Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 25 appraisals
JMIR formative research
Automated Machine Learning Frameworks for Radiomics: Comparative Evaluation Study
BACKGROUND: Automated machine learning (AutoML) frameworks can lower technical barriers for predictive and prognostic model development in radiomics by enabling researchers without programming expertise to build models. However, their effectiveness in addressing radiomics-specific challenges remains unclear. OBJECTIVE: This study aimed to evaluate the performance, efficiency, and accessibility of general-purpose and radiomics-specific AutoML frameworks on diverse radiomics classification tasks, thereby guiding researchers and highlighting development needs for radiomics. METHODS: A total of 10 public and private radiomics datasets with varied imaging modalities (computed tomography and magnetic resonance imaging), sizes, anatomies, and end points were used. Six general-purpose and 5 radiomics-specific frameworks were tested with predefined parameters using standardized cross-validation. Evaluation metrics included area under the receiver operating characteristic curve, runtime, and qualitative aspects related to software status, accessibility, and interpretability. RESULTS: Simplatab, a radiomics-specific tool with a no-code interface, achieved the best overall balance between performance and computational efficiency, recording the highest average test area under the receiver operating characteristic curve (mean 78.46%, SD 12.22%) with a moderate runtime (1.1 h). However, its performance was not statistically superior to the most intensive general-purpose solutions. Most radiomics-specific frameworks were excluded from the performance analysis due to obsolescence, extensive programming requirements, or computational inefficiency. Conversely, general-purpose frameworks demonstrated higher accessibility and ease of implementation. CONCLUSIONS: While no single framework demonstrated absolute predictive superiority, Simplatab provides an effective balance of performance, efficiency, and accessibility for radiomics classification problems. However, continued efforts are needed to further mature AutoML solutions in the radiomics domain.
14 June 2026
Read appraisal →Critical care (London, England)
Large language models for optimizing clinical trial recruitment in ICUs: application to ventilator-induced diaphragm dysfunction
BACKGROUND: Ventilator-induced diaphragm dysfunction (VIDD) is a frequent and under-recognized consequence of prolonged mechanical ventilation in intensive-care unit (ICU) patients. Identifying eligible candidates for clinical trials targeting VIDD remains a major operational challenge. This study evaluates the use of large language models (LLMs) to automate patient prescreening from ICU discharge summaries and estimate recruitment capacity for a future phase 2 trial. METHODS: We developed an LLM-based prescreening pipeline to assess trial eligibility criteria from ICU discharge summaries, which was deployed to screen all 2024 ICU stays. Stays that were flagged as potentially eligible underwent expert adjudication. An enriched set of 50 ICU stays was independently annotated by six clinicians to define a reference standard, which was used to evaluate criterion-level model performances using F1-scores. RESULTS: The best-performing model was GPT-OSS:120B with a criterion-level F1-score of 0.82. When applied to consecutive 1,342 ICU stays from Montpellier University Hospital in 2024, the selected model identified 532 patients with ≥ 3 days of mechanical ventilation. After applying exclusion criteria, 185 patients remained potentially eligible. Expert review confirmed 133 patients as eligible, resulting in a positive predictive value of 72% (95% CI 65-78). The LLM-assisted workflow resulted in an estimated 86% reduction in clinician review time. The LLM-based prescreening pipelines achieved criterion-level F1 scores ranging from 0.73 to 0.82, with GPT-OSS:120B demonstrating the highest performance. CONCLUSIONS: LLM-based prescreening offers a promising approach for identifying trial candidates in critical care, prioritizing candidates for clinician review. Future deployments should include targeted expert validation and ongoing monitoring to ensure safety and generalizability.
13 June 2026
Read appraisal →Purinergic signalling
Turning failure into success: how artificial intelligence can help personalize therapies and re-use patient data.
Despite robust preclinical evidence, many clinical trials, including several that targeted the purinergic system, fail to demonstrate efficacy in humans. Failure may stem from inability to accurately identify patient subgroups responding similarly to treatments. Here, we explore the potential of artificial intelligence to revolutionize how we group and classify patients in clinical studies. We introduce a new framework using Large Language Models-generated embeddings of detailed patient data, to create a semantic-aware latent space, enabling us to identify truly meaningful patients' clusters. Large Language Models can provide explainable groupings, giving clear reasons why certain patients respond similarly to treatments. We present an example of successful application of this approach through the re-analysis of the AMARANTH clinical trial (NCT02245737, involving ~ 2200 patients and completed in 2018) testing Lanabecestat, a BACE1 inhibitor decreasing β-amyloid production in Alzheimer's disease, for which traditional analysis reported no efficacy. As in the original trial, our simulation showed no overall benefit. However, re-analysis per patients' clusters and subjects' re-stratification by semantic similarities (shared symptom profiles, progression patterns) identified a patients' subgroup in one of the clusters showing Lanabecestat-associated slower disease worsening, thus succeeding where the full trial had failed. By making a new therapy available to at least a subset of patients with a defined disease, this new approach may help maximize the return on drug development and reduce the burden on healthcare. Moreover, it will significantly improve the precision, efficiency and interpretability of clinical trials, paving the way for a new era of personalized medical treatments.
31 May 2026
Read appraisal →JMIR medical informatics
Blockchain Smart Contracts for Automating Clinical Trials: Systematic Review and Proposed System Architecture
BACKGROUND: Blockchain technologies have revolutionized the financial sector through their ability to generate immutable, cryptographically secure records. Clinical trials and health care data possess several synergies with those of the financial sector, specifically pertaining to the importance of tamper-resistant recording of processes. The evolution of blockchain to autonomously execute tasks contingent upon predefined contractual terms via smart contracts (SCs) allows a dynamic chain of interlinked events to unfold independently and in sequence, with time-stamped records. In recent years, mistrust in clinical trial data has grown significantly. Recording the entire clinical trial lifecycle from application, registration, recruitment to conduct, finance management, statistical analysis, and reporting in an immutable, cryptographically secure ledger with SC execution of trial processes could limit the potential for human intervention and tampering. This would produce a time-stamped record of all events within the trial lifecycle. Leveraging the capabilities of SCs could alleviate recruitment challenges and address ongoing concerns regarding data transparency, ownership, and integrity that currently undermine clinical trial processes. OBJECTIVE: This study aimed to review the existing literature on SC applications in clinical trials and propose a system architecture for using SCs to automate key processes throughout the clinical trial lifecycle. METHODS: A systematic search was conducted in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, identifying peer-reviewed studies and open-source repositories pertaining to the implementation of SCs in clinical trials. Data were extracted specific to the stage of the trial lifecycle described, SC architecture, and technical specifications for real-world implementation. Data were synthesized to propose an architecture for automating clinical trial processes within the lifecycle using SCs. RESULTS: A total of 144 records were screened; 10 studies met the inclusion criteria. Most implementations used private Ethereum-based networks (7/10, 70%). Reported applications included automated patient matching (5/10, 50%), consent management with dynamic permissioning (6/10, 60%), protocol enforcement and time-stamped audit logs (9/10, 90%), adverse event reporting (3/10, 30%), and financial or workflow automation (3/10, 30%). SC-based recruitment systems demonstrated rapid matching performance (eg, 6000 simulated patients matched in 2.13 s). However, all included systems were prototypes or simulations, and none were tested in real-world regulatory settings. Scalability, interoperability limitations, regulatory ambiguity (eg, General Data Protection Regulation right-to-erasure conflicts), and high infrastructural complexity were common gaps noted across studies. CONCLUSIONS: Current evidence suggests that SCs can enhance transparency, traceability, and automation throughout the clinical trial lifecycle. However, the literature remains dominated by simulation-based prototypes, primarily Ethereum-dependent architectures, and lacks analyses of cost-effectiveness, governance, and integration with institutional workflows. Future research should evaluate hybrid architectures, develop interoperability standards, and assess regulatory and ethical implications in real deployments.
30 May 2026
Read appraisal →European respiratory review : an official journal of the European Respiratory Society
Validating exacerbations of asthma in electronic health records: a systematic review
BACKGROUND: Previous studies have shown that the algorithms and code lists used to define asthma exacerbations vary across different sources of data, if reported at all. Defining and validating asthma exacerbations in electronic health records (EHR) would help to improve future research on asthma using EHR by leading to more consistent and comparable evidence. METHODS: We systematically reviewed the literature to evaluate studies that define exacerbations of asthma in EHR and report which algorithms have the highest validity. An adapted version of the QUADAS-2 designed for this review was used to assess risk of bias. RESULTS: Of the studies yielded by the search, only five met the inclusion criteria. Eligible studies used algorithms that contained codes from versions or modifications of either the 9th or 10th revisions of the International Statistical Classification of Diseases and Related Health (ICD-9 or ICD-10), and validity scores varied. Using the ICD-9 code 493 within algorithms to detect asthma exacerbations, sensitivity scores varied from 44.8% to 91.28% and specificity was >85%. Using the ICD-9 code 493.xx as the principal and secondary diagnosis in claims data, validity measures were all >85%. Using the ICD-10 code J45, scores for sensitivity, specificity and negative predictive value were also all >85%. CONCLUSIONS: Algorithms have been used to identify asthma exacerbations in EHR with varying degrees of validity. Algorithms including the ICD-9 code 493.xx or the ICD-10 code J45 to detect asthma exacerbations had high validity scores. However, there was a risk of bias in these studies and urgent work is needed using robust methods to validate definitions for future research using EHR.
29 May 2026
Read appraisal →Neuroscience
Therapeutic efficacy of engineered exosomes in Alzheimer's disease: A systematic review and meta-analysis of preclinical animal models
Engineered exosomes are modified extracellular vesicles designed to enhance targeting and cargo delivery, and they have been proposed as a therapeutic strategy for Alzheimer's disease. We systematically reviewed preclinical animal studies evaluating engineered exosomes, synthesized evidence from comparisons with disease models and with natural exosomes, and reported the study in accordance with the PRISMA 2020 checklist. Outcomes included spatial learning and memory assessed by the Morris water maze, amyloid beta pathology, tau phosphorylation, and neuroinflammatory markers. Random effects meta-analyses suggested that engineered exosomes improved Morris water maze performance and reduced amyloid beta burden and pro-inflammatory cytokines compared with natural exosomes, whereas evidence regarding tau phosphorylation was limited and largely qualitative, and the overall certainty of evidence was low to very low. These findings support further investigation of engineered exosomes, but conclusions should be interpreted cautiously until confirmed by rigorously designed and blinded preclinical studies and clinical trials with standardized protocols.
25 May 2026
Read appraisal →Studies in health technology and informatics
De-Identification of Free-Text Medical Records Using Large Language Models
This study evaluates large language models (LLMs) for automated de-identification of free-text medical records. Using 150 synthetically generated, personal health information (PHI)-enriched doctor's letters (23.2 PHIs per letter), we compared the full LLaMA-3.1-8B model (BF16, GPU) with a quantized variant (Q8, CPU) under zero-shot and few-shot prompting. Few-shot prompting improved performance from a macro F1 of 0.989 to 0.996 (recall = 0.994); the quantized Q8 model achieved a macro F1 of 0.992 (recall = 0.987) while enabling fully local, GPU-free inference. Although LLMs perform at a level comparable to human annotation, false negatives remain a concern for highly sensitive PHI, such as names. While human annotators typically require 13.4 seconds per PHI, the LLMs de-identified complete letters within seconds, demonstrating an efficiency and scalability advantage alongside GDPR-compliant, high-precision de-identification.
24 May 2026
Read appraisal →Studies in health technology and informatics
Build and Query Indexes of Clinical Documents with Easy-to-Reuse Pipelines
Electronic Health Records are a central source of healthcare data, containing structured data alongside unstructured clinical texts. The latter capture detailed reasoning, observations, treatment plans and clinical evolutions, which are crucial for phenotyping, and real-world evidence generation. Natural language processing enables the extraction, thus the subsequent use, of these crucial elements; however, these extractions remain one-off, study-specific efforts. This is detrimental as the extracted elements could be valuable for future research. We present medkit Seshat, an open-source Python pipeline that: (1) ingests free text, (2) recognizes relevant entities, (3) normalizes them with OMOP vocabularies, (4) builds an index that can either be searched by concept or by document. In addition, we share a flexible web UI to illustrate the interest of built indexes in terms of search, text analysis and export. Seshat aims at facilitating the reuse and adaptation of this prototypical pipeline to various purposes, with the main objective of enabling the secondary use of results of phenotyping campaigns.
24 May 2026
Read appraisal →Acta oncologica (Stockholm, Sweden)
KaSARi: a national framework for standardized, automated, and predictive radiotherapy in Finland.
BACKGROUND AND PURPOSE: National radiotherapy (RT) data infrastructures are emerging to support treatment quality assurance and outcome research. However, prospective nationwide integration of full DICOM-RT data with toxicity and patient-reported outcome measures (PROMs) remains uncommon. KaSARi (Key advances in Standardizing, Automating, and predicting Risks in RT) was established to create national research infrastructure for prospective RT data collection and integration in Finland. MATERIALS AND METHODS: KaSARi is a prospective, consent-based multicenter cohort infrastructure involving Finnish university and central hospitals. All adult patients receiving RT are eligible. DICOM-RT datasets from treatment planning and oncology information systems are linked to clinician-graded toxicity, PROMs and relevant clinical variables. The infrastructure builds on previously validated multi-institutional DICOM workflows and follows FAIR (Findable, Accessible, Interoperable, Reusable) data principles. Predefined work packages support data harmonization, scalable data processing and enable downstream applications such as AI-based segmentation, dose prediction, and outcome modeling. RESULTS: Patient recruitment started in May 2025. By February 2026, 221 patients had been enrolled at the coordinating center, initially including breast cancer patients and subsequently expanding to all RT indications. Recruitment at a second center began in November 2025, with 37 patients enrolled. The infrastructure is projected to include approximately 29,000 patients over 15 years. Integration of dosimetric, clinical and PROM data is progressing through a phased national implementation as additional centers join the network. INTERPRETATION: KaSARi represents a national infrastructure prospectively integrating full DICOM-RT datasets with clinician-graded toxicity and PROMs across all RT indications within a unified research protocol. The study provides a foundation for nationwide outcome modeling, harmonization of RT practices and development and validation of data-driven AI-based methods.
19 May 2026
Read appraisal →Drug discoveries & therapeutics
Artificial intelligence (AI)-assisted ultrasound in clinical trials: Endpoint automation, decentralized monitoring, and regulatory readiness
Ultrasound is among the most widely used imaging modalities in clinical trials, and yet its dependence on operator skill and equipment settings has historically limited the reproducibility of ultrasound-based endpoints in multi-center studies. Artificial intelligence (AI) now addresses this limitation across two complementary dimensions: automated measurement algorithms that quantify cardiac function, organ volume, and vascular parameters with reproducibility approaching or, in select settings, exceeding that of trained human readers and real-time acquisition guidance systems that enable clinicians with no formal sonography training to perform diagnostic-level examinations, making remote and decentralized assessment increasingly feasible. This narrative review synthesizes current evidence and regulatory developments across three interconnected domains. First, use of automated ultrasound to ascertain endpoints has advanced from single-institution validation to prospective and randomized evidence, with deep learning measurement of the left ventricular ejection fraction demonstrating formal equivalence to expert readers across multiple echocardiographic parameters and AI-first workflows shortening the time to diagnosis in a blinded non-inferiority trial. Second, AI-guided ultrasound acquisition by nurses and other non-expert operators has achieved a high rate of diagnostic acceptability in cardiac and pulmonary ultrasound, laying the groundwork for use of ultrasound-based endpoints in decentralized clinical trial designs, as reflected in Food and Drug Administration (FDA) guidance on decentralized trial elements. Third, the regulatory frameworks governing AI-enabled medical devices - including the U.S. FDA's Predetermined Change Control Plan guidance, the EU Artificial Intelligence Act, and internationally harmonized good machine learning practice relevant to Japan and other jurisdictions - increasingly emphasize overlapping principles such as specification of prospective performance, post-marketing oversight, and transparent reporting. Addressing remaining challenges in domain generalization across vendors, subgroup fairness, and algorithm change management during ongoing trials will be essential for AI-assisted ultrasound to fulfill its potential as a robust, scalable endpoint in clinical research worldwide.
18 May 2026
Read appraisal →JMIR research protocols
A Natural Language Processing Framework for Structuring and Visualizing Clinical Trial Eligibility Criteria at Scale: Protocol for a Quantitative Study
BACKGROUND: Eligibility criteria are essential to clinical trial design, guiding recruitment, and ensuring patient safety and scientific rigor. However, criteria are often lengthy, heterogeneous, and inconsistently formatted, which hinders large-scale interpretation and slows patient-trial matching. Manual review is time-consuming and error-prone. Advances in natural language processing and large language models (LLMs) offer opportunities to standardize and analyze eligibility text at scale. OBJECTIVE: This study aims to develop and evaluate a scalable system that uses LLM-enabled natural language processing and unsupervised learning to identify, normalize, categorize, and visualize clinical trial eligibility criteria, with the goal of improving patient-trial matching and revealing domain-level trends. METHODS: We designed a three-part pipeline: (1) representation of eligibility text using embeddings, followed by clustering to group semantically similar criteria; (2) dual-layer zero-shot LLM summarization for concept normalization, refinement, and deduplication of cluster exemplars; and (3) an interactive, web-based visualization interface to explore criteria distributions and trends by disease domain and over time. The pipeline was applied to 53,872 oncology trials (breast, lung, and gastrointestinal cancer) indexed on ClinicalTrials.gov. Outputs include cluster labels, normalized criterion summaries, and per-domain frequency profiles. Feasibility was assessed via successful end-to-end processing and inspection of face validity for cluster coherence and domain-specific patterns. RESULTS: The system successfully processed all 53,872 trials and generated stable clusters of inclusion and exclusion concepts. The LLM summarization layers produced concise, nonredundant labels that improved the interpretability of clustered criteria. The visualization interface enabled rapid exploration of cross-trial patterns and temporal trends within breast, lung, and gastrointestinal oncology, facilitating identification of common inclusion requirements and potential barriers to enrollment. A public, open-source demonstration instance allows for interactive exploration of these clusters and summaries. Benchmarking through human validation on a random sample of eligibility criteria found the system to be 94% (470/500) accurate, reflecting its ability to consistently categorize criteria correctly in congruence with human judgment. CONCLUSIONS: A combined embeddings-clustering-LLM pipeline can standardize heterogeneous eligibility text and surface domain-level patterns at scale. This framework provides a foundation for accelerating patient-trial matching and informing future trial design. While the current implementation was evaluated on ClinicalTrials.gov oncology trials, the approach is readily generalizable to additional diseases and alternative modeling configurations.
16 May 2026
Read appraisal →Blood advances
Novel use of a hash-based tokenization for sharing sickle cell disease data without sharing protected health information
Efforts to improve care for people living with sickle cell disease (SCD) have led to the development of several registries; however, many are dependent on time-limited funding and lack coordination. Consequently, existing data sets are fragmented and do not provide the comprehensive, longitudinal insights achievable through well-integrated registries. Although relevant data exist within electronic medical records across institutions, aggregation is limited by poor interoperability, inconsistent use of common data elements, and poor translation of natural language into codified data. These barriers hinder population-level research and contribute to gaps in understanding the lifelong progression of SCD. Creating a new common data system risk losing years of valuable data, highlighting the need to optimize existing data resources. This study aimed to develop a privacy-preserving method to securely link 3 of the largest SCD data collection efforts in the United States. Conducted at the University of Alabama at Birmingham Lifespan Sickle Cell Center, the study leveraged institutional review board-approved access to the Sickle Cell Data Collection project, the American Society of Hematology Research Collaborative Data Hub, and the Globin Research Network for Data and Discovery. Identity tokens were generated and hashed using Secure Hash Algorithm (SHA)-256 to enable secure linkage without sharing protected health information. A total of 8026 records were identified across the 3 registries. Deterministic matching of hashed tokens identified 1080 unique individuals appearing in at least 2 data sets. This study demonstrates the first privacy-preserving linkage of multiple SCD registries. Secure data integration enhances interoperability and enables richer longitudinal analyses critical for advancing SCD research and treatment development.
15 May 2026
Read appraisal →European journal of heart failure
Surrogate markers of clinical endpoints in clinical trials of heart failure.
AIMS: We aimed to determine whether treatment related changes in surrogate markers predict longer-term therapeutic effects on all-cause mortality and heart failure (HF) hospitalization in randomized trials of HF. METHODS: Systematic literature search included randomized trials of interventions in patients with HF until October 2024. Random-effects meta-regression models with inverse variance weighting were calculated between fifteen surrogate markers and the clinical endpoints of (i) all-cause mortality and (ii) HF hospitalization. The degree of heterogeneity of each model explained by the surrogate marker was determined with R2. Surrogate threshold effects (STEs) were also calculated. RESULTS: Ninety-six randomized trials with median follow-up 12 months were included, enrolling a total of 120 304 patients with HF. Treatment related changes in natriuretic peptides (NPs) were weakly correlated with all-cause mortality (64 comparisons, P = .002, R2 = 12%, and STE = -34%) and HF hospitalization (41 comparisons, P < .001, R2 = 32%, and STE = -30%). Changes in LVEF were moderately correlated with mortality (69 comparisons, P < .001, R2 = 59%, and STE = +6%) and strongly correlated with HF hospitalization (45 comparisons, P < .001, R2 = 90%, and STE = +2%), although this finding was only observed in trials of HFrEF. LV end-diastolic diameter was correlated with HF hospitalization but not mortality. Other echocardiographic markers were not predictive of clinical endpoints. Treatment related changes in patient reported outcomes and exercise capacity were either weakly correlated with clinical outcomes or derived from small clinical trials. CONCLUSION: In HF trials, most surrogate markers, including NPs and echocardiographic measures were only weakly or moderately correlated with treatment effects on all-cause mortality. There is insufficient evidence to support the use of a single biomarker or echocardiographic measure in regulatory trials of HF.
14 May 2026
Read appraisal →Molecular biology reports
Genetic modulation of pain pathways: toward a new era in pain therapy- a systematic review
Gene therapy represents a new strategy in pain management targeting the causes of pain rather than its symptoms. This review summarizes recent advances across RNA interference (RNAi), viral vector delivery systems, CRISPR/Cas9, gene replacement therapy, and endogenous opioid gene delivery, emphasizing efficacy, safety, and mechanisms of action in pain conditions. RNAi and gene replacement techniques remain powerful tools for reducing pain and improving the quality of life by modulating pain-associated genes. Long-term relief may also be achieved with CRISPR/Cas9 and site-directed delivery using nanoparticle systems. Safety profiles especially with CRISPR/Cas9 remains a concern. A systematic search of Web of Science, Medline, Scopus, and Google Scholar identified 512 records (January 2010-March 2023). Following PRISMA screening, 18 studies met inclusion criteria. These studies evaluated strategies of gene therapy in neuropathy, arthritis, fibromyalgia, and complex regional pain syndrome. The review outlines available options and highlights preclinical findings.
11 May 2026
Read appraisal →Journal of the American Society of Nephrology : JASN
Streamlining the Histopathologic Workflow in Diabetic Kidney Disease with Artificial Intelligence
KEY POINTS: Artificial intelligence models effectively generalized across studies and animal models and reduced translational gaps when applied to human biopsies. Artificial intelligence assistance reduced study evaluation turnaround times by up to 90% versus manual whole slide imaging scoring, matching expert-level performance. Self-supervised learning captured diabetic kidney disease-relevant features and mitigated expert-specific bias. BACKGROUND: Assessment of pathology end points in animal models of diabetic kidney disease is time-consuming and prone to expert bias. In addition, the sparsity of human kidney biopsy data hinders the development of translational models from animals to humans. METHODS: We developed an artificial intelligence (AI)-driven workflow to streamline histopathologic assessments in animal models of diabetic nephropathy. Our approach ( 1 ) detected glomeruli in whole slide images, ( 2 ) enabled fast expert scoring through an annotation tool, and ( 3 ) automated scoring. By leveraging unlabeled preclinical data for self-supervised learning, we enhanced AI scoring performance, reduced expert bias, and enabled the translation of AI scoring from animal models to human biopsies. To translate AI models from preclinical studies to human biopsies, we introduced a method that adjusted the feature extractor to human-specific features during inference without the need for annotated examples. RESULTS: Our annotation tool streamlined glomerular scoring, reducing turnaround time by 80%. Supervised AI models outperformed expert agreement and further reduced turnaround time by 90%, demonstrating generalization across studies involving both the same and different animal models. Without supervision, the self-supervised model achieved a κ value of 0.78, effectively identifying glomerular changes without guidance. Incorporating self-supervised learning into supervised training improved performance to κ=0.84 and reduced bias compared with individual experts ( P < 0.001). Our translational approach achieved a κ value of 0.63 on human glomeruli, although the model was trained exclusively on mouse glomeruli scores, reducing the translational gap by 45%. CONCLUSIONS: In this study, we accelerated and enhanced pathology readouts in a real-life pharmaceutical industry setting. We show that AI-assisted scoring reduced pathologists' workload and expedited study assessments. Self-supervised learning captured intrinsic properties of kidney morphology without expert annotation and reduced expert bias and translational discrepancies, greatly facilitating translational activities in drug development for patients with diabetic kidney disease.
5 May 2026
Read appraisal →American Society of Clinical Oncology educational book. American Society of Clinical Oncology. Annual Meeting
Harnessing Artificial Intelligence for the Management of Patients With GI Cancers
Artificial intelligence (AI) has the potential of reshaping GI oncology by enabling more nuanced interpretation of complex clinical, imaging, and molecular data, while supporting more timely and patient-centered decisions. This article synthesizes perspectives across the GI cancer continuum, beginning with a framework for context-aware AI that emphasizes metadata, multimodal integration, and lifecycle quality and safety as foundations for trustworthy tools that clarify, rather than conceal, uncertainty. Next, AI in endoscopy is highlighted as an example in clinic practice, focusing on computer-aided detection and diagnosis systems that not only increase adenoma detection rates but also raise questions about surveillance burden, real-world effectiveness, and the balance between skill enhancement and potential deskilling of endoscopists. Another section explores how AI can help GI oncologists design, prioritize, and implement highly innovative clinical trials-particularly multi-omic and imaging-driven approaches-while envisioning a future in which far more patients participate in trials that align with their goals and values. The final section reviews emerging AI-enabled clinical trial matching pipelines, including large language model-based retrieval and prescreening tools that operate on real-world electronic health record and protocol data, and discusses challenges related to bias, privacy, explainability, and workflow integration. Together, these contributions argue that the greatest impact of AI in GI oncology will come from deliberately aligning technical capabilities with highly relevant patient-centered clinical questions, ethical governance, and implementation strategies that expand access to trials and improve outcomes for patients with GI malignancies.
2 May 2026
Read appraisal →Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer
Conducting a randomized controlled clinical trial on palliative care in patients with glioblastoma - what are the challenges?
PURPOSE: Patients with glioblastoma represent a highly vulnerable cohort as they often experience rapid health deterioration with severe symptom burden including neurological, (neuro)psychological, and psychiatric symptoms. The aim of this sub-analysis of the "Early Palliative Care for Patients with Glioblastoma" (EPCOG) trial was to investigate the specific challenges of conducting a multicenter, randomized, controlled, clinical trial in glioblastoma patients testing a specialized palliative care (PC) intervention. METHODS: We analyzed screening protocols and protocol deviations with respect to number and reasons for non-participation, skipped/delayed visits and attrition using descriptive statistics and content analysis of free-text comments. RESULTS: In total, 41.5% of 556 screened patients were enrolled. Main reasons for non-participation were lack of interest (25.7%) and low functional status (11.5%). Attrition due to death (57.6%) was higher than due to illness (5.2%) or other reasons (21.2%). Main reasons for visit deviations were structural issues (in > 50% of neurosurgical visits), health status, and patient request. Protocol deviations showed that specialized PC intervention visits were least frequently skipped (4.5%) compared to study-specific outcome assessment (10.1%) and neurosurgical (43.3%) visits. Further, only 11.0% of the specialized PC intervention visits were delayed compared to 22.3% of the outcome assessment and 56.4% of the neurosurgical visits. CONCLUSION: In this clinical trial involving glioblastoma patients, a high level of motivation among the study participants could be reached, as reflected by low protocol deviations during the specialized PC intervention and study-specific outcome assessment visits. Reasons for this might be a close guidance as well as a patient and caregiver-oriented communication, e.g., by a personal contact of the PC team in the intervention group, personal outcome assessment visits at patients' whereabouts, or the inclusion of a study nurse at each site. Considering the high vulnerability of glioblastoma patients is crucial when designing and conducting clinical trials.
2 May 2026
Read appraisal →Lab on a chip
MaGIC-OT: an AI-guided optical tweezers platform for autonomous single-cell isolation in microfluidic devices
Automating the isolation of rare cells such as circulating tumour cells (CTCs) within crowded microfluidic environments remains a bottleneck in liquid biopsy workflows. Optical tweezers offer contact-free, selective manipulation but traditionally rely on expert operators. We present MaGIC-OT (machine-guided isolation of cells using optical tweezers), a platform that integrates classical path planning and deep reinforcement learning (DRL) to automate single-cell manipulation inside a microfluidic chip. We built a high-fidelity simulation to train and benchmark control policies and show that cooperative, human-in-the-loop training improves DRL performance. Trained agents outperform expert users in speed and isolation success in silico, and we demonstrate proof-of-concept isolation of a cancer cell from a spiked blood sample on-chip. MaGIC-OT provides a flexible framework for intelligent optical manipulation, aligning microfluidic device design with autonomous control strategies and offering a pathway toward high-purity, label-free single-cell workflows.
26 Apr 2026
Read appraisal →Journal of medicinal chemistry
Machine Learning Approach to Anticancer Activity Prediction of Transition-Metal Complexes Based on a Large-Scale Experimental Database
In this work, we developed a straightforward data-driven approach to predict the cytotoxicity of metal complexes based entirely on their (metal + ligands) composition. To this end, we have manually curated MetalCytoToxDB─a comprehensive experimental database comprising 26,500 IC50 values for 7050 metal complexes against 754 cell lines from 1921 articles. Based on these, machine learning models were created to accurately assign the cytotoxicity class within the ruthenium and iridium subsets. Moreover, external validation of the best-performing model on the unseen data was carried out. The possibility of multimetal predictions was explored, enabling assessment of cytotoxicity among the complexes of metals, for which experimental data are relatively scarce. The interpretability and limitations of the developed models are discussed. Finally, a pipeline for the effective high-throughput computational screening of ruthenium complexes is proposed. The MetalCytoToxDB is available online for AI-assisted exploration at https://biometaldb.streamlit.app/.
25 Apr 2026
Read appraisal →Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer
Predictive biomarkers of placebo response in patients with cancer: an exploratory analysis of the ABCD randomized clinical trial
PURPOSE: Placebo effect is commonly observed in symptom management randomized clinical trials. However, there are currently no established predictive biomarkers of placebo response. We examined the patterns of association between placebo response and baseline plasma cytokine levels for 10 symptoms in patients with cancer. METHODS: This is an exploratory analysis of the double-blind, randomized ABCD trial, which compared high-dose dexamethasone to placebo for dyspnea treatment in patients with cancer (clinicaltrials.gov; NCT03367156). The primary outcome was change in dyspnea intensity. Four plasma cytokines (TNF, IL-6, IL-8, and IL-10) and 10 Edmonton Symptom Assessment System symptoms were measured at baseline, day 7, and day 14. Generalized additive models and exploratory analyses were used to examine the patterns of association between baseline cytokine levels and symptom responses on day 7 and day 14 in placebo and dexamethasone groups. RESULTS: This analysis included data from 45 patients. In the placebo group, we observed a significant negative association (p < 0.05) between ≥ 1 of the measured cytokines' baseline levels across multiple symptoms on day 7 (5/10 symptoms) and day 14 (3/10 symptoms), including appetite, drowsiness, nausea, and pain. Exploratory analysis revealed a negative association in the placebo group in 33/40 cytokine-symptom response combinations for day 7 (p < 0.001) and 29/40 combinations for day 14 (p = 0.006). CONCLUSION: Our preliminary findings suggest patients with high baseline cytokine levels may be less likely to report placebo response for multiple symptoms. Upon further confirmation, these findings may have implications for future clinical trial design. In this exploratory analysis, we observed that patients with cancer were less likely to report placebo response for multiple symptoms if they had higher levels of baseline cytokines. These preliminary findings have important potential implications for placebo-controlled clinical trials, including patient selection, design of interventional controls, and trial interpretation. Additionally, they invite further research on possible mechanistic links between inflammation and placebo effect.
25 Apr 2026
Read appraisal →Journal of the American College of Cardiology
African Representation in Randomized Controlled Trials Published in Leading Medical and Cardiovascular Journals, 2019-2024
BACKGROUND: Despite accounting for a substantial proportion of the global population and disease burden, African countries are underrepresented in randomized controlled trials (RCTs), including those informing cardiovascular (CV) care. OBJECTIVES: In this study, we sought to quantify African representation in RCTs published from 2019 to 2024 in: 1) 5 leading general medical journals; and 2) 3 leading CV journals. METHODS: We conducted a systematic review of RCTs published from 2019 to 2024 in the British Medical Journal, the Journal of the American Medical Association, The Lancet, Nature Medicine, and the New England Journal of Medicine, and in Circulation, the European Heart Journal, and the Journal of the American College of Cardiology. Eligible studies included traditional, pragmatic, cluster, and stepped-wedge RCTs. African representation was assessed by trial scope (Africa-only vs multicontinental), country and regional participation, disease category, and African authorship. RESULTS: Among 2,138 RCTs published in leading general medical journals, only 83 (3.9%) were conducted exclusively in Africa, and 195 (9.1%) were multicontinental studies including at least 1 African site. In the CV journals, 2 out of 334 RCTs (0.6%) were conducted exclusively in Africa, and African sites were included in only 9 multicontinental trials (2.7%). South Africa accounted for the majority of Africa-based RCTs across both journal categories. Regionally, southern Africa predominated and central Africa was minimally represented. Trials published in general medical journals and conducted exclusively in Africa largely focused on infectious diseases (n = 63; 75.9%), with only 3 addressing cardiovascular disease (CVD). In contrast, Africa-including multicontinental trials more frequently investigated noncommunicable diseases, including CVD. African leadership was common in Africa-only trials but rare in multicontinental studies. CONCLUSIONS: African countries are profoundly underrepresented in RCTs published in the world's most influential medical and CV journals. Addressing this imbalance requires expanding African participation in global trials, investing in local research capacity, and promoting equitable leadership to strengthen the relevance and validity of clinical evidence. (Underrepresentation of African Countries in Randomized Controlled Trials: A Systematic Review of Leading General Medical and Cardiovascular Journals; CRD42024603157).
24 Apr 2026
Read appraisal →Journal of the American College of Cardiology
Using Artificial Intelligence to Adjudicate Major Adverse Cardiovascular Events in Clinical Trials
BACKGROUND: Major adverse cardiovascular events (MACE)-cardiovascular (CV) death, nonfatal myocardial infarction (MI), and nonfatal stroke-are highly relevant clinical outcomes. In global randomized trials, medical records review by a physician clinical events committee (CEC) is the conventional standard for adjudicating MACE but is labor intensive. Automated adjudication with the use of artificial intelligence (AI) could reduce cost and improve reproducibility. OBJECTIVES: In this study, the authors sought to develop and validate an AI-based adjudication system for MACE and compare its performance with CEC adjudication in a large global randomized trial. METHODS: We developed an AI-based system ("Auto-MACE") that uses an iteratively refined prompt of the OpenAI o1-mini language model to adjudicate MACE events, and a Clinical Longformer model trained on adjudicated events to assign a confidence level. We validated Auto-MACE against CEC adjudication in the PARADISE-MI global clinical trial comparing sacubitril/valsartan and ramipril in 5,661 patients with MI complicated by systolic dysfunction or pulmonary congestion. RESULTS: Auto-MACE provided a confident adjudication in 315/455 deaths (69%), 301/659 potential MIs (46%), and 136/167 potential strokes (81%). Auto-MACE agreed with the CEC adjudication in 97%, 89%, and 88% of confident events, respectively. Among all events, Auto-MACE agreed with CEC adjudications in 86% of deaths, 76% of potential MIs, and 84% of potential strokes. The estimated effect of sacubitril/valsartan vs ramipril on composite MACE was similar with Auto-MACE adjudication (HR: 0.91; 95% CI: 0.78-1.07) and CEC adjudication (HR: 0.90; 95% CI: 0.77-1.05). CONCLUSIONS: AI-based adjudication of MACE showed high agreement with human CEC adjudication, especially for CV death and stroke, and where the model was confident. Initial AI-based adjudication with CEC review of uncertain events may reduce workload while maintaining accuracy.
24 Apr 2026
Read appraisal →Trials
The use of complex clinical trials: a regulatory review.
BACKGROUND: Complex clinical trials offer flexibility in evaluating multiple treatments or diseases simultaneously. These trials often feature adaptive designs, common controls, and the potential to add new arms. However, the increased complexity raises methodological challenges particularly regarding multiple testing or the adequate choice of control groups. Despite guidance from regulatory bodies like the European Medicines Agency and the U.S. Food and Drug Administration, uncertainties remain about the regulatory acceptance of these trials. METHODS: This systematic review examines scientific advice procedures of products in the remit of the Paul-Ehrlich-Institut for complex clinical trials to highlight key concerns and regulatory feedback. We identified 30 scientific advice procedures corresponding to 29 different complex clinical trials. RESULTS: Our findings reveal an increasing number of complex trial designs proposed by applicants. A lack of multiplicity control due to multiple arms was generally considered acceptable by regulators in exploratory trials and if cohorts can be considered independent. Additionally, the use of common control groups is frequently proposed by applicants. The review underscores the importance of pre-planning for new treatment arms, appropriate multiplicity control, and the definition of control groups in trial designs. CONCLUSION: Overall, our findings suggest that regulatory concerns regarding complex trials largely align with those in traditional trial designs, though their complexity requires careful, case-by-case consideration. Early engagement with regulatory agencies can be crucial to ensure the successful design and implementation of these trials.
12 Apr 2026
Read appraisal →Neuroscience
Limitations and opportunities in multi-omics integration for neurodevelopmental, neurodegenerative and psychiatric disorders: A systematic review
Recent advances in high-throughput technologies have led to an increased generation of biological data across genomics, transcriptomics, proteomics, epigenomics, and metabolomics. However, a major challenge remains: effectively integrating these multi-omics datasets to allow a more holistic understanding of the complex, interconnected mechanisms underlying human diseases. Neurodevelopmental, neurodegenerative, and psychiatric disorders are particularly multifactorial and heterogeneous, making them candidates for multi-omics approaches. In this context, this systematic review assesses the current state of multi-omics integration in neurological research. Records retrieved from five major databases were processed, and 156 studies were included for further analysis. The most frequently studied conditions were Alzheimer's Disease, Depressive Disorder and Parkinson's Disease, with epigenomics-transcriptomics and metagenomics-metabolomics emerging as the most common omics pairings. The field remains dominated by studies integrating pairs of omics layers. Only a limited number of computational tools are currently being applied to the integration of more than two omics layers, highlighting a gap in comprehensive multi-omics modeling. Despite progress, key challenges persist, including data accessibility and the need for standardized frameworks to allow cross-study comparisons. Moreover, most computational findings lack experimental validation in wet-laboratory settings. Future research should address these challenges, develop scalable algorithms for integrating multi-omics data, and leverage large, open-access datasets. Integrating computational predictions with experimental validation could help researchers prioritize high-confidence biomarkers relevant to clinical applications. Collaborative efforts among bioinformaticians, clinicians, and experimentalists will be essential to translating these advances into clinically actionable solutions.
6 Apr 2026
Read appraisal →Annals of oncology : official journal of the European Society for Medical Oncology
Next-generation multicenter studies: using artificial intelligence to automatically process unstructured health records of patients with lung cancer across multiple institutions
BACKGROUND: Manual abstraction of real-world data (RWD) from unstructured health records (HRs) remains resource intensive, error prone, and highly variable across institutions. Large language models (LLMs) offer a scalable alternative, but their performance in multicenter oncology settings is not fully validated. PATIENTS AND METHODS: We conducted a multicenter study within the French Large & Unified Cancer Cohort (LUCC) consortium to compare the accuracy of artificial intelligence (AI)-based data extraction against manual abstraction by clinical research professionals. A fine-tuned LLM was applied to de-identified unstructured HRs in PDF format to extract 31 variables from lung cancer patients across 10 centers. Ground truth was defined as concordant values across sources, with discrepant cases adjudicated by a blinded expert. The primary endpoint was the extraction error rates. Secondary endpoints included per-variable performance, interinstitutional variability, F1-score for multiple-choice variables, added value of hybrid AI-human workflows, and survival analyses. RESULTS: Among 10 327 patients with AI-based extraction, 311 were included in the test cohort. Across 8708 datapoints for 28 variables with only one correct answer, the LLM achieved a 7.0% error rate, outperforming manual abstraction (14.2%, P <0.001). The F1-scores of three multiple-choice variables were superior (gene alterations 0.97 versus 0.86, comorbidities 0.86 versus 0.76, metastatic sites 0.71 versus 0.69). Interinstitutional variance was lower with AI (0.12% versus 0.39%). A hybrid approach with targeted human review of 30% of low-confidence AI outputs further decreased error rates to 4.4%. Survival analyses based on AI-extracted data closely matched ground truth, with similar median overall and progression-free survival. CONCLUSIONS: In a multicenter setting, our AI pipeline yielded lower error rates and greater consistency than manual abstraction. These findings support the feasibility of next-generation, AI-enabled multicenter studies to generate high-quality RWD at scale, with potential applicability in prospective clinical trials.
4 Apr 2026
Read appraisal →