Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 16 appraisals
Current opinion in pediatrics
Clinical implementation of artificial intelligence in adolescent mental healthcare
PURPOSE OF REVIEW: This review aims to summarize recent literature on artificial intelligence (AI) tools for adolescent mental health, including the types of tools available, their clinical applications, effectiveness, and safety, as well as relevant ethical considerations. RECENT FINDINGS: For clinicians, AI can facilitate clinical documentation, enhance therapy, and support the diagnosis process. Adolescents show interest in using AI for their mental healthcare and can benefit from AI-guided therapy apps and chatbots. Most studies that show effectiveness focus on depression treatment. Many tools are only in the prototyping stage, not tested on clinical samples, or lack safety measures, highlighting the need for further safety evaluation before specific app recommendations can be made. SUMMARY: AI is increasingly being implemented in pediatric health systems and adolescents' daily lives. Adolescent medicine practitioners should recognize the growing potential for certain AI applications to enhance access and support adolescents, review and utilize those applications that have empirical support of efficacy, and that provide guardrails for safe and ethical use.
1 Aug 2026
Read appraisal →International journal of medical informatics
A scoping review on conversational AI in mental health: A human-centered perspective.
BACKGROUND: Conversational AI offers scalable mental health support, with large language models (LLMs) enabling personalized interactions. Human-centered design is critical in this domain, yet a comprehensive synthesis from this perspective is lacking. This review maps conversational AI research in mental health across the patient journey and develops a human-centered taxonomy to guide future design. METHODS: Following PRISMA guidelines, we conducted a comprehensive search across fifteen multidisciplinary databases. We systematically analyzed the literature across six dimensions: research foci, mental disorder types, target populations, AI technologies, data sources, and evaluation metrics. A consensual taxonomy research method was employed to develop a human-centered design framework. RESULTS: Of 10,293 identified records, 677 studies met the inclusion criteria. Analysis reveals a marked increase in publications since 2020, predominantly from computer science (449 studies), followed by medicine (148) and social sciences (80). Research is skewed toward detection (23%) and intervention (66%) stages, with prevention (8%) and maintenance (3%) receiving less attention. Mood, anxiety, and stress-related disorders are the most investigated conditions. LLMs have emerged as the predominant AI technology, particularly within intervention and maintenance stages. Data sources continue to rely heavily on text-based inputs, with multimodal approaches still limited in adoption. Evaluation metrics vary significantly by discipline, reflecting limited cross-disciplinary integration. Through thematic synthesis, we developed a human-centered taxonomy comprising four primary dimensions: Emotional Sensitivity to Users, User-Centric Interaction Design, Human-AI Collaboration and Capability Enhancement, and Ethics and Accountability, with a total of thirteen sub-dimensions. CONCLUSIONS: This review provides a comprehensive, human-centered mapping of conversational AI research in mental health across the patient journey. Critical gaps remain in stage coverage, disorder diversity, population inclusivity, multimodal data integration, and interdisciplinary evaluation. The proposed taxonomy offers a structured framework to align AI development with human-centered principles, fostering empathetic, ethical, effective, and equitable mental health support.
16 July 2026
Read appraisal →Journal of affective disorders
Ecological momentary interventions for depression: A systematic review and meta-analysis
INTRODUCTION: Depression remains a prevalent condition with many individuals experiencing residual symptoms despite standard treatments. Ecological momentary interventions (EMIs) offer real-time, ecologically-valid microinterventions, yet their clinical utility and implementation challenges in depression remain underexplored. METHOD: A systematic search of six databases (inception to 25 July 2025) identified randomised controlled trials (RCTs) evaluating EMIs for depression. Pooled effect sizes assessed differences relative to comparator conditions. RESULTS: Sixteen RCTs involving 1258 participants were included. EMIs significantly reduced depressive symptoms at posttest (Hedges' g = 0.57; 95% CI = 0.33-0.80; p < 0.001) and at follow-up ranging from 10 to 32 weeks (Hedges' g = 0.43). High heterogeneity reflected variability in EMI formats. EMIs also showed a statistically significant improvement in quality of life (Hedges' g = 0.44; 95% CI = 0.17-0.71; p < 0.01), supporting their broader impact beyond symptom reduction. Engagement averaged 64.91% (SD = 17.18), ranging 37.5%- 88.0%, with variation across reporting methods. Acceptability and usability ratings were consistently high. Intervention dosage and risk of bias were significant moderators of treatment efficacy. Subgroup analyses revealed greater benefits from EMIs incorporating psychoeducation and active practice, and fully-automated formats. CONCLUSION: The review highlights EMI efficacy in reducing depressive symptoms and improving quality of life, with intervention dosage and methodological rigor emerging as key moderating factors. Reporting engagement remains a challenge, and substantial heterogeneity underscores the need for refined trial designs to isolate the active EMI components to best optimise treatment outcomes in depression. Future studies should prioritise strategies strengthen methodological rigor and optimising user engagement. PROSPERO No. CRD420251105663.
16 July 2026
Read appraisal →Psychological medicine
Mechanisms of mindfulness-based cognitive therapy in difficult-to-treat depression: moderation and mediation analyses from the RESPOND trial.
BACKGROUND: Mindfulness-based cognitive therapy (MBCT) was developed for relapse prevention in people with remitted depression but is increasingly used for those with difficult-to-treat depression (DTD). A key question regarding this broader application is whether ongoing depressive symptoms constrain therapeutic responsiveness or disrupt MBCT's proposed mechanism, decentering. We explored whether baseline depressive severity moderates clinical outcomes, whether changes in decentering mediate treatment effects, and whether this mediation varies by baseline severity. METHODS: Secondary moderation, mediation, and moderated mediation analyses were conducted using data from the RESPOND randomized trial (N = 234), comparing MBCT plus treatment as usual (TAU) with TAU alone in adults not remitted after high-intensity psychological therapy. Depressive symptoms (PHQ-9) and decentering (Experiences Questionnaire) were assessed at baseline, post-treatment (10 weeks), and follow-up (34 weeks). Analyses were conducted using structural equation modelling. RESULTS: Higher baseline severity predicted greater symptom improvement across both groups. Treatment-related increases in decentering partially mediated the effect of MBCT on depressive symptoms at follow-up. Although baseline severity did not moderate the treatment effect, it moderated the indirect effect, with decentering more strongly associated with symptom reduction among those with higher baseline depression. Severity did not moderate the acquisition of decentering skills. CONCLUSIONS: Concerns that more severe depressive symptoms limit the effectiveness of MBCT were not supported. MBCT's core mechanism remained operative under substantial symptom burden, with clinical impact amplified at higher severity. These findings reduce key uncertainties regarding the application of MBCT in DTD and support its use across a broad range of symptom severity.
15 July 2026
Read appraisal →JMIR mental health
AI Agents Are Coming: 5-Stage Taxonomy of Language-Based AI Systems for Psychiatry, Psychotherapy, and Counseling
The rapid evolution of large language models has accelerated the development of agentic artificial intelligence (AI) systems capable of pursuing autonomous goals, creating an urgent need for structural frameworks in psychiatry and psychotherapy. While existing classifications often draw parallels to autonomous driving, this paper argues that the mental health domain requires a distinct, domain-specific theoretical foundation, as the 2 domains differ fundamentally in their semantic, ideographic, and epistemological demands. Furthermore, they differ in their end goals, for which we introduce terms such as agentic guidance capability. To guide clinicians and researchers through these developments, we propose a 5-stage taxonomy for language-based AI systems that differentiates technical functionality from clinical effectiveness. The taxonomy progresses from level 1 (knowledge level), in which systems perform static benchmark tasks, to level 2 (elementary level), characterized by dynamic engagement in specific therapeutic microskills. At level 3 (integration level), systems achieve consistency across and within modules, as well as basic case-level conceptualization suitable for blended therapy under human oversight. Level 4 (saturation level) describes therapist-in-the-loop systems capable of autonomous functioning with minimal supervision, whereas level 5 (mastery level) represents AI systems that are technically capable of performing autonomous therapy. By distinguishing technical functionality from clinical effectiveness, we conclude that level 4 or level 5 performance does not automatically translate into full treatment effectiveness, even if high treatment fidelity can be achieved. We conclude by emphasizing the need to shift benchmarking from static knowledge tests to dynamic evaluations of therapeutic capabilities in order to safely navigate the transition toward autonomous care.
15 July 2026
Read appraisal →JMIR medical informatics
Natural Language Processing Applied to Psychiatric Clinical Notes: Scoping Review
BACKGROUND: Psychiatric clinical notes in electronic health records (EHRs) provide rich longitudinal information that can support clinical decision-making. Using historical medical data can enable earlier identification of mental illness, better characterization of disease trajectories, and more personalized treatment planning. Natural language processing (NLP) transforms these unstructured notes into analyzable representations for research and care. OBJECTIVE: This study aims to systematically summarize NLP methodologies for psychiatric clinical notes, compare major modeling paradigms and application areas, and highlight emerging large language model (LLM) trends, key challenges, and future research directions. METHODS: Following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines, a literature search was conducted for articles on NLP methods based on psychiatric clinical notes published from January 2021 to December 2025 in Ovid MEDLINE, Ovid EMBASE, PubMed, Scopus, Web of Science, the ACM Digital Library, and ScienceDirect. This scoping review analyzed NLP methods applied to psychiatric clinical notes, focusing on major trends, identifying suitable features for traditional machine learning (ML)-based models, applications of pretrained language models (PLMs), and key challenges. Approaches were categorized as rule-based, traditional ML, hybrid, deep learning (DL), and LLM-based methods across information extraction and text classification tasks. RESULTS: In total, 101 studies were eligible for inclusion. Rule-based methods (n=36) and hybrid approaches (n=34) remained the most widely used techniques, largely favored for their interpretability in handling nuanced, subjective clinical notes. These were followed by DL (n=15), traditional ML (n=10), and LLM-based approaches (n=6). Traditional ML studies relied heavily on engineered features, which could be grouped into 5 broad categories: domain knowledge features, lexical and statistical features, vector-based semantic features, emotion-related features, and temporal features. PLMs improved performance mainly through domain adaptation and task-specific fine-tuning, enhancing the handling of psychiatric language, medical terminology, and clinical note structure. LLM-based studies, although still limited in number, indicated a growing shift toward generative and reasoning-based applications. CONCLUSIONS: Hybrid NLP approaches remain dominant, combining domain rules with ML for extraction and classification. DL approaches continue to advance, with domain adaptation supporting medical terminology and clinical semantics. LLMs may further automate complex workflows via zero-shot capabilities and reasoning, alongside growing interest in temporal modeling and multimodal integration. Key future needs include improved generalizability across institutions, privacy protection, and careful attention to ethical implications in clinical deployment.
13 July 2026
Read appraisal →JMIR mental health
Digital Mental Health Research Priorities, Revisited for the AI and Large Language Model Era
Digital mental health has become an established part of mental health care, but the rapid arrival of large language models and other artificial intelligence (AI) tools has refocused attention on the evidence needed to guide the field. This editorial updates the research priorities articulated by JMIR Mental Health in 2023, while reaffirming their emphasis on equity, replicability, privacy, efficacy, and engagement. While the importance of these priorities has not changed in recent years, the urgency with which they must now be applied has. As digital tools become more clinically consequential, research must move beyond demonstrating that a technology is feasible, usable, or novel. The field now needs studies that clarify how these tools work, for whom they are beneficial, under what conditions they may cause harm, and how they can be ethically integrated into care. We call for research that is transparent about the technologies being studied, grounded in meaningful clinical questions, attentive to safety, and designed to produce knowledge that remains useful as specific products and models change.
13 July 2026
Read appraisal →JMIR mental health
From Alliance to Nexus: Rethinking Digital Therapeutic Relationships
In traditional human psychotherapy, the therapeutic alliance (TA) is regarded as a fundamental factor that describes the client-therapist relationship, mainly due to strong evidence demonstrating its impact on treatment outcomes regardless of theoretical orientation. More recently, advances in artificial intelligence (AI) and other technologies have led to the emergence of the concept of digital TA, used to characterize the relationship between clients and AI-based therapeutic systems. This approach replicates human dynamics but overlooks key differences between human therapists and digital agents. Prematurely translating the concept of TA into the digital context fails to address issues such as the sycophantic tendencies of current systems and the inherent limitations of algorithmic interaction. We propose the digital therapeutic nexus, a framework that recognizes these differences and provides a set of structured criteria for categorizing digital interactions into 3 progressive levels. This Viewpoint argues that only at the highest level can parallels be drawn to the human TA and stratifies the main risks associated with each nexus level. Transitioning from the concept of alliance to that of a nexus offers a more precise conceptual basis for describing and evaluating digital therapeutic relationships, with implications for research, design, and the ethical development of AI-based mental health interventions.
3 July 2026
Read appraisal →The Journal of international medical research
Examining the state of telehealth for mental health and substance use care after the coronavirus disease 2019 pandemic: An integrative review.
ObjectiveThe objective of this integrative review was to synthesize literature and provide implications for clinical practice on telehealth use among patients with serious mental illness and substance use disorders following the coronavirus disease 2019 pandemic.MethodsAn integrative review guided by Socio-Technical Systems Theory was applied. The PubMed, Cumulative Index to Nursing and Allied Health Literature, PsycINFO, Medline, Academic Search Complete, and Gale Health and Wellness databases were searched for publications from 1 January 2019 to 1 December 2024. Articles selected according to the established inclusion and exclusion criteria were evaluated using a rapid critical appraisal checklist developed by Fineout-Overholt and Melnyk.ResultsAmong the 172 articles reviewed, 16 peer-reviewed and 2 government publications were included. Four themes were identified: (a) treatment adherence; (b) satisfaction reported by patients and providers; (c) telehealth policy developments; and (d) access to services. Telehealth supported continuity of care, improved satisfaction, and improved access. Technological and financial barriers restricted equitable access. Policy changes enabled broader adoption; however, regulatory approaches varied across jurisdictions.ConclusionTelehealth remains an integral method for delivering mental health and substance use care following the coronavirus disease 2019 pandemic. Greater focus is needed on long-term effectiveness and limitations of telehealth.
3 July 2026
Read appraisal →Child and adolescent psychiatric clinics of North America
Technology-Enabled Crisis Care for Youth: Bridging the Gap
The article discusses technological advancements in mental health care for youth in crisis, addressing workforce shortages and enhancing care delivery. Technologies like remote patient monitoring, telehealth, mobile health applications, virtual reality therapy, and artificial intelligence improve symptom tracking, communication, and treatment accessibility. Clinical decision support systems and therapy chatbots enhance crisis assessment and management. Various settings employ telepsychiatry and extend reach, while digital therapeutics and monitoring ensure ongoing support. Challenges include regulatory compliance, data privacy, and technological limitations. Future directions emphasize interoperability, safeguards for new and adapting technologies, patient-centered care, and integrated digital health systems.
3 July 2026
Read appraisal →Journal of the American Medical Informatics Association : JAMIA
TRUST: an large language model-based dialogue system for trauma understanding and structured assessments
OBJECTIVES: While large language models (LLMs) have been widely used to assist clinicians and support patients, no existing work has explored dialogue systems for standard diagnostic interviews and assessments. This study aims to bridge the gap in mental healthcare accessibility by developing an LLM-powered dialogue system that replicates clinician behavior. MATERIALS AND METHODS: We introduce TRUST, a framework of cooperative LLM modules capable of conducting formal diagnostic interviews and assessments for post-traumatic stress disorder (PTSD) following the Clinician-Administered PTSD Scale for DSM-5 (CAPS-5). To guide the generation of appropriate clinical responses, we propose a Dialogue Acts schema specifically designed for clinical interviews. Additionally, we develop a patient simulation approach based on real-life interview transcripts to replace time-consuming and costly manual testing by clinicians. RESULTS: A comprehensive set of evaluation metrics is designed to assess the dialogue system from both the agent and patient simulation perspectives. Expert evaluations by conversation and clinical specialists show that TRUST performs comparably to real-life clinical interviews. DISCUSSION: Our system performs with clinical quality approaching that of human clinicians, with room for future enhancements in communication styles and response appropriateness. CONCLUSIONS: Our TRUST framework shows its potential to facilitate mental healthcare availability.
2 July 2026
Read appraisal →JMIR mental health
Coproduction Without Youth? Closing the Participation Gap in Digital Mental Health Research
Young people are among the most intensive users of digital and generative artificial intelligence (GenAI)-enabled mental health tools, yet they remain underrepresented in the research and design processes that shape these technologies. Although participatory approaches such as co-design and patient and public involvement are widely endorsed as best practices, youth involvement in digital youth mental health (DYMH) research is often inconsistent, superficial, or limited to late-stage consultation. This participation gap risks producing interventions that are misaligned with young people's lived experiences, priorities, and vulnerabilities, particularly in the context of rapidly evolving and scalable GenAI systems. This Viewpoint aims to reexamine the underlying drivers of the participation gap in DYMH research; clarify how participation is conceptualized and implemented across disciplines; and propose concrete, actionable recommendations to support more meaningful and consistent youth involvement across the research life cycle. We draw on interdisciplinary literature from digital mental health, human-computer interaction, child-computer interaction, and health research policy. Our Viewpoint integrates conceptual frameworks (eg, Lundy's model of participation), existing reviews of co-design practices, and emerging evidence on GenAI in mental health. We adopt a life cycle-oriented perspective to examine how youth participation is distributed across stages of research and development, including problem formulation, design, implementation, and evaluation. We identify 3 interrelated drivers of the participation gap. First, conceptual and linguistic fragmentation obscures what participation entails in practice, with terms such as co-design, participatory design, user-centered design, and patient and public involvement used inconsistently across disciplines. Second, youth involvement is uneven across the research life cycle, with participation often concentrated in early ideation or usability testing but largely absent from upstream decision-making and downstream evaluation. Third, institutional barriers-including ethics review processes, consent requirements, funding constraints, and adult-centric research norms-systematically limit meaningful youth partnership. These challenges are amplified in the context of GenAI, where opaque "black box" systems, simulated therapeutic interactions, and rapid deployment cycles introduce distinct risks if youth perspectives are not integrated. We propose a set of minimum expectations to address these gaps, including explicit specification of participatory models, life cycle mapping of youth involvement, reporting of youth influence on decisions, dedicated funding for participation, proportional ethics frameworks, and mechanisms for youth-informed governance of GenAI systems. Closing the participation gap in DYMH research is both an ethical imperative and a practical necessity. Moving beyond aspirational commitments requires embedding youth participation as a standard, resourced, and accountable component of research, design, and governance. In the context of rapidly evolving digital and GenAI technologies, failure to do so risks producing interventions that are scalable but not safe, credible, or responsive to the needs of young people.
27 June 2026
Read appraisal →Current psychiatry reports
Digital Tools to Support Mental Health in Later Life: Scoping Review of Systematic Reviews
PURPOSE OF REVIEW: This scoping review synthesises existing evidence from systematic reviews on the effectiveness and implementation of digital mental health interventions among community-dwelling older adults. RECENT FINDINGS: Twenty-one systematic reviews were included. Results showed that a range of digital tools demonstrate potential to improve common mental health and psychosocial symptoms among older adults, with most evidence concentrating on digital tools to improve depressive symptoms. However, reviews' findings were frequently mixed and accompanied with cautions that primary evidence under-reported key elements such as theoretical underpinnings, intervention design process, participant demographics, intervention acceptability and usability, participant retention, adverse events, and long-term outcomes. More rigorous research and reporting are needed to understand the mechanisms underpinning effective digital mental health interventions for older adults and how they might mitigate the age-related digital divide in mental health services.
19 June 2026
Read appraisal →Journal of affective disorders
Emotion regulation-targeted interventions initiated during hospitalization for suicidal crisis: a systematic review and exploratory meta-analysis
INTRODUCTION: Suicide is a leading cause of premature death, with risk peaking around psychiatric hospitalization. Emotion dysregulation (ED) is recognized as a key factor contributing to suicidal ideation and behavior across psychiatric diagnoses. The efficacy of interventions that target ED for suicidality reduction remains unclear, so we aimed to assess these interventions in psychiatric inpatients. METHODS: We conducted a PRISMA-compliant, PROSPERO-registered (CRD420251140949) systematic review and meta-analysis of randomized and non-randomized trials evaluating interventions targeting emotion regulation (ER) for psychiatric inpatients with suicidal ideation and/or behavior. Searches covered PubMed, Embase, and PsycINFO to September 18, 2025. Standardized mean differences (Hedges' g) were pooled under random-effects models and heterogeneity was assessed (Q, I2, τ2). Exploratory meta-regressions examined age, sex, and study quality; small-study effects were explored with funnel plots. RESULTS: Twelve studies met inclusion (n = 1708), spanning dialectical behavior therapy (DBT), mindfulness-based interventions, acceptance and commitment therapy (ACT), and other ER-related protocols. Across modalities, feasibility and acceptability were high and interventions consistently improved suicide-related outcomes in transdiagnostic adolescents and adult populations. Suicide attempts and ideation met outcome criteria for exploratory meta-analyses, and, for both, ER-targeted interventions outperformed usual care, despite heterogeneity and small samples. Exploratory meta-regressions were non-significant; funnel plots did not suggest marked publication bias, though power was limited. CONCLUSIONS: ER-targeted interventions delivered during psychiatric hospitalization are feasible and show promising benefits on suicide-related outcomes. Given heterogeneity and limited sample sizes, larger, well-powered randomized trials using standardized suicidality endpoints are needed to establish efficacy, refine inpatient protocols, and inform acute care pathways.
16 June 2026
Read appraisal →JMIR aging
Facilitators and Barriers to Digital Self-Management in Older Adults With Depression: COM-B and Theoretical Domain Framework Qualitative Study
BACKGROUND: Depression in older adults presents unique challenges in self-management. Digital tools, such as mobile health (mHealth) apps, have the potential to support this population. This study explored the facilitators and barriers to digital self-management in older adults with depression to inform the design of effective mHealth apps. OBJECTIVE: This study aims to explore the facilitators and barriers to digital self-management in older patients with depression with the aim of informing the design and development of mHealth apps for older adults. METHODS: A purposive sampling method was used to recruit 25 older patients with depression from July to September 2024. Semistructured interviews were conducted to capture real-life experiences. Directed content analysis ensured objective and accurate data interpretation, and the Capability, Opportunity, Motivation, and Behavior (COM-B) model and the Theoretical Domains Framework were applied to identify facilitators and barriers related to behavior. RESULTS: Six themes were identified based on the COM-B model and the Theoretical Domains Framework: perception of illness and accumulation of personal experience; dual challenges of cognitive abilities and physical limitations; integration of digital technologies and acceptance differences; social influences and access to and utilization of support resources; environmental constraints and accommodations; and intertwined influences of beliefs, emotions, and motivation. A total of 13 barriers and 11 facilitators were identified. CONCLUSIONS: Digital self-management in older adults with depression is complex and influenced by multiple interrelated factors. Effective mHealth apps must integrate the cognitive, emotional, and social contexts of patients to provide user-friendly, personalized solutions.
11 Apr 2026
Read appraisal →Psychological medicine
Interventions to prevent antipsychotic-induced weight gain and metabolic complications in individuals with a first-episode psychosis and minimal antipsychotic exposure: a systematic review and meta-analysis
BACKGROUND: Rapid weight gain commonly occurs following the onset of first-episode psychosis (FEP), leading to cardiometabolic disease. Most weight gain in FEP occurs in the first 3 months of treatment, offering a critical window for prevention. Despite this, most studies aiming to prevent antipsychotic-induced weight gain include people with chronic illness or people who have had lengthy exposure to antipsychotic medication. We aimed to synthesize and analyze the literature on interventions aimed at preventing antipsychotic-induced weight gain. METHODS: We conducted a systematic review in PsycInfo, MEDLINE, CINAHL, and EMBASE of studies that examined the effectiveness of interventions in preventing antipsychotic-induced weight gain in FEP. We examined their effect on weight gain and a range of cardiometabolic markers. RESULTS: We screened 2,092 articles, 13 of which were eligible. Behavioral interventions, all three of which consisted of a multidisciplinary team approach, resulted in a mean of 3.05 kg less weight gain than treatment-as-usual (95% CI 1.36 kg to 4.73 kg). Pharmacological interventions displayed marked clinical and statistical heterogeneity, with each of the seven trials in adults using a different pharmacological intervention. Few studies collected comprehensive data on metabolic health. Only two pharmacological studies, and five studies in total, have been published since 2010. CONCLUSIONS: Despite the importance of preventing weight gain in FEP, there have been few recent studies investigating this topic. Our results indicate that multidisciplinary team interventions are effective in preventing weight gain in FEP and should be offered to all patients.
11 Apr 2026
Read appraisal →