the GOALS score compared with the control group. To achieve 0.8 statistical power, a P value <.05, and a 20% dropout rate in a definitive RCT, 12 residents per group are required. We present a pilot RCT with 5 residents per group. Challenges encountered during the trial will be reported, and amendments will be proposed to assess the need for a future definitive RCT. RESULTS: The primary outcomes will be technical and nontechnical surgical skills, measured by the GOALS and NOTSS scores, respectively. Patient-reported experience measures and satisfaction scores of eligible mentees and mentors will be analyzed as secondary outcomes. The ST system configuration at the 2 inclusion centers was completed in December 2023. Ethics approval and the most recent update report to ClinicalTrials.gov were obtained on October 23, 2023, and December 8, 2024, respectively. Recruitment of residents to the study commenced in spring 2024. Recruitment is expected to be completed in May 2026, with data analysis in November 2026 and manuscript submission of results in January 2027. CONCLUSIONS: The SURGTEACH (Surgical Telementoring in Acquisition of Surgical Skills of Laparoscopic Cholecystectomy) trial is the first pilot RCT evaluating ST for educational outcomes. This research may provide high-quality evidence to improve surgical education, particularly in rural hospitals.
18 Apr 2026
Read appraisal →JMIR formative research
Public Perceptions of AI in Medicine and Implications for Future Medical Education: Cross-Sectional Survey
BACKGROUND: The integration of artificial intelligence (AI) into clinical practice is contingent on public trust. This trust often depends on physician oversight, yet a significant gap exists between the need for AI-competent physicians and the current state of medical education. While the perspectives of students and experts on this gap are known, the views of the US general public remain largely unquantified. OBJECTIVE: This study aimed to assess US public perceptions regarding AI in medicine and the corresponding emergent needs for medical education. We specifically sought to quantify public trust in different diagnostic scenarios, concerns about physician overreliance on AI, support for mandatory AI education, and priorities for the future focus of medical training. METHODS: We conducted a cross-sectional, web-based survey of adults in the United States in November 2025. Participants (N=524) were recruited via SurveyMonkey Audience. We calculated descriptive statistics, frequencies, proportions (percentages), and 95% CIs for all main survey items. RESULTS: A total of 524 participants completed the survey. Most (n=329, 62.8%; 95% CI 58.6%-66.9%) placed the most trust in a physician's diagnosis based on their expertise alone; only 7.8% (n=41; 95% CI 5.5%-10.1%) trusted an AI-first diagnostic model. Trust was highly contingent on training: 93.9% (n=492) of participants rated formal physician training on AI limitations as "essential" or "very important." Widespread concern about physician overreliance on AI was reported, with 81.1% (n=425) being "very concerned" or "extremely concerned." Consequently, 85.1% (n=446) agreed or strongly agreed that training on AI use, ethics, and limitations should be mandatory in medical school. When asked about future educational priorities, 70.2% (n=368; 95% CI 66.3%-74.1%) believed that medical education should focus on human-centered skills (eg, empathy and communication) over clinical skills. CONCLUSIONS: The US public expressed conditional trust in medical AI, strongly preferring physician-led and critically supervised models. These findings reveal a clear public mandate for medical education reform. The public expects future physicians to be mandatorily trained to appraise AI, understand its limitations, and refocus their professional development on the human-centered skills that technology cannot replace.
18 Apr 2026
Read appraisal →Journal of neurointerventional surgery
Feasibility and non-inferiority of mobile telementoring for digital subtraction angiography: a single-center observational study
BACKGROUND: Telementoring is an emerging approach in surgical education that offers remote supervision and guidance through digital platforms. This study aimed to evaluate the feasibility and non-inferiority of a mobile-based telementoring system for digital subtraction angiography (DSA) and compare it with traditional face-to-face mentoring. METHODS: This prospective, single-center observational study included 71 patients who underwent DSA between April 2021 and May 2024. Patients were categorized into control (n=48, face-to-face mentoring) and telementoring (n=23) groups. A mobile telementoring system (JOIN, Allm Inc., Tokyo, Japan), which enabled real-time image sharing and voice communication between the examiner and the remote supervisor, was employed. The primary endpoints were contrast volume, procedural time, and radiation dose, with a non-inferiority margin of 20% applied. RESULTS: No significant differences were observed between the two groups in contrast volume (88.3±39.6 mL vs 97.1±36.4 mL, p=0.499), procedural time (44.1±17.7 min vs 50.7±19.0 min, p=0.308), or radiation dose (427.9±262.2 mGy vs 506.6±307.1 mGy, p=0.346). Non-inferiority was confirmed across all primary endpoints. No procedural complications occurred. Qualitative feedback indicated high user satisfaction, with the system facilitating effective remote supervision and decision-making. CONCLUSIONS: This study demonstrates the feasibility and non-inferiority of a mobile telementoring system for DSA, effectively supporting real-time remote guidance and reducing the need for on-site supervision. Its implementation may enhance access to expert mentoring, particularly in regions with limited specialist availability, contributing to equitable and efficient cerebrovascular care.
18 Apr 2026
Read appraisal →Thorax
Digital twin-based bronchoscopy simulator improves training performance and skill retention of novices: a randomised controlled study
RATIONALE: Conventional bronchoscopy training often does not ensure lasting skill retention or adaptability to different anatomies, limiting real-world impact. This study used a digital-twin bronchoscopy simulator with various CT-derived bronchial tree models to better train novices. OBJECTIVES: To explore training with various anatomically diverse bronchial tree models in novices' bronchoscopy performance. METHODS: 60 bronchoscopy-naive participants were randomly assigned to three groups (n=20 each): control (written instruction only), anatomic-uniformity (trained on one standard bronchial model) and anatomic-variety (trained on multiple patient-derived bronchial models). All participants performed two tests: test 1 on a standard model and test 2 on a new CT-derived model. Both tests were repeated 3 months later to assess skill retention. The primary comparison was between the anatomic-variety and anatomic-uniformity groups. MEASUREMENTS AND MAIN RESULTS: 60 participants completed tests 1 and 2. 55 returned at 3 months. In test 1, there were no significant differences between the anatomic-variety and anatomic-uniformity groups in diagnostic completeness (DC, 0 segments, p=0.576), structured progress (SP, 1 correct progression, p=0.091) and procedure time (31 s, p=0.831). In test 2, the anatomic-variety group had significantly higher DC (2.5 segments, p<0.001) and SP (9 progression, p<0.001) than the anatomic-uniformity group. At 3 months, the anatomic-variety group retained superior DC and SP scores in both tests despite slight declines. CONCLUSIONS: Training with diverse anatomical models significantly enhanced bronchoscopy performance compared with repetitive practice on a single standardised model with partially maintained learning gains at 3 months.
17 Apr 2026
Read appraisal →JMIR cardio
Large Language Models in Cardiology: Systematic Review
BACKGROUND: Large language models (LLMs) are increasingly used in health care, but their role in cardiology has not yet been systematically evaluated. OBJECTIVE: This review aimed to assess the applications, performance, and limitations of LLMs across diverse cardiology tasks, including chronic and progressive conditions, acute events, education, and diagnostic testing. METHODS: A systematic search was conducted in PubMed and Scopus for studies published up to April 14, 2024, using keywords related to LLMs and cardiology. Studies evaluating LLM outputs in cardiology-related tasks were included. Data were extracted across 5 predefined domains and the risk of bias was assessed using an adapted QUADAS-2 tool (developed by Whiting et al at the University of Bristol). The review protocol was registered in PROSPERO (CRD42024556397). RESULTS: A total of 33 studies contributed quantitative outcome data to a descriptive synthesis. Across chronic conditions, ChatGPT-3.5 (OpenAI) answered 91% (43/47) heart failure questions accurately, although readability often required college-level comprehension. In acute scenarios, Bing Chat omitted key myocardial infarction first aid steps in 25% (5/20) to 45% (9/20) of cases, while cardiac arrest information was rated highly (mean 4.3/5, SD 0.7) but written above recommended reading levels. In physician education tasks, ChatGPT-4 (OpenAI) demonstrated higher accuracy than ChatGPT-3.5, improving from 38% (33/88) to 66% (58/88). In patient education studies, ChatGPT-4 provided scientifically adequate explanations (5.0-6.0/7) comparable to hospital materials but at higher reading levels (11th vs 7th grade). In diagnostic testing, ChatGPT-4 interpreted 91% (36/40) electrocardiogram vignettes correctly, significantly better than emergency physicians (31/40, 77%; P< .001), but showed lower performance in echocardiography. CONCLUSIONS: LLMs show meaningful potential in cardiology, especially for education and electrocardiogram interpretation, but performance varies across clinical tasks. Limitations in emergency guidance and readability, as well as small in silico study designs, highlight the need for multimodal models and prospective validation.
17 Apr 2026
Read appraisal →JMIR formative research
Fact-Checking Large Language Model Responses to a Health Care Prompt: Comparative Study
BACKGROUND: Large language models use machine learning to produce natural language. These models have a range of potential applications in health care, such as patient education and diagnosis. However, evaluations of large language models in health care are still scarce. OBJECTIVE: This study aimed to (1) evaluate the accuracy and efficiency of automated fact-checking by 2 large language models and (2) illustrate a process through which a large language model might support a patient in redrafting a prompt to include key information needed for patient safety. METHODS: A parallel comparison of 2 large language models and 3 human experts was conducted. A clinical scenario was devised in which a woman aged 23 years questions the safety of retinoid treatment for acne by sending prompts to 2 large language models (GPT-4o and OpenBioLLM-70B). GPT-4o and OpenBioLLM-70B were asked to suggest improvements to the patient's initial prompt to elicit key information for clinical decision-making. After the patient sent the revised prompt to the large language models, the models were then asked to fact-check the final response. To test the generalizability of automated fact-checking, a set of 20 clinical statements on disparate topics, mostly related to drug indications, contraindications, and side effects, was developed. The large language models also fact-checked these 20 medical statements. The results were compared against the evaluations of 3 clinical experts. The outcome measures were as follows: (1) percentage of accuracy of automated fact-checking, (2) time to complete fact-checking, and (3) a binary outcome for prompt redrafting (advising the patient to revise her prompt by naming her acne medication to address safety concerns). RESULTS: For the scenario of a patient with acne, GPT-4o and OpenBioLLM-70B both had 86% agreement with the clinical experts' fact-checking. The large language models did not consistently convey the urgency of discontinuing isotretinoin treatment when pregnancy is suspected. In addition, the models did not adequately convey the importance of folic acid supplementation during pregnancy. For the set of 20 medical claims, GPT-4o fact-checking had 100% agreement with that of human experts, whereas OpenBioLLM-70B had 95% agreement. OpenBioLLM-70B diverged from human experts and GPT-4o on 1 question related to pediatric use of antihistamines. The expert fact-checks took a mean time of 18 (SD 3.74) minutes, GPT-4o took 42 seconds, and OpenBioLLM-70B took 33 minutes. The GPT-4o responses for the acne scenario had some inconsistencies but zero fabrication and no obvious omissions. In contrast, OpenBioLLM-70B omitted 1 key information item needed for patient safety. CONCLUSIONS: GPT-4o can interact with patients to improve the quality and comprehensiveness of the information contained in health-related prompts. GPT-4o and OpenBioLLM-70B can conduct efficient fact-checking that is close to the level of accuracy of human experts. Human experts need to perform additional checks for accuracy and safety.
17 Apr 2026
Read appraisal →JMIR medical informatics
Classification of Cochrane Plain Language Summaries by Conclusiveness Using Transformer-Based Models and ChatGPT: Retrospective Observational Study
BACKGROUND: Cochrane plain language summaries (PLSs) aim to make systematic review findings more accessible to the general public. However, inconsistencies in how conclusions are presented may impact comprehension and decision-making. Classifying PLSs based on conclusiveness can improve clarity and facilitate informed health decisions. OBJECTIVE: This study aimed to develop and evaluate deep learning language models for the classification of PLSs according to 3 levels of conclusiveness (conclusive, inconclusive, and unclear) and to compare their performance with a general-purpose large language model (GPT-4o). METHODS: We used a publicly available dataset containing 4405 Cochrane PLSs of systematic reviews published until 2019, already classified by humans according to 9 categories of conclusiveness regarding the intervention's effectiveness or safety. We merged these categories into 3 classes based on the strength of conclusiveness: conclusive, inconclusive, and unclear. For the fine-tuning, we used Scientific Bidirectional Encoder Representations from Transformers (SciBERT), a pretrained language model trained on 1.14 million papers primarily from the health sciences, and Longformer, a transformer model designed specifically to process long documents. The script was developed using the Python programming language and the PyTorch framework. We computed evaluation metrics using the scikit-learn machine learning library and determined the area under the curve of the receiver operating characteristic (AUCROC) to measure the model performance in balancing sensitivity and specificity. We also analyzed a separate set of 213 PLSs and compared the predictions of our pretrained models with both manual verification and outputs generated by ChatGPT. RESULTS: The model based on SciBERT achieved a balanced accuracy of 56.6%. The AUCROC was 0.91 for "conclusive," 0.67 for "inconclusive," and 0.75 for "unclear" conclusiveness classes. The Longformer-based model had a balanced accuracy of 60.9%, with AUCROCs of 0.86 for "conclusive," 0.67 for "inconclusive," and 0.72 for "unclear" conclusiveness classes. Both models underperformed compared with ChatGPT, which demonstrated higher accuracy (74.2%), better precision and recall, and a higher Cohen κ (0.57). CONCLUSIONS: Fine-tuning 2 transformer-based language models showed mixed results in classifying Cochrane PLSs by conclusiveness, likely due to semantic overlap and subtle linguistic differences. Despite satisfactory internal test metrics, the fine-tuned models failed to generalize to newly published PLSs, where performance dropped to near-chance levels. These findings suggest that general-purpose large language models like GPT-4o may currently offer more reliable results for practical classification tasks in biomedical applications.
16 Apr 2026
Read appraisal →JMIR nursing
Application of the Technology Acceptance Model to Predict Nursing Students' Intention to Use Informatics: Cross-Sectional Study
BACKGROUND: Nursing informatics is essential for digital health transformation; however, the technology acceptance of undergraduate nursing students in Saudi Arabia remains underexplored. OBJECTIVE: This study examined factors influencing nursing students' intention to use informatics technologies using the technology acceptance model. METHODS: A cross-sectional survey was conducted with 132 undergraduate nursing students. Data were analyzed using descriptive, correlational, and hierarchical regression analyses. RESULTS: Perceived usefulness (mean 3.68, SD 1.22) and perceived ease of use (mean 3.64, SD 1.32) were the strongest predictors of acceptance, together explaining 87% of the variance (R²=0.87; β=0.323 for usefulness, P<.001; β=0.195 for ease of use, P=.032). Only 25.8% (n=34) of the students often used electronic health records, while 31.8% (n=42) had no electronic health record experience, indicating a clear gap in practical informatics exposure. CONCLUSIONS: Nursing students' acceptance of informatics is primarily driven by its perceived usefulness and perceived ease of use. These findings highlight the urgent need to integrate practical, user-centered informatics training and clinical simulation into undergraduate nursing curricula to better prepare students for technology-based practice.
16 Apr 2026
Read appraisal →BMJ open
Generative artificial intelligence-driven chatbots and medical misinformation: an accuracy, referencing and readability audit
OBJECTIVES: Artificial intelligence (AI)-driven chatbots have been rapidly adopted across research, education, business, marketing and medicine. Most interactions, however, come from non-experts using chatbots like search engines, including for everyday health and medical queries. DESIGN: We conducted an original study to audit chatbot responses in health and medical fields prone to misinformation. METHODS: Five popular chatbots were assessed: Gemini (Google), DeepSeek (High-Flyer), Meta AI (Meta), ChatGPT (OpenAI) and Grok (xAI). In February 2025, each chatbot was prompted with 10 questions from five categories: cancer, vaccines, stem cells, nutrition and athletic performance. We deployed an adversarial-like framework, using open- and closed-ended prompts designed to strain models toward misinformation or contraindicated advice. Two experts from each category rated responses as 'non-problematic', 'somewhat problematic' or 'highly problematic' using a coding matrix based on objective, predefined criteria. Citations were scored for accuracy and completeness, and each response was given a Flesch Reading Ease score. RESULTS: Nearly half (49.6%) of responses were problematic: 30% somewhat problematic and 19.6% highly problematic. Response quality did not differ significantly among chatbots (p=0.566) but Grok generated significantly more highly problematic responses than would be expected under a random distribution (z-score +2.07, p=0.038). Performance was strongest in vaccines (mean z-score -2.57) and cancer (-2.12), and weakest in stem cells (+1.25), athletic performance (+3.74) and nutrition (+4.35). Chatbot outputs were consistently expressed with confidence and certainty; from 250 total questions, there were only two refusals to answer (0.8%), both from Meta AI. Reference quality was poor, with a median completeness score of 40% (Q1-Q3: 20-67%). Chatbot hallucinations and fabricated citations precluded any chatbot from producing a fully accurate reference list. All readability scores were graded as 'Difficult' (30-50), equivalent to college sophomore-senior level. CONCLUSIONS: The audited chatbots performed poorly when answering questions in misinformation-prone health and medical fields. Continued deployment without public education and oversight risks amplifying misinformation.
16 Apr 2026
Read appraisal →African journal of reproductive health
Effects of Simulation-Based Mastery Learning versus Deliberate Practice on midwifery students' knowledge, skills and self confidence in managing the third stage of labour: A quasi-experimental study
Achieving maternal health care coverage by 2030 requires strengthening the midwifery workforce. To ensure accessible, culturally appropriate, and high-quality care, midwives must receive education aligned with global standards. This study aimed to evaluate the effect of a 20 hours Simulation-Based Mastery Learning (SBML) combined with Deliberate Practice (DP) and the Objective Structured Clinical Examination (OSCE) on midwifery students' knowledge, skills, and self-confidence in managing the third stage of labor. Sixty midwifery students were randomly allocated to experimental (n = 30) and control (n = 30) groups. Following the intervention, all students met or surpassed the minimum passing standard (MPS), achieving at least 90% in skills (Z=-4.791; p<.001; r~0.87), 80% in knowledge (Z=-4.814; p<.001, r~0.87 ), and an increased score in self-confidence (Z=-4.792; p<.001; r~0.87 ). These improvements were maintained after the clinical experience. The performance of students trained through the traditional approach was significantly lower than that of those trained with SBML, and none of them achieved the MPS. This study highlights the need to structure nursing and midwifery training programs according to the Theory-SBML-Clinical placement model to strengthen students' competencies. La réalisation de la couverture universelle des soins de santé maternelle d’ici 2030 passe par un renforcement substantiel de la profession de sage-femme. Pour assurer des soins accessibles, culturellement adaptés et de qualité optimale, il est essentiel que les sages-femmes bénéficient d’une formation conforme aux normes internationales. Cette étude avait pour objectif d’évaluer l’impact de 20 heures d’apprentissage par simulation fondé sur la pédagogie de la maîtrise, la pratique délibérée, et l’Examen Clinique Objectif Structuré (ECOS) sur les connaissances, les compétences et la confiance en soi des étudiantes sages-femmes dans la prise en charge de la troisième phase de l’accouchement. Un total de 60 étudiantes sages-femmes ont été réparties de façon aléatoire en un groupe expérimental (n = 30) et un groupe témoin (n = 30). À la suite de l’intervention, toutes les étudiantes ont atteint ou dépassé la norme minimale de réussite (MPS), obtenant au moins 90 % en compétences (Z=-4.791; p<.001 ; r~0.87), 80% en connaissances (Z=-4.814; p<.001 ; r~0.87), ainsi qu’une amélioration de leur score de confiance en soi (Z=-4.792; p<.001 ; r~0.87). Ces progrès ont été conservés après l’expérience clinique. Les performances des étudiantes formées selon l’approche traditionnelle étaient significativement inférieures, et aucune d’entre elles n’a atteint le Seuil Minimal de Réussite (SMR). L’apprentissage par maîtrise, la pratique délibérée et l’ECOS apparaissent comme des éléments essentiels au développement d’un programme de formation par simulation de haute qualité, favorisant un transfert efficace des acquis vers la pratique clinique.
15 Apr 2026
Read appraisal →BMJ open
Challenging history taking encounters: a systematic review, meta-analysis and phenomenological framework
OBJECTIVES: All physicians will experience challenging history taking encounters, where communication is impaired and negatively impacts the diagnostic process. The aims of this systematic review were to (1) undertake a meta-analysis of the frequency of challenging encounters; (2) collate adverse outcomes of challenging encounters; (3) identify underlying causes of challenging encounters; (4) identify strategies to deal with different challenges; and (5) align these strategies with our published phenomenological framework of history taking challenges. DESIGN: This was a systematic review and meta-analysis of prevalence data adhering to the Preferred Reporting Items for Systematic reviews and Meta-Analyses and the Meta-analyses of Observational Studies in Epidemiology guidelines. DATA SOURCES: A literature search in MEDLINE, Embase and Cochrane databases was performed on 12 July 2020, and updated on 4 August 2025, focusing on challenging history taking encounters in any clinical setting. ELIGIBILITY CRITERIA: Articles reporting on the frequency, adverse outcomes, causative factors or strategies used to address challenges in the history taking process in any clinical area of medicine. DATA EXTRACTION AND SYNTHESIS: Factors associated with challenging history encounters (causative or consequential) were categorised using inductive coding and referenced to a phenomenological framework. Meta-analysis was used to estimate the prevalence of history taking encounters using a restricted maximum likelihood model with τ 2 and I 2 as tests for heterogeneity and funnel plot with Egger's test for publication bias. RESULTS: 73 articles were included in the analysis. The overall prevalence of challenging history taking encounters was 19.5% (95% CI 14.2% to 24.7%). Adverse outcomes of patient dissatisfaction (level 1 evidence) and diagnostic uncertainty (level 3 evidence) were identified. Factors associated with (n=22) and strategies to mitigate challenging encounters (n=13) were categorised. Correlation of factors and strategies with a phenomenological approach created a framework to assist novice history takers in approaching such circumstances. CONCLUSIONS: Challenging history taking encounters are common. Little is known of the relative importance of factors associated with challenging history taking encounters or the impact of suggested strategies. Many of the suggested strategies to facilitate meaningful communication in these situations involve a departure from standard history taking. More research is required to better define the nature of challenges encountered in history taking with a view to develop better educational models for trainee physicians.
15 Apr 2026
Read appraisal →JMIR medical education
Developing and Validating a Coding Scheme for Clinical Reasoning in History Taking Using Generative AI-Based Virtual Patients: Systematic Text Condensation Approach
BACKGROUND: Effective history taking helps clinicians identify key symptoms and form accurate hypotheses. Generative artificial intelligence (GenAI)-based virtual patients (VPs) are increasingly used to simulate and practice history taking. However, there is currently no straightforward approach to effectively identify students' clinical reasoning activities during these interactions, which limits the ability to provide instructional feedback. OBJECTIVE: This study aims to develop and validate a coding scheme to identify medical students' history-taking behaviors during interactions with GenAI-based VPs. METHODS: Second-year medical students (N=210) participated in 5 history-taking cases with GenAI-based VPs, yielding 1030 dialogues. Researchers applied the systematic text condensation method to these dialogue data from cases 1 to 4 to inductively develop a coding scheme and validate coding consistency. Subsequently, the dialogue data from case 5 were used to assess the correlation between the students' history-taking behaviors and their academic performance, including diagnostic accuracy, history-taking checklist scores, clinical knowledge test scores, and postencounter form scores. RESULTS: A coding scheme comprising 12 behaviors across 3 dimensions-clinical reasoning behaviors, information gathering behaviors, and social interaction behaviors-was developed with high interrater reliability (κ≥0.85). The correlation analysis revealed that key clinical reasoning behaviors, such as summarizing and integrating and logical organization, showed significant positive correlations with multiple performance metrics, underscoring their importance in fostering clinical competence. In contrast, information gathering behaviors such as specifying symptoms and routine question were associated with clinical knowledge and thoroughness of history taking but were less predictive of diagnostic accuracy. CONCLUSIONS: This study developed a reliable, theory-informed coding scheme that can identify students' questioning behaviors during history taking with GenAI-based VPs. The scheme effectively captures higher-order cognitive strategies and provides valuable insights into the development of clinical reasoning in medical students. This approach offers a scalable and efficient way to integrate real-time feedback into future medical education, fostering personalized learning and advancing competency-based assessments in clinical training.
14 Apr 2026
Read appraisal →Annals of plastic surgery
Evaluating GPT-4 Performance on Plastic Surgery Oral Examination Vignettes: A Quantitative and Qualitative Analysis
BACKGROUND: The use of artificial intelligence (AI) in medicine is rapidly evolving. However, its role in plastic and reconstructive surgery remains underexplored. Plastic surgery requires nuanced, dynamic decision making, and individualized care, making AI integration challenging. This study evaluates GPT-4's ability to respond to American Board of Plastic Surgery (ABPS) Oral Board-style clinical vignettes and assesses its potential as a decision making and educational adjunct. METHODS: Twelve clinical vignettes spanning aesthetic, reconstructive, hand, craniofacial, pediatric, and trauma surgery were input into GPT-4. Each response was scored by 2 board-certified plastic surgeons across 6 clinical domains: Case Introduction, Diagnosis, Treatment Planning, Patient Counseling, Operative Steps, and Complication Management. Domains were scored on a 0-4 scale; scores <2 were considered failing. Interrater reliability was assessed via weighted κ . A structured qualitative interview was conducted. RESULTS: GPT-4 achieved mean domain scores ranging from 2.3 to 3.7 across vignettes, with passing rates of 91.7% (rater 1) and 83.3% (rater 2). The highest-performing domains were Diagnosis (84.4%) and Complication Handling (82.3%), and the lowest-performing domains were seen in Case Introductions (62.5%). Interrater agreement was strong across domains ( κ = 0.70-0.89). Qualitative findings emphasized GPT-4's accuracy in guideline-based cases, limitations in trauma triage, and potential as an educational resource. CONCLUSION: GPT-4 demonstrates concordance with board-level clinical reasoning in structured plastic surgery scenarios. However, limitations in heuristic judgment and real-time adaptability underscore the need for optimization with specialty-specific training datasets and performance rubrics. With appropriate curation, GPT-4 could serve as a valuable supplement in surgical education and oral board preparation.
13 Apr 2026
Read appraisal →Games for health journal
The Effect of Emergency Escape Room Simulation on Knowledge, Anxiety, and Satisfaction Levels of Students: A Randomized Controlled Trial
BACKGROUND: The aim of this study is to determine the effect of escape room simulation intervention on the knowledge, anxiety, and satisfaction levels of students in emergency nursing education. METHODS: This randomized controlled study was conducted with 40 students studying at the nursing faculty of a university in Istanbul. The students in the intervention group (n = 20) were given an escape room simulation intervention related to emergency nursing education. The students in the control group (n = 20) were not given any intervention other than the traditional education method. Data were collected using the Knowledge Test, State Anxiety Scale, and Visual Analog Scale for satisfaction. RESULTS: The knowledge level of the students in the intervention group measured immediately after the education (P = 0.003), 1 week after the education (P < 0.001), and 1 month after the education (P < 0.001) was found to be significantly higher than that of the control group. While no significant difference was found in anxiety levels before and after the education between the groups, a significant difference was found in anxiety levels before and after the training in the intervention group (P < 0.001). The satisfaction level measured immediately after the education was found to be significantly higher in the intervention group than in the control group (P < 0.001). CONCLUSION: This study show that escape room simulation increased emergency nursing knowledge and satisfaction and reduced anxiety levels of the students. It is recommended that escape room simulation intervention be used in more studies in nursing education. The study was registered on ClinicalTrials.gov.tr with the number NCT06619119.
11 Apr 2026
Read appraisal →Journal of medical Internet research
The Alberta Quality Assessment Tool: Risk of Bias (AQAT:RoB) for the Evaluation of Medical Large Language Model Question-Answer Studies: Development and Pilot Validation
BACKGROUND: Despite the transformative potential of large language models (LLMs) in health care, the rapid development of these tools has outpaced their rigorous evaluation. While artificial intelligence-specific reporting guidelines have been developed to address standardized reporting of artificial intelligence studies, there is currently no specific tool available for risk of bias assessment of LLM question-answer (QA) studies. Existing risk-of-bias tools for medical research are not well suited to the unique challenges of evaluating LLM-QA studies, which creates a critical gap in assessing their safety and effectiveness. OBJECTIVE: This study aims to develop the Alberta Quality Assessment Tool: Risk of Bias (AQAT:RoB) for LLM-QA studies to systematically evaluate the validity and risk of bias in LLM-QA studies. METHODS: We conducted 2 literature reviews. The first was on quality assessment tools for LLM-QA studies, and the second was on LLM-QA studies, which informed the first draft of the AQAT:RoB. The draft AQAT:ROB was further refined through a prespecified iterative process of modified Delphi, consensus meeting, and validation. The first Delphi process occurred between May 1 and May 20, 2025, and the first consensus meeting was held on May 22. The first round of validation was completed by 4 evaluators, who were not part of the consensus meeting, on 16 randomly selected studies. As this first round of validation surpassed our a priori threshold of ≥80% agreement and a Cohen κ of ≥0.61 between evaluators, no further rounds of development and validation were undertaken. A second Delphi process occurred between February 20 and February 23, 2026, to vote on postpilot changes in response to peer review. RESULTS: The AQAT:RoB consists of 5 high-level domains (Questions, Reference Answers, LLM Answers, Evaluators, Outcomes). These domains are subdivided into 9 subdomains. Each subdomain includes at least one "Support for Judgment" and at least one "Type of Bias" and is to be rated "low," "high," or "unclear" for risk of bias. A pilot evaluation was completed by internal validators who were not part of the consensus discussion and were asked to complete the AQAT:RoB form for each assigned study. Each of the 16 studies was evaluated by 2 evaluators independently. Pilot validation showed a percent agreement of 86.1% and a Cohen κ of 0.70 between assessors. CONCLUSIONS: The AQAT:RoB demonstrates promising initial reliability for assessing the validity or risk of bias in LLM-QA studies. The tool will benefit from future refinements, external validation, and periodic updates to keep pace with evolving technology.
10 Apr 2026
Read appraisal →PloS one
Comparative analysis of text readability and writing styles in AI-generated vs. Human-written academic abstracts
Research article abstracts are vital in scientific publications for readers to assess a study's significance. The increasing use of AI tools, such as Kimi, ChatGPT and DeepSeek, to generate abstracts raises concerns about their readability and writing styles compared to human-written ones. The study aims to compare the differences in text readability and writing styles between human-written against AI-generated abstracts. A total of 150 abstracts of high-impact journal articles in the field of linguistics and computer science, 75 from each discipline, and another 150 AI-generated abstracts from the same corpus of articles served as the source texts for analysis. The Readability Scoring System, a computational tool, yielded readability and writing style metrics, while expert evaluation was performed to assess the quality of AI-generated academic abstracts. The quantitative data generated were analysed using SPSS 27 with non-parametric statistical methods. Key findings revealed: (1) AI-generated abstracts exhibited significantly lower readability across eight metrics, indicating greater complexity and lower readability; (2) Discipline-specific analysis showed five differing metrics in linguistics and eight in computer science; (3) Interdisciplinary comparisons revealed non-significant differences across nine readability metrics, highlighting AI's potential to mimic natural writing. However, it still faces challenges in generating lexically diverse content. These results underscored the current limitations of AI in generating readable and human-like abstracts, especially in technical fields.
10 Apr 2026
Read appraisal →JMIR medical informatics
Exploring the Role of AI in Managing Treatment Recommendations for Lymphedema: International, Multidisciplinary, Multiprofessional Survey Study of Trust, Reliability, and Impact on Decision-Making
BACKGROUND: Upper and lower extremity lymphedema is a chronic, progressive condition that significantly impairs the quality of life of affected patients. Despite the recently established effectiveness of physical therapy and supermicrosurgical interventions, current guidelines frequently lag behind emerging evidence and commonly do not offer stage-specific treatment algorithms. This gap in evidence-based guidance may prompt clinicians with limited experience to seek support from large language models such as ChatGPT. OBJECTIVE: Given the potential of artificial intelligence to rapidly integrate emerging research, this study evaluated how clinicians from different professional backgrounds rate the quality and reliability of personalized lymphedema management recommendations generated by ChatGPT. METHODS: In this exploratory cross-sectional study, ChatGPT generated treatment recommendations for 6 standardized lymphedema case scenarios. An international panel of 67 participants (resident doctors, board-certified specialists, physiotherapists, and advanced practice nurses) from 34 institutions across 11 countries assessed the recommendations using a modified DISCERN questionnaire with a 9-point agreement scale ranging from 1 (completely disagree) to 9 (completely agree). Ratings were summarized as pooled means with variability measures and compared across clinician groups (residents vs board-certified physicians vs physiotherapists or advanced practice nurses) using group comparison testing. RESULTS: ChatGPT was rated most favorably for diagnostic accuracy and treatment relevance, with higher ratings among residents than board-certified physicians. Residents assigned significantly lower scores for source indication, source currency, and communication of uncertainty. Between-group differences were observed across multiple DISCERN items, consistent with systematically more critical appraisal by experienced specialists. Participants reported moderate to high trust and willingness to consider ChatGPT as a supplementary resource, with more favorable perceptions among younger respondents. CONCLUSIONS: Clinicians perceived ChatGPT as potentially useful for preliminary orientation and educational support in lymphedema management, especially for less experienced users. Despite not being blinded, lower ratings in evidence transparency and uncertainty communication, particularly among experienced specialists, suggest that current artificial intelligence outputs should not be used as stand-alone guidance. Future work should test clinically integrated, citation-grounded workflows in prospective settings and evaluate whether they improve decision quality and efficiency.
9 Apr 2026
Read appraisal →JMIR formative research
Performance of DeepSeek V3, DeepSeek R1, ChatGPT 4o, and ChatGPT o1 on the National Health Professional and Technical Qualification Examination (Intermediate Level) in China: Comparative Analysis
BACKGROUND: In recent years, large language models (LLMs) have undergone swift cycles of refinement and iteration. However, in the realm of clinical medicine, different LLMs' capability of logical reasoning and disease diagnosis needs further investigation. OBJECTIVE: The aim of our study was to evaluate the performance of 4 different LLMs in the National Health Professional and Technical Qualification Examination in China. METHODS: A total of 398 multiple-choice questions of 5 different question types were integrated within the examination with respect to the diagnosis or care of cases. These questions were categorized into different cardiology subspecialties and different clinical disciplines. DeepSeek V3 and R1 were accessed through an application programming interface, while ChatGPT 4o and o1 were queried via its public chat-based interface. We offered the same prompts instructing LLMs to assume the role of a physician and provide answers with explanations at the beginning of each conversation. We assessed different LLMs' performance by the accuracy in the responses to the multiple-choice questions. For the first 3 examination sections, McNemar test was used to compare the accuracy among the models, with post hoc pairwise comparisons performed using partitions of chi-square method and Bonferroni correction (significance set at P<.008). For the fourth section involving partially credit scoring, one-way ANOVA was performed to compare the mean scores among the models, with statistical significance set at P<.05. RESULTS: Both DeepSeek V3 and R1 showed superior performance in the first 3 sections of the Chinese National Health Professional and Technical Qualification Examination, achieving an overall performance of 93% and 93.6%, respectively. ChatGPT 4o and o1 achieved accuracies of 73.3% and 69%, respectively (all P<.001 compared with DeepSeek V3). For the fourth section, the performance of all 4 LLMs markedly declined compared to their results in the preceding sections. Particularly, in the section of gastroenterology and hematology, DeepSeek V3 achieved the highest accuracy, while R1 ranked first in cardiology and neurology. ChatGPT o1 achieved the highest accuracy in the topic of coronary artery disease, with no statistical significance. CONCLUSIONS: DeepSeek V3 and R1 showed remarkable potential in facilitating clinical decision-making in the Chinese professional examination, with both outperforming ChatGPT 4o and o1. Nonetheless, future research should continue evaluating their economic efficiency and susceptibility to hallucination.
7 Apr 2026
Read appraisal →Prehospital and disaster medicine
Effectiveness of Video Call-Assisted Versus Voice Call-Assisted Dispatcher-Guided CPR in Untrained Laypersons: A Randomized Simulation Study
INTRODUCTION: Out-of-hospital cardiac arrest (OHCA) remains a major cause of mortality world-wide. Early bystander cardiopulmonary resuscitation (CPR) is a critical determinant of survival; however, many witnessed arrests are managed by untrained laypersons. Dispatcher-assisted CPR (DA-CPR) increases bystander intervention rates, but telephone-based guidance limits real-time assessment of compression quality. Video-assisted CPR (V-CPR) may overcome these limitations by enabling visual feedback and demonstration-based guidance. STUDY OBJECTIVE: The aim of this study was to evaluate whether video call-assisted dispatcher guidance incorporating simultaneous real-time demonstration improves CPR performance quality compared with voice call-assisted guidance in untrained laypersons during a simulated adult OHCA scenario. METHODS: This prospective, randomized, single-blind, manikin-based trial included 85 university students without prior CPR training. Participants were randomized to telephone-assisted CPR (T-CPR; n = 40) or video-assisted CPR (V-CPR; n = 45). All participants performed standardized hands-only CPR for five minutes following dispatcher instructions. In the V-CPR group, the dispatcher simultaneously demonstrated CPR on a manikin during the video call. The primary outcome was the composite CPR Quality Score generated by the manikin feedback system. Secondary exploratory outcomes included compression depth, compression rate, interruption time, and Emergency Medical Services (EMS)-related time intervals. Robust regression analysis adjusted for age, sex, dominant hand, height, and weight was performed. RESULTS: The mean age of participants was 20.13 (SD = 1.81) years, and 54.1% were female. The CPR Quality Score was significantly higher in the V-CPR group than in the T-CPR group (median difference -47; 95% CI, -60 to -36; P < .001). The V-CPR group demonstrated greater mean compression depth, higher proportions of compressions within recommended rate and depth ranges, and shorter interruption times between compressions. The T-CPR group showed shorter time from case recognition to EMS call, while the interval from dispatcher contact to CPR initiation was similar between groups. In multivariable robust regression analysis, allocation to the V-CPR group remained independently associated with higher CPR Quality Score and improved compression performance metrics. CONCLUSION: Video call-assisted dispatcher guidance incorporating simultaneous real-time visual demonstration significantly improves CPR quality in untrained lay rescuers compared with voice-only guidance. These findings suggest that structured visual modeling integrated into DA-CPR systems may enhance bystander resuscitation performance and help bridge gaps in community CPR training.
7 Apr 2026
Read appraisal →Archives of gynecology and obstetrics
Comparative validation of a cost-effective in-house 3D-printed LLETZ simulator versus a commercial training model.
PURPOSE: Traditional surgical training methods such as "learning-by-doing" raise ethical and methodological concerns. To improve training and reduce patient risk, a 3D-printed LLETZ simulator was developed. While initial studies showed advantages over a conventional model, they were limited to medical students and lacked comparison with a commercially available simulator. METHODS: A single-center study was conducted at the University Hospital Wuerzburg. 60 medical students without prior LLETZ experience and 10 gynecology residents with prior exposure were randomly assigned to train on either a commercial or the novel in-house simulator. Each participant performed five electrosurgical excisions. Performance was evaluated using LEEP scores, resection status (R0 resections), and blinded video assessments by two senior clinicians. Additionally, participants completed questionnaires, to capture subjective training impressions. RESULTS: The in-house simulator demonstrated superior performance compared to the commercial model. When analyzed separately, changes in LEEP scores over the five attempts were statistically significant for both simulators. The effect size was larger for the in-house simulator (η2 = 0.227) than for the conventional simulator (η2 = 0.10). Within-group analysis revealed no significant pairwise differences across all attempts for the commercial simulator. In contrast, several pairwise comparisons remained statistically significant for the in-house simulator (attempts 1 vs. 3, 1 vs. 4, 2 vs. 5, and 1 vs. 5), all with large effect sizes (Cohen's d > 1.1). Between-group comparison of individual LEEP scores showed a statistically significant difference in the fifth attempt (p = 0.002), with a large effect size (Cohen's d = 1.01) favoring the in-house simulator. Higher R0 resection rates were observed with the in-house simulator in the third (100% vs. 83.3%) and fourth attempts (96.7% vs. 73.3%). Blinded video assessments by two senior experts confirmed these findings, demonstrating higher checklist, Global Rating Scale (GRS), and overall mean scores for the in-house simulator from the third attempt onward (all p < 0.05; all Cohen's d > 0.8). Participant feedback further supported these results, indicating improved confidence, technical skills, and perceived educational value. CONCLUSION: This study demonstrated that the novel in-house 3D-printed simulator significantly outperformed the commercial model in objective surgical performance, learning progression and user satisfaction.
5 Apr 2026
Read appraisal →Annals of medicine
Immersive virtual reality-assisted anatomy training improves endotracheal intubation performance in simulation: a randomized controlled trial among Chinese non-anesthesiology residents
INTRODUCTION: This study aimed to compare immersive virtual reality (IVR)-assisted versus conventional anatomy training for teaching endotracheal intubation (ETI) to novice non-anesthesiology residents enrolled in China's Standardized Residency Training program. METHODS: A total of 90 non-anesthesiology residents without prior ETI experience were randomly assigned to either an IVR group receiving IVR-assisted anatomy training (n = 45) or a control group receiving conventional anatomy training (n = 45). All participants underwent a standardized teaching protocol. The primary endpoint was residents' ETI performance on a simulator, assessed using both the Global Rating Scale (GRS) and a task-specific checklist. The secondary endpoints included changes in written multiple-choice question (MCQ) scores and residents' evaluations of the course. RESULTS: In practical ETI assessments on a manikin, the IVR group achieved significantly higher scores on the task-specific checklist than the control group (90.34 ± 2.89 vs. 87.20 ± 3.29; p < 0.001), whereas GRS scores were comparable between groups. Both groups showed significant post-training improvement in knowledge scores (p < 0.001), with the IVR group showing a greater gain in theoretical knowledge (54.0% vs. 36.3%; p < 0.001). Participants in the IVR group also expressed a stronger preference for their training method (80.8%) and reported higher levels of motivation, confidence, and enjoyment (all p < 0.05). CONCLUSION: IVR-assisted anatomy training enhances the effectiveness of ETI training for novice non-anesthesiology residents, offering an interactive, engaging, and reproducible approach within China's Standardized Residency Training framework.
5 Apr 2026
Read appraisal →Medical education online
AI-assisted learning: ChatGPT for anamnesis in women's health education
UNLABELLED: Artificial intelligence (AI) tools such as ChatGPT are rapidly being adopted in medical education, yet evidence regarding their impact on learners' history-taking (anamnesis) skills remains limited. This gap is particularly relevant in women's health education, where high-quality anamnesis is essential for addressing sensitive, context-dependent concerns and for ensuring the safety of two interrelated patients: mother and fetus. METHODS: This study comprised two phases. First, semi-structured virtual interviews were administered to students and faculty to assess their familiarity with ChatGPT and access to digital technologies. Second, an in-person classroom intervention was implemented within the Women's Health discipline, integrating ChatGPT into history-taking instruction. Students' anamnesis performance was evaluated before and after ChatGPT-assisted learning. Additionally, a novel instructional activity was introduced in which ChatGPT generated cases classified as plausible, intermediate, or physiologically impossible, serving as prompts for guided discussion focused on diagnostic pitfalls, critical appraisal, and clinical reasoning. RESULTS: In the virtual phase, faculty (n = 62) and students (n = 115) completed the questionnaires. The classroom intervention involved 40 medical students participating as part of routine Women's Health teaching activities, with faculty oversight to ensure pedagogical alignment and responsible AI use. A pronounced discrepancy emerged between students' familiarity with ChatGPT (99.1%) and lower levels of familiarity among faculty. Anamnesis performance improved significantly after ChatGPT-assisted learning (p < 0.0001). Students reported increased confidence and perceived enhancement of history-taking quality, and all participants viewed ChatGPT as a valuable educational resource. The AI-generated cases effectively stimulated discussion and reinforced clinical reasoning processes. Findings contributed to the development of a practical guideline for the responsible integration of ChatGPT into Women's Health education. CONCLUSIONS: ChatGPT can enhance anamnesis and promote critical reasoning through structured interaction with AI-generated cases. However, its effective and responsible use depends on targeted faculty development to ensure alignment with pedagogical goals, appropriate oversight, and consistent integration into curriculum.
5 Apr 2026
Read appraisal →Scientific reports
Potential of large language models for rapid clinical information support: evidence from acute kidney injury knowledge testing.
Large language models (LLMs) are increasingly applied in clinical contexts; however, to our knowledge, their performance in acute kidney injury (AKI) has not been directly compared with physician performance on standardized clinical knowledge assessments. We conducted a cross-sectional study to evaluate the performance of 13 publicly available LLMs and 123 volunteer participants at the 131st Annual Congress of the German Society of Internal Medicine in Wiesbaden, Germany. Both groups completed an identical AKI knowledge assessment consisting of two case vignettes and 15 single-best-answer multiple-choice questions. LLMs achieved a mean score of 13.5 out of 15 (90%), with several models reaching a perfect score, while human participants averaged 7.3 out of 15 (48.7%). Only 16.3% of participants scored 11 points or higher. As an illustrative example, ChatGPT-4o completed the test in approximately 0.5 minutes, whereas humans required a mean of 7.3 minutes. These findings demonstrate that LLMs substantially outperformed a heterogeneous group of medical professionals in AKI knowledge assessments and did so with markedly greater efficiency. While this highlights the potential of LLMs as rapid, cost-effective tools for clinical knowledge support, their role in real-world patient care remains undetermined, and human clinical judgment remains essential to ensure safe, context-sensitive, and patient-centered care.
5 Apr 2026
Read appraisal →European journal of pediatrics
Facilitator-guided vs self-guided debriefing in immersive virtual reality paediatric emergency training: a randomised pilot study on learning outcomes and feasibility
UNLABELLED: This study evaluated the feasibility and effectiveness of immersive virtual reality (VR)-based paediatric emergency training, comparing facilitator-guided with self-guided debriefing methods. In a single-blinded, randomised controlled pilot trial, 24 healthcare professionals (12 interprofessional dyads) were randomised to VR-based paediatric emergency training followed by either facilitator- or self-guided debriefing. Both groups received a standardised preparatory lecture and skills workshop. We collected data on the feasibility of the interventions and additional trial procedures. For pre- and post-performance assessment, all dyads were video-recorded whilst managing a mannequin-based paediatric emergency. Two independent, blinded raters assessed the dyads' teamwork, ABCDE adherence, and time to critical actions based on the videos. We also collected data on participants' cognitive load and perceived effectiveness of the two debriefing methods. The study demonstrated the feasibility of interprofessional VR-based paediatric emergency training with both facilitator- and self-guided debriefing in a clinical setting. Twenty-two healthcare professionals completed the intervention, and 20 completed follow-up. VR was acceptable and usable, though 46% of participants reported some cybersickness. Additional trial procedures were feasible but required substantial logistical coordination. VR training significantly improved teamwork (facilitator-guided mean 1.2, confidence interval (CI) 0.5 to 1.9, p = 0.005; self-guided mean 1.4, CI 0.8 to 2.0, p < 0.001) and ABCDE adherence (facilitator-guided mean 0.5, CI 0.1 to 1.0, p = 0.02; self-guided mean 0.5, CI 0.1 to 0.9, p = 0.01), with similar outcomes between the debriefing methods. However, participants perceived the facilitator-guided debriefing to be more effective (mean difference 1.4, CI 0.1 to 2.7, p = 0.04). CONCLUSION: Immersive VR-based paediatric emergency training with facilitator-guided and self-guided debriefing was feasible in a pilot context and yielded comparable performance outcomes. A larger, adequately powered trial is warranted to formally evaluate non-inferiority between debriefing methods. WHAT IS KNOWN: • Simulation-based paediatric emergency training improves clinical outcomes, but widespread implementation is limited by logistical challenges and high costs. • Immersive virtual reality (VR) may help overcome these barriers, yet evidence on its feasibility and effectiveness in this context is limited. WHAT IS NEW: • VR-based paediatric emergency training is feasible and effectively improves interprofessional performance. • Self-guided and facilitator-guided debriefing yielded comparable outcomes, highlighting the potential for scalable use.
5 Apr 2026
Read appraisal →Journal of medical Internet research
Artificial Intelligence in Health Professions Education: Qualitative Study of Student Experiences
BACKGROUND: Artificial intelligence (AI) is increasingly integrated into education and health care, raising questions about how students use these technologies and how AI influences their learning. In health education, understanding these trends is particularly important because student learning directly impacts future clinical skills. OBJECTIVE: This study aimed to explore the use of AI tools by health sciences students at the University of Ottawa. More specifically, it sought to identify the most frequently used AI tools, describe students' usage habits, determine which tools support knowledge acquisition and skill development, and gather students' recommendations for effective strategies to raise awareness and train their peers on the responsible use of AI. METHODS: A qualitative approach was used with students from 10 health professions who reported using AI in their studies. Data were collected through semistructured interviews and an open-ended qualitative online survey. Inductive thematic analysis within an interpretive paradigm was applied to capture patterns, perceptions, and emergent themes. RESULTS: A total of 51 health professions students participated in the study. Most were women between the ages of 20 and 29 years. ChatGPT (OpenAI) emerged as the most frequently used AI tool. Students perceived AI as a complementary tool that facilitated knowledge acquisition, skill development, writing, and problem-solving. AI adoption was driven by curiosity, peer influence, and the desire to improve work efficiency. Students critically evaluated AI results, integrated the tools into their learning processes, and emphasized the importance of technical skills, critical thinking, and digital literacy. Peer learning, hands-on demonstrations, and access to online resources were recommended for effective AI training. CONCLUSIONS: This research demonstrates that health professions students actively use AI tools, particularly ChatGPT, to support learning, skill development, and academic tasks. Although AI is valuable as an educational aid and its use varies by student and context, this highlights the need for structured guidance, critical evaluation skills, and peer-supported training. These findings highlight the importance of thoughtfully integrating AI into educational programs to enhance learning outcomes, foster skill acquisition, and ensure responsible and effective adoption.
4 Apr 2026
Read appraisal →Journal of biomedical informatics
Natural language generation in healthcare: A review of methods and applications
OBJECTIVE: This study presents a systematic review of natural language generation (NLG) methods and applications in the medical domain, providing quantitative and qualitative analyses to answer four key research questions regarding methods, evaluation, applications, and challenges of NLG in healthcare. METHODS: We searched PubMed, ACM Digital Library, Web of Science, Science Direct, Scopus, Embase, and ACL Anthology for NLG-related studies in healthcare from 2018 to 2024. Out of 3,988 research articles, 113 met the inclusion criteria and were analyzed across data modality, model architecture, evaluation metrics, and application domain. RESULTS AND CONCLUSION: NLG in healthcare has grown substantially, with annual publications increasing from 2 in 2018 to 40 in 2024. Of the 113 included studies, text-to-text generation was the most common data modality (65.5%), followed by image-to-text (19.5%) and multimodal-to-text (15.0%). Transformer-based architectures were dominant, especially encoder-decoder models (61.6%). Automatic evaluation metrics such as ROUGE (81.4%) and BLEU (57.5%) were widely used. Human evaluation metrics, such as Likert scales (31.9%), were increasingly adopted. The four most prevalent application domains include summarization (e.g., discharge summaries, radiology reports), clinical documentation, medical dialogue, and data augmentation. The transformer-based large language models (LLMs) and the accumulation of large-scale multimodal clinical datasets have remarkably advanced NLG in healthcare. However, challenges remain in factual consistency, explainability, evaluation robustness, and AI safety. Addressing these challenges is essential for the adoption of NLG in various healthcare applications.
4 Apr 2026
Read appraisal →Clinical nutrition ESPEN
Artificial intelligence in clinical nutrition. A narrative review.
The rapid integration of Artificial Intelligence (AI) into healthcare, particularly clinical nutrition, holds transformative potential for enhanced diagnostics, risk prediction, and personalized therapeutic support. However, many clinicians lack sufficient understanding of AI principles, capabilities, and limitations, which may hinder adoption, lead to inappropriate use, or result in missed opportunities to enhance patient care. This narrative review aims to provide an accessible overview of foundational AI concepts, such as machine learning, deep learning, and large language models, and their practical applications in clinical nutrition. While AI offers immense promise in advancing nutritional care, its successful implementation requires clinicians to be adequately prepared to engage with these technologies. Education programs tailored to healthcare professionals, interdisciplinary collaboration between AI experts and clinicians, and robust ethical oversight are critical to ensure responsible and effective integration. By equipping clinicians with the necessary knowledge and tools, AI can serve as a powerful ally in delivering personalized and patient-centered nutritional care while maintaining human expertise at the forefront of decision-making.
2 Apr 2026
Read appraisal →Am J Perinatol
Application of Generative AI to Enhance Obstetrics and Gynecology Research
The rapid evolution of large-language models such as ChatGPT, Claude, and Gemini is reshaping the methodological landscape of obstetrics and gynecology (OBGYN) research. This narrative review provides a comprehensive account of generative AI capabilities, key use cases, and recommended safeguards for investigators. First, generative AI expedites hypothesis generation, enabling researchers to interrogate vast corpora and surface plausible, overlooked questions. Second, it streamlines systematic reviews by composing optimized search strings, screening titles and abstracts, and identifying full-text discrepancies. Third, AI assistants can draft reproducible analytic code, perform preliminary descriptive or inferential analyses, and create publication-ready tables and figures. Fourth, the models support scholarly writing by suggesting journal-specific headings, refining prose, harmonizing references, and translating technical content for multidisciplinary audiences. Fifth, they augment peer-review and editorial workflows by delivering evidence-focused critiques. In educational settings, these models can create adaptive curricula and interactive simulations for trainees, fostering digital literacy and evidence-based practice early in professional development among clinicians. Integration into clinical decision-support pipelines is also foreseeable, warranting proactive governance. Notwithstanding these opportunities, responsible use demands vigilant oversight. Large-language models occasionally fabricate citations or misinterpret domain-specific data ("hallucinations"), potentially propagating misinformation. Outputs are highly prompt-dependent, creating a reliance on informed prompt engineering that may disadvantage less technical clinicians. Moreover, uploading protected health information or copyrighted text raises privacy, security, and intellectual property concerns. We outline best-practice recommendations: maintain human verification of all AI-generated content; cross-validate references with primary databases; employ privacy-preserving, on-premises deployments for sensitive data; document prompts for reproducibility; and disclose AI involvement transparently. In summary, generative AI offers a powerful adjunct for OBGYN scientists by accelerating topic formulation, evidence synthesis, data analysis, manuscript preparation, and peer review. When coupled with rigorous oversight and ethical safeguards, these tools can enhance productivity without compromising scientific integrity. Future studies should quantify accuracy, bias, and downstream patient impact. · Generative AI supports various research stages in OBGYN, such as hypothesis generation, systematic review assistance, data analysis, and scientific writing, demonstrating its potential to streamline research workflows and improve research efficiency.. · Generative AI has notable limitations, including the risk of generating inaccurate references ("hallucinations") and the need for careful supervision.. · Effective usage requires skill in prompt engineering, posing a challenge for those without technical expertise.. · Utilizing generative AI in sensitive fields like OBGYN raises privacy, security, and ethical concerns..
1 Dec 2025
Read appraisal →Am Surg
Enhancing Surgical Education Through Artificial Intelligence in the Era of Digital Surgery
Artificial Intelligence (AI) is transforming surgical education, playing a pivotal role in the era of digital surgery. This review, conducted from January 2023 to December 2024, examines the integration of AI into surgical training, focusing on its benefits and limitations. Thirteen studies were included, with emphasis on AI's impact in General Surgery training. Digital surgery leverages AI-powered tools such as virtual reality (VR) and augmented reality (AR) to create immersive, simulated environments where residents can practice surgical techniques safely and effectively. These platforms improve technical skills, hand-eye coordination, and error reduction, while personalized AI-driven feedback systems enhance learning and skill assessment. Digital surgery also bridges the gap between theoretical knowledge and clinical application, fostering innovative training methodologies. Despite challenges such as financial constraints and ethical concerns, AI within digital surgery emerges as a transformative force, redefining surgical education and equipping trainees with the expertise needed for modern health care.
1 Nov 2025
Read appraisal →J Surg Educ
Effect of Artificial Intelligence-Augmented Human Instruction on Feedback Frequency and Surgical Performance During Simulation Training
OBJECTIVE: To determine whether personalized feedback from a human instructor receiving artificial intelligence (AI) error data will result in reduced feedback frequency and improvement of surgical skill compared to AI instruction. As feedback was only provided following AI error detection, a reduced feedback frequency is associated with fewer errors in performance. We hypothesized that AI-augmented personalized instruction would result in reduced feedback frequency and improvement in technical skill. DESIGN: This cross-sectional cohort study was a follow-up of a randomized controlled trial, which utilized the NeuroVR, an immersive virtual reality neurosurgical simulator. Participants were stratified by year in medical school and block randomized to receive one of 3 educational interventions as they performed simulated procedures on the NeuroVR: AI tutor instruction, scripted human instruction, and AI-augmented personalized instruction. Performance was assessed by the feedback frequency and technical skill performance metrics. CLINICALTRIALS: gov ID: NCT06273579. SETTING: Neurosurgical Simulation and Artificial Intelligence Learning Centre, McGill University, Montreal, Canada. PARTICIPANTS: Volunteer sample of medical students from 4 Quebec universities in preparatory, first, or second year without prior use of the NeuroVR. Eighty-eight students participated in the study with 87 included in the final analysis; 1 was excluded due to technical issues. RESULTS: By the third repetition, the AI-augmented personalized instruction group received significantly fewer total instructions (incidence rate ratio [IRR], 1.50 [95% CI, 1.16-1.94] instructions; p < 0.001), and high aspirator force instructions (IRR, 1.71 [95% CI, 1.15-2.55] instructions; p = 0.002), compared to the second repetition. Compared to AI tutor instruction, AI-augmented personalized instruction resulted in a significantly lower rate of healthy tissue removal (p = 0.01), instrument tip separation distance (mean ratio, 1.25 [95% CI, 1.05-1.50] mm; p = 0.008), and aspirator force (mean ratio, 1.68 [95% CI, 1.23-2.31] N; p < 0.001). AI-augmented personalized instruction showed a significant improvement from baseline in all subsequent repetitions for all performance metrics. CONCLUSIONS: This cohort study demonstrated that AI-augmented personalized instruction resulted in less frequent feedback, indicating fewer errors in trainee performance, and an improvement in simulated surgical skills.
1 Nov 2025
Read appraisal →