{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T10:42:55Z","timestamp":1791715375345,"version":"4.3.4"},"reference-count":109,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR AI"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>General-purpose large language models (LLMs) are increasingly being tested in mental health care, where language is central to assessment, diagnosis, risk evaluation, therapeutic interaction, monitoring, and patient education. However, their clinical usefulness, safety, and readiness for implementation remain uncertain. Existing reviews have largely been descriptive or scoping in nature, and broad health care reviews have not examined in detail the distinctive risks and applications of LLMs in mental health care.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>We aim to systematically review empirical evidence on the use of general-purpose LLMs in mental health care; characterize the clinical tasks, study designs, models, outcomes, and methodological quality of the evidence; and synthesize findings across clinically meaningful task domains, including quantitative synthesis where sufficiently comparable studies were available.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We followed PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) and searched PubMed, Embase, ACM Digital Library, IEEE Xplore, and Google Scholar from November 2022 to March 2026. Eligible studies reported quantitative data evaluating general-purpose LLMs for direct mental health care tasks. Methodological quality was assessed using the Mixed Methods Appraisal Tool and certainty of evidence using GRADE (Grading of Recommendations, Assessment, Development, and Evaluation) domains. Findings were narratively synthesized, and random-effects meta-analyses were conducted on studies that tested LLMs on screening and diagnosis by ChatGPT-4 (OpenAI), ChatGPT-3.5 (OpenAI), and GPT-3 (OpenAI) models for mental health outcomes that reported on specificity and sensitivity. Hartung-Knapp adjustments were applied, and prediction intervals (PIs) estimated.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We included 66 studies, comprising 37 vignette or simulation studies, 22 retrospective studies, and 7 prospective studies. Applications included screening and diagnosis (n=29), clinical decision support (n=14), treatment support (n=10), documentation and monitoring (n=6), patient education (n=4), and patient engagement (n=3). In screening and diagnosis, meta-analysis of 8 studies found that GPT-4 had the higher pooled sensitivity (0.83, 95% CI 0.38\u20100.97; 95% PI 0.02\u20101.00) than GPT-3.5 (0.70, 95% CI 0.13\u20100.97; 95% PI 0.00\u20101.00) and GPT-3 (0.61, 95% CI 0.33\u20100.82; 95% PI 0.10\u20100.96). However, GPT-4 specificity was lower at 0.77 (95% CI 0.52\u20100.91; 95% PI 0.10\u20100.99). Narrative synthesis suggested that LLMs performed most consistently in structured and linguistically explicit tasks. Certainty of evidence was generally low across domains, although documentation and monitoring reached moderate certainty. Major limitations included indirectness from vignette-based designs, uncertain representativeness, inconsistent outcome reporting, and sparse prospective real-world evaluation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>General-purpose LLMs show promise for selected mental health care applications. However, current evidence remains too heterogeneous, indirect, and uncertain to support routine unsupervised use, particularly for diagnosis, risk assessment, crisis response, or therapeutic interaction. Broad accessibility should not be mistaken for clinical readiness. Future studies should move beyond simulations and retrospective evaluations toward prospective, real-world research assessing safety, reliability, equity, acceptability, clinical outcomes, and implementation in diverse mental health care settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/87730","type":"journal-article","created":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T17:22:55Z","timestamp":1788196975000},"page":"e87730-e87730","source":"Crossref","is-referenced-by-count":2,"title":["Generative Large Language Models in Mental Health Care Settings: Systematic Review and Meta-Analysis"],"prefix":"10.2196","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5816-2959","authenticated-orcid":false,"given":"Janni","family":"Leung","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2831-0150","authenticated-orcid":false,"given":"Benjamin","family":"Johnson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1505-3224","authenticated-orcid":false,"given":"Kelsey","family":"McRae","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7858-8160","authenticated-orcid":false,"given":"Stephanie","family":"Fong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6586-0266","authenticated-orcid":false,"given":"Paula Cardona","family":"Gonzalez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3605-0742","authenticated-orcid":false,"given":"Caitlin","family":"McClure-Thomas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3939-9499","authenticated-orcid":false,"given":"Tianze","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2007-0397","authenticated-orcid":false,"given":"Naomi","family":"Kern","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1887-6539","authenticated-orcid":false,"given":"Yuen Ming","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4044-6756","authenticated-orcid":false,"given":"Richard","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7569-1948","authenticated-orcid":false,"given":"Gary Chung Kai","family":"Chan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,8,31]]},"reference":[{"issue":"2","key":"R1","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/S2215-0366(21)00395-3","article-title":"Global, regional, and national burden of 12 mental disorders in 204 countries and territories, 1990\u20132019: a systematic analysis for the Global Burden of Disease Study 2019","volume":"9","author":"GBD 2019 Mental Disorders Collaborators","journal-title":"Lancet Psychiatry"},{"issue":"9803","key":"R2","doi-asserted-by":"publisher","first-page":"1654","DOI":"10.1016\/S0140-6736(11)61093-3","article-title":"Human resources for mental health care: current situation and strategies for action","volume":"378","author":"Kakuma","journal-title":"Lancet"},{"issue":"8","key":"R3","doi-asserted-by":"publisher","first-page":"1485","DOI":"10.4103\/jfmpc.jfmpc_391_22","article-title":"Barriers to mental health treatment in primary care practice in low- and middle-income countries in a post-COVID era: a systematic review","volume":"12","author":"Rameez","journal-title":"J Family Med Prim Care"},{"issue":"1","key":"R4","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1001\/jamapediatrics.2022.4419","article-title":"Association of youth suicides and county-level mental health professional shortage areas in the US","volume":"177","author":"Hoffmann","journal-title":"JAMA Pediatr"},{"issue":"4","key":"R5","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1001\/jama.2024.21700","article-title":"Testing and evaluation of health care applications of large language models: a systematic review","volume":"333","author":"Bedi","journal-title":"JAMA"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.2196\/22769","article-title":"Applications and concerns of ChatGPT and other conversational large language models in health care: systematic review","volume":"26","author":"Wang","journal-title":"J Med Internet Res"},{"key":"R7","unstructured":"First MB Tasman A . Clinical Guide to the Diagnosis and Treatment of Mental Disorders. John Wiley & Sons; 2010. ISBN: 978-0-470-74520-5"},{"issue":"9","key":"R8","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1001\/archpsyc.1986.01800090017003","article-title":"A comparative study of manic vs schizophrenic speech disorganization","volume":"43","author":"Hoffman","journal-title":"Arch Gen Psychiatry"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01611-4","article-title":"A scoping review of large language models for generative tasks in mental health care","volume":"8","author":"Hua","journal-title":"npj Digital Med"},{"issue":"1","key":"R10","doi-asserted-by":"publisher","DOI":"10.2196\/70014","article-title":"Evaluating generative AI in mental health: systematic review of capabilities and limitations","volume":"12","author":"Wang","journal-title":"JMIR Ment Health"},{"issue":"1","key":"R11","doi-asserted-by":"publisher","DOI":"10.2196\/57400","article-title":"Large language models for mental health applications: systematic review","volume":"11","author":"Guo","journal-title":"JMIR Ment Health"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.2196\/70610","article-title":"The application and ethical implication of generative AI in mental health: systematic review","volume":"12","author":"Wang","journal-title":"JMIR Ment Health"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","DOI":"10.2196\/53672","article-title":"Debate and dilemmas regarding generative AI in mental health care: scoping review","volume":"13","author":"Xian","journal-title":"Interact J Med Res"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.1017\/neu.2024.50","article-title":"Use of generative artificial intelligence (AI) in psychiatry and mental health care: a systematic review","volume":"37","author":"Kolding","journal-title":"Acta Neuropsychiatr"},{"issue":"1","key":"R15","doi-asserted-by":"publisher","DOI":"10.2196\/69284","article-title":"The applications of large language models in mental health: scoping review","volume":"27","author":"Jin","journal-title":"J Med Internet Res"},{"key":"R16","unstructured":"Chung NC Dyer G Brocki L . Challenges of large language models for mental health counseling. arXiv. Preprint posted online on Nov 23, 2023. [doi: 10.48550\/arXiv.2311.13857]"},{"key":"R17","unstructured":"Zhang D Li W Song K et al. Memory in large language models: mechanisms, evaluation and evolution. arXiv. Preprint posted online on Sep 23, 2025. [doi: 10.48550\/arXiv.2509.18868]"},{"key":"R18","unstructured":"OpenAI. OpenAI o1 system card. arXiv. Preprint posted online on Apr 30, 2026. [doi: 10.48550\/arXiv.2412.16720]"},{"issue":"3","key":"R19","doi-asserted-by":"publisher","first-page":"1152","DOI":"10.1038\/s41591-026-04229-5","article-title":"LLM-assisted systematic review of large language models in clinical medicine","volume":"32","author":"Chen","journal-title":"Nat Med"},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.n71","article-title":"The PRISMA 2020 statement: an updated guideline for reporting systematic reviews","volume":"372","author":"Page","journal-title":"BMJ"},{"issue":"2","key":"R21","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1017\/rsm.2025.1","article-title":"A comprehensive systematic review dataset is a rich resource for training and evaluation of AI systems for title and abstract screening","volume":"16","author":"Chan","journal-title":"Res Synth Methods"},{"issue":"7","key":"R22","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2025.14040","article-title":"Generative artificial intelligence with youth codesign to create vaping awareness advertisements","volume":"8","author":"Leung","journal-title":"JAMA Netw Open"},{"issue":"7","key":"R23","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2025.14047","article-title":"Generative artificial intelligence for tobacco health promotion","volume":"8","author":"Erinoso","journal-title":"JAMA Netw Open"},{"issue":"4","key":"R24","doi-asserted-by":"publisher","first-page":"285","DOI":"10.3233\/EFI-180221","article-title":"The Mixed Methods Appraisal Tool (MMAT) version 2018 for information professionals and researchers","volume":"34","author":"Hong","journal-title":"EFI"},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2014.09.021","article-title":"Performance measures of the bivariate random effects model for meta-analyses of diagnostic accuracy","volume":"83","author":"Diaz","journal-title":"Comput Stat Data Anal"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.d4002","article-title":"Recommendations for examining and interpreting funnel plot asymmetry in meta-analyses of randomised controlled trials","volume":"343","author":"Sterne","journal-title":"BMJ"},{"issue":"8","key":"R27","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1016\/j.jclinepi.2015.03.017","article-title":"Small studies are more heterogeneous than large ones: a meta-meta-analysis","volume":"68","author":"IntHout","journal-title":"J Clin Epidemiol"},{"issue":"1","key":"R28","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1002\/jrsm.1230","article-title":"Basics of meta-analysis: I is not an absolute measure of heterogeneity","volume":"8","author":"Borenstein","journal-title":"Res Synth Methods"},{"key":"R29","doi-asserted-by":"crossref","unstructured":"Sch\u00fcnemann HJ Higgins JPT Vist GE et al. Completing \u2018summary of findings\u2019 tables and grading the certainty of the evidence. In: Cochrane Handbook for Systematic Reviews of Interventions. Cochrane; 2019:375-402. [doi: 10.1002\/9781119536604.ch14]","DOI":"10.1002\/9781119536604.ch14"},{"issue":"1","key":"R30","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-54242-2","article-title":"AI and narrative embeddings detect PTSD following childbirth via birth stories","volume":"14","author":"Bartal","journal-title":"Sci Rep"},{"key":"R31","doi-asserted-by":"crossref","unstructured":"Danner M Hadzic B Gerhardt S et al. Advancing mental health diagnostics: GPT-based method for depression detection. Presented at: 2023 62nd Annual Conference of the Society of Instrument and Control Engineers (SICE); Sep 6-9, 2023; Tsu, Japan. [doi: 10.23919\/SICE59929.2023.10354236]","DOI":"10.23919\/SICE59929.2023.10354236"},{"key":"R32","doi-asserted-by":"crossref","unstructured":"Hu C Li W Ruan M et al. Exploiting ChatGPT for diagnosing autism-associated language disorders and identifying distinct features. Research Square. Preprint posted online on May 20, 2024. [doi: 10.21203\/rs.3.rs-4359726\/v1] [Medline: 38826194]","DOI":"10.21203\/rs.3.rs-4359726\/v1"},{"key":"R33","doi-asserted-by":"crossref","unstructured":"Lorenzoni G Velmovitsky PE Alencar P Cowan D . GPT-4 on clinic depression assessment: an LLM-based pilot study. Presented at: 2024 IEEE International Conference on Big Data (BigData); Dec 15-18, 2024:5043-5049; Washington, DC. [doi: 10.1109\/BigData62323.2024.10825184]","DOI":"10.1109\/BigData62323.2024.10825184"},{"key":"R34","doi-asserted-by":"crossref","unstructured":"Kaliosis P Ganesan AV Kjell ONE et al. A systematic evaluation of large language models for PTSD severity estimation: the role of contextual knowledge and modeling strategies. Research Square. Preprint posted online on Dec 24, 2025. [doi: 10.21203\/rs.3.rs-8376581\/v1]","DOI":"10.21203\/rs.3.rs-8376581\/v1"},{"issue":"7","key":"R35","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000943","article-title":"Leveraging large language models for automated depression screening","volume":"4","author":"Teferra","journal-title":"PLOS Digital Health"},{"issue":"2","key":"R36","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0001205","article-title":"Interpretable depression assessment using a large language model","volume":"5","author":"Lee","journal-title":"PLOS Digital Health"},{"key":"R37","doi-asserted-by":"publisher","DOI":"10.2196\/54617","article-title":"Using large language models to detect depression from user-generated diary text data as a novel approach in digital mental health screening: instrument validation study","volume":"26","author":"Shin","journal-title":"J Med Internet Res"},{"key":"R38","volume":"2024","author":"Bhagat","journal-title":"AMIA Jt Summits Transl Sci Proc"},{"key":"R39","doi-asserted-by":"publisher","DOI":"10.1016\/j.xjmad.2025.100109","article-title":"Applying large language models to stratify suicide risk using narrative clinical notes","volume":"10","author":"McCoy","journal-title":"J Mood Anxiety Disord"},{"issue":"1","key":"R40","doi-asserted-by":"publisher","DOI":"10.1136\/bmjment-2025-301654","article-title":"Reasoning language models for more transparent prediction of suicide risk","volume":"28","author":"McCoy","journal-title":"BMJ Ment Health"},{"issue":"5","key":"R41","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2025.11922","article-title":"Large language models and text embeddings for detecting depression and suicide in patient narratives","volume":"8","author":"Lho","journal-title":"JAMA Netw Open"},{"key":"R42","doi-asserted-by":"publisher","DOI":"10.2196\/77699","article-title":"Large language models for psychiatric diagnosis based on multicenter real-world clinical records: comparative study","volume":"14","author":"Sun","journal-title":"JMIR Med Inf"},{"key":"R43","doi-asserted-by":"publisher","DOI":"10.1177\/10731911251406405","article-title":"Detecting suicidal ideation in adolescence using self-reported emotional and behavioral patterns: comparing machine learning and large language model predictions","volume":"0","author":"Marengo","journal-title":"Assessment"},{"issue":"39","key":"R44","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2321321121","article-title":"Language sentiment predicts changes in depressive symptoms","volume":"121","author":"Hur","journal-title":"Proc Natl Acad Sci U S A"},{"key":"R45","doi-asserted-by":"publisher","DOI":"10.2196\/78401","article-title":"Evaluating the efficacy of AI-based interactive assessments using large language models for depression screening: development and usability study","volume":"10","author":"Jin","journal-title":"JMIR Form Res"},{"key":"R46","doi-asserted-by":"publisher","DOI":"10.1177\/20552076231170499","article-title":"Testing domain knowledge and risk of bias of a large-scale general artificial intelligence model in mental health","volume":"9","author":"Heinz","journal-title":"Digital Health"},{"key":"R47","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajp.2024.104168","article-title":"Diagnostic accuracy of large language models in psychiatry","volume":"100","author":"Gargari","journal-title":"Asian J Psychiatr"},{"key":"R48","doi-asserted-by":"crossref","unstructured":"Sarma KV Hanss KE Halls AJM Becker DF Glowinski AL Krystal A . Simulated reasoning and self-verification in generalist large language models for psychiatric diagnostic performance: cross-sectional study. medRxiv. Preprint posted online on Sep 9, 2025. [doi: 10.1101\/2025.09.05.25335196] [Medline: 40963745]","DOI":"10.1101\/2025.09.05.25335196"},{"issue":"12","key":"R49","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.50729","article-title":"Safety of large language models in addressing depression","volume":"15","author":"Heston","journal-title":"Cureus"},{"key":"R50","doi-asserted-by":"publisher","DOI":"10.2196\/51232","article-title":"Suicide risk assessments through the eyes of ChatGPT-3.5 versus ChatGPT-4: vignette study","volume":"10","author":"Levkovich","journal-title":"JMIR Ment Health"},{"key":"R51","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2025.1544951","article-title":"Effectiveness of generative AI-large language models\u2019 recognition of veteran suicide risk: a comparison with human mental health providers using a risk stratification model","volume":"16","author":"Lauderdale","journal-title":"Front Psychiatry"},{"key":"R52","doi-asserted-by":"crossref","unstructured":"Zeng Q Li X Wang S Liu K . Adversarial evaluation algorithm for detecting extreme behaviors of LLMs in psychological counseling scenarios. Presented at: 2025 2nd International Conference on Algorithms, Software Engineering and Network Security (ASENS); Mar 21-23, 2025:412-415; Guangzhou, China. [doi: 10.1109\/ASENS64990.2025.11011189]","DOI":"10.1109\/ASENS64990.2025.11011189"},{"issue":"4","key":"R53","doi-asserted-by":"publisher","DOI":"10.1136\/fmch-2023-002391","article-title":"Identifying depression and its determinants upon initiating treatment: ChatGPT versus primary care physicians","volume":"11","author":"Levkovich","journal-title":"Fam Med Community Health"},{"key":"R54","doi-asserted-by":"publisher","DOI":"10.1177\/20552076241294182","article-title":"Large language models outperform general practitioners in identifying complex cases of childhood anxiety","volume":"10","author":"Levkovich","journal-title":"Digital Health"},{"issue":"1","key":"R55","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01181-x","article-title":"Large language models outperform mental and medical health care professionals in identifying obsessive-compulsive disorder","volume":"7","author":"Kim","journal-title":"npj Digital Med"},{"key":"R56","doi-asserted-by":"publisher","DOI":"10.1016\/j.chbah.2025.100212","article-title":"Harnessing large language models for identification and treatment of obsessive-compulsive disorder","volume":"6","author":"Levkovich","journal-title":"Comput Hum Behav: Artif Hum"},{"issue":"1","key":"R57","doi-asserted-by":"publisher","DOI":"10.3390\/ejihpe15010009","article-title":"Evaluating diagnostic accuracy and treatment efficacy in mental health: a comparative analysis of large language model tools and mental health professionals","volume":"15","author":"Levkovich","journal-title":"Eur J Invest Health Psychol Educ"},{"key":"R58","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2025.1599900","article-title":"A step toward the future? Evaluating GenAI QPR simulation training for mental health gatekeepers","volume":"12","author":"Levkovich","journal-title":"Front Med (Lausanne)"},{"key":"R59","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajp.2023.103770","article-title":"Appraising the performance of ChatGPT in psychiatry using 100 clinical case vignettes","volume":"89","author":"D\u2019Souza","journal-title":"Asian J Psychiatr"},{"key":"R60","doi-asserted-by":"crossref","unstructured":"Jin KW Rostam-Abadi Y Chaudhary P et al. Evaluating diagnostic accuracy and clinical reasoning of multiple large language models in psychiatry. medRxiv. Preprint posted online on Feb 11, 2026. [doi: 10.64898\/2026.02.03.26345402] [Medline: 41728283]","DOI":"10.64898\/2026.02.03.26345402"},{"key":"R61","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2025.116844","article-title":"Integrating expert knowledge into large language models improves performance for psychiatric reasoning and diagnosis","volume":"355","author":"Sarma","journal-title":"Psychiatry Res"},{"key":"R62","doi-asserted-by":"crossref","unstructured":"Zhang M Yang X Zhang X et al. CBT-bench: evaluating large language models on assisting cognitive behavior therapy. Presented at: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics; Apr 29 to May 4, 2025; Albuquerque, New Mexico. [doi: 10.18653\/v1\/2025.naacl-long.196]","DOI":"10.18653\/v1\/2025.naacl-long.196"},{"key":"R63","doi-asserted-by":"crossref","unstructured":"Aleem M Zahoor I Naseem M . Towards culturally adaptive large language models in mental health: using ChatGPT as a case study. Presented at: CSCW Companion \u201924: Companion Publication of the 2024 Conference on Computer-Supported Cooperative Work and Social Computing; Nov 9-13, 2024:240-247; San Jose Costa Rica. [doi: 10.1145\/3678884.3681858]","DOI":"10.1145\/3678884.3681858"},{"issue":"7","key":"R64","doi-asserted-by":"publisher","first-page":"2205","DOI":"10.1108\/IMDS-05-2025-0609","article-title":"Understanding medical information and emotional support needs in mental health questions with large language models","volume":"126","author":"Liu","journal-title":"Ind Manage Data Syst"},{"key":"R65","doi-asserted-by":"publisher","DOI":"10.2196\/53043","article-title":"Comparing the perspectives of generative AI, mental health experts, and the general public on schizophrenia recovery: case vignette study","volume":"11","author":"Elyoseph","journal-title":"JMIR Ment Health"},{"key":"R66","doi-asserted-by":"crossref","unstructured":"Perlis RH . Research letter: application of GPT-4 to select next-step antidepressant treatment in major depression. medRxiv. Preprint posted online on Apr 18, 2023. [doi: 10.1101\/2023.04.14.23288595] [Medline: 37131648]","DOI":"10.1101\/2023.04.14.23288595"},{"issue":"9","key":"R67","doi-asserted-by":"publisher","first-page":"1412","DOI":"10.1038\/s41386-024-01841-2","article-title":"Clinical decision support for bipolar depression using large language models","volume":"49","author":"Perlis","journal-title":"Neuropsychopharmacology"},{"key":"R68","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.110065","article-title":"An adaptive language model-based intelligent medication assistant for the decision support of antidepressant prescriptions","volume":"190","author":"Silva","journal-title":"Comput Biol Med"},{"issue":"11","key":"R69","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1176\/appi.ps.20250086","article-title":"Evaluation of alignment between large language models and expert clinicians in suicide risk assessment","volume":"76","author":"McBain","journal-title":"Psychiatr Serv"},{"issue":"1","key":"R70","doi-asserted-by":"publisher","DOI":"10.1080\/29974100.2025.2545258","article-title":"AI meets psychology: an exploratory study of large language models\u2019 competence in psychotherapy contexts","volume":"1","author":"Tan","journal-title":"J Psychol AI"},{"issue":"3","key":"R71","doi-asserted-by":"publisher","DOI":"10.1002\/pcn5.70159","article-title":"Potential of ChatGPT in youth mental health emergency triage: comparative analysis with clinicians","volume":"4","author":"Thotapalli","journal-title":"PCN Rep"},{"issue":"1","key":"R72","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1176\/appi.psychotherapy.20240070","article-title":"Evaluating the efficacy of ChatGPT-3.5 versus human-delivered text-based cognitive-behavioral therapy: a comparative pilot study","volume":"79","author":"Acevedo","journal-title":"Am J Psychother"},{"issue":"3","key":"R73","doi-asserted-by":"publisher","first-page":"1111","DOI":"10.1177\/02601060241281906","article-title":"ChatGPT as a psychotherapist for anxiety disorders: an empirical study with anxiety patients","volume":"31","author":"Alanzi","journal-title":"Nutr Health"},{"key":"R74","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2025.1709743","article-title":"Validating GenAI feedback in suicide prevention training: a mixed-methods study of QPR skill assessment","volume":"12","author":"Haber","journal-title":"Front Med (Lausanne)"},{"key":"R75","doi-asserted-by":"publisher","DOI":"10.2196\/52500","article-title":"Can large language models replace therapists? Evaluating performance at simple cognitive behavioral therapy tasks","volume":"3","author":"Hodson","journal-title":"JMIR AI"},{"key":"R76","doi-asserted-by":"crossref","unstructured":"Jain A Sandhu R Singh G Rakhra M . The role of AI counselling in journaling for mental health improvement. Presented at: 2024 International Conference on Electrical Electronics and Computing Technologies (ICEECT); Aug 29-31, 2024:1-6; Greater Noida, India. [doi: 10.1109\/ICEECT61758.2024.10739128]","DOI":"10.1109\/ICEECT61758.2024.10739128"},{"key":"R77","doi-asserted-by":"publisher","DOI":"10.2196\/78138","article-title":"Comparing human and AI therapists in behavioral activation for depression: cross-sectional questionnaire study","volume":"9","author":"Napiwotzki","journal-title":"JMIR Form Res"},{"key":"R78","doi-asserted-by":"crossref","unstructured":"Moell B . Comparing the efficacy of GPT-4 and Chat-GPT in mental health care: a blind assessment of large language models for psychological support (preprint). JMIR Ment Health. Preprint posted online on Mar 20, 2023. [doi: 10.2196\/preprints.47439] [Medline: 37114093]","DOI":"10.2196\/preprints.47439"},{"key":"R79","doi-asserted-by":"crossref","unstructured":"Shen H Li Z Yang M et al. Are large language models possible to conduct cognitive behavioral therapy? Presented at: 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); Dec 3-6, 2024:3695-3700; Lisbon, Portugal. [doi: 10.1109\/BIBM62325.2024.10821773]","DOI":"10.1109\/BIBM62325.2024.10821773"},{"key":"R80","doi-asserted-by":"publisher","DOI":"10.2196\/57306","article-title":"Exploring the efficacy of large language models in summarizing mental health counseling sessions: benchmark study","volume":"11","author":"Adhikary","journal-title":"JMIR Ment Health"},{"key":"R81","doi-asserted-by":"publisher","DOI":"10.2196\/65454","article-title":"Classifying unstructured text in electronic health records for mental health prediction models: large language model evaluation study","volume":"13","author":"Cardamone","journal-title":"JMIR Med Inf"},{"key":"R82","doi-asserted-by":"crossref","unstructured":"Donnelly HK Brown GK Green KL et al. Exploring the potential of large language models for automated safety plan scoring in outpatient mental health settings (preprint). JMIR Ment Health. Preprint posted online on Sep 3, 2025. [doi: 10.2196\/preprints.79010] [Medline: 40196270]","DOI":"10.2196\/preprints.79010"},{"issue":"1","key":"R83","doi-asserted-by":"publisher","DOI":"10.1111\/dar.70059","article-title":"Language models for standardising clinical notes and information extraction in addiction psychiatry-an empirical study","volume":"45","author":"Gireesh","journal-title":"Drug Alcohol Rev"},{"issue":"1","key":"R84","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-026-39676-0","article-title":"Quantifying improvement of psychotic symptoms in clozapine-treated schizophrenia: clinical note analysis with large language models","volume":"16","author":"Matsumura","journal-title":"Sci Rep"},{"issue":"3","key":"R85","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1177\/00912174241284730","article-title":"Application of artificial intelligence (AI) in the creation of discharge summaries in psychiatric clinics","volume":"60","author":"Janota","journal-title":"Int J Psychiatry Med"},{"key":"R86","doi-asserted-by":"publisher","DOI":"10.2196\/54706","article-title":"Physician versus large language model chatbot responses to web-based questions from autistic patients in Chinese: cross-sectional comparative analysis","volume":"26","author":"He","journal-title":"J Med Internet Res"},{"issue":"1","key":"R87","doi-asserted-by":"publisher","DOI":"10.1186\/s12888-026-07896-3","article-title":"Development and preliminary evaluation of a virtual standardized patient system for psychiatric interview training","volume":"26","author":"Li","journal-title":"BMC Psychiatry"},{"key":"R88","doi-asserted-by":"crossref","unstructured":"Yilanli M McKay I Jackson DI Sezgin E . Large language models for individualized psychoeducational tools for psychosis: a cross-sectional study. medRxiv. Preprint posted online on Jul 29, 2024. [doi: 10.1101\/2024.07.26.24311075]","DOI":"10.1101\/2024.07.26.24311075"},{"issue":"1","key":"R89","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1177\/08901171251348208","article-title":"ChatGPT-4o vs psychiatrists in responding to common antidepressant concerns","volume":"40","author":"Senturk","journal-title":"Am J Health Promot"},{"issue":"3","key":"R90","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1007\/s00115-025-01837-3","article-title":"Exploring the potential of ChatGPT as a digital advisor in acute psychiatric crises: a feasibility study","volume":"97","author":"Barabas","journal-title":"Nervenarzt"},{"key":"R91","doi-asserted-by":"publisher","DOI":"10.2196\/67891","article-title":"Competency of large language models in evaluating appropriate responses to suicidal ideation: comparative study","volume":"27","author":"McBain","journal-title":"J Med Internet Res"},{"key":"R92","doi-asserted-by":"publisher","DOI":"10.2196\/69709","article-title":"A comparison of responses from human therapists and large language model-based chatbots to assess therapeutic communication: mixed methods study","volume":"12","author":"Scholich","journal-title":"JMIR Ment Health"},{"key":"R93","doi-asserted-by":"crossref","unstructured":"Bannett Y Gunturkun F Pillai M et al. Leveraging a large language model to assess quality-of-care: monitoring ADHD medication side effects. medRxiv. Preprint posted online on Apr 24, 2024. [doi: 10.1101\/2024.04.23.24306225] [Medline: 38712037]","DOI":"10.1101\/2024.04.23.24306225"},{"issue":"1","key":"R94","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-024-02075-x","article-title":"ChatGPT: a conceptual review of applications and utility in the field of medicine","volume":"48","author":"Rao","journal-title":"J Med Syst"},{"issue":"10","key":"R95","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1080\/14787210.2024.2386669","article-title":"Artificial intelligence and prescription of antibiotic therapy: present and future","volume":"22","author":"Giacobbe","journal-title":"Expert Rev Anti-Infect Ther"},{"key":"R96","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2026.3698694","article-title":"From LLM reasoning to autonomous AI agents: a comprehensive review","volume":"14","author":"Ferrag","journal-title":"IEEE Access"},{"key":"R97","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2023.1277756","article-title":"ChatGPT is not ready yet for use in providing mental health assessment and interventions","volume":"14","author":"Dergaa","journal-title":"Front Psychiatry"},{"issue":"Suppl 1","key":"R98","doi-asserted-by":"publisher","DOI":"10.1136\/fmch-2023-002583","article-title":"Assessing prognosis in depression: comparing perspectives of AI models, mental health professionals and the general public","volume":"12","author":"Elyoseph","journal-title":"Fam Med Community Health"},{"issue":"4","key":"R99","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1097\/YCO.0000000000001088","article-title":"Opportunities and risks of large language models in digital interventions for substance use disorders","volume":"39","author":"de Vries","journal-title":"Curr Opin Psychiatry"},{"issue":"1","key":"R100","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01157-x","article-title":"The ethics of ChatGPT in medicine and healthcare: a systematic review on large language models (LLMs)","volume":"7","author":"Haltaufderheide","journal-title":"npj Digital Med"},{"key":"R101","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108013","article-title":"ChatGPT in healthcare: a taxonomy and systematic review","volume":"245","author":"Li","journal-title":"Comput Methods Programs Biomed"},{"issue":"12","key":"R102","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2025.101366","article-title":"The widespread adoption of large language model-assisted writing across society","volume":"6","author":"Liang","journal-title":"Patterns (N Y)"},{"issue":"10","key":"R103","doi-asserted-by":"publisher","first-page":"2736","DOI":"10.1111\/add.15972","article-title":"Causal inference with observational data in addiction research","volume":"117","author":"Chan","journal-title":"Addiction"},{"issue":"6","key":"R104","doi-asserted-by":"publisher","first-page":"1125","DOI":"10.1111\/add.16442","article-title":"Designing observational studies for credible causal inference in addiction research-directed acyclic graphs, modified disjunctive cause criterion and target trial emulation","volume":"119","author":"Chan","journal-title":"Addiction"},{"issue":"1","key":"R105","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01029-4","article-title":"Prompt engineering in consistency and reliability with the evidence-based guideline for LLMs","volume":"7","author":"Wang","journal-title":"npj Digital Med"},{"issue":"9","key":"R106","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.1007\/s00127-023-02488-y","article-title":"A review of excluded groups and non-response in population-based mental health surveys from high-income countries","volume":"58","author":"Wright","journal-title":"Soc Psychiatry Psychiatr Epidemiol"},{"key":"R107","doi-asserted-by":"crossref","unstructured":"Jin Y Chandra M Verma G Hu Y De Choudhury M Kumar S . Better to ask in English: cross-lingual evaluation of large language models for healthcare queries. Presented at: WWW \u201924: Proceedings of the ACM Web Conference 2024; May 13-17, 2024:2627-2638; Singapore, Singapore. [doi: 10.1145\/3589334.3645643]","DOI":"10.1145\/3589334.3645643"},{"key":"R108","doi-asserted-by":"crossref","unstructured":"Nadkarni A Hanlon C Patel V . Mental health care models in low-and middle-income countries, in Tasman\u2019s Psychiatry. In: Tasman A Riba MB Alarc\u00f3n RD Alfonso CA , editors. Tasman\u2019s Psychiatry. Springer; 2023:1-47. [doi: 10.1007\/978-3-030-42825-9_156-1]","DOI":"10.1007\/978-3-030-42825-9_156-1"},{"issue":"8071","key":"R109","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1038\/d41586-025-02069-w","article-title":"Will AI speed up literature reviews or derail them entirely?","volume":"643","author":"Reynolds","journal-title":"Nature"}],"container-title":["JMIR AI"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T17:22:59Z","timestamp":1788196979000},"score":1,"resource":{"primary":{"URL":"https:\/\/ai.jmir.org\/2026\/1\/e87730"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,31]]},"references-count":109,"URL":"https:\/\/doi.org\/10.2196\/87730","relation":{},"ISSN":["2817-1705"],"issn-type":[{"value":"2817-1705","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,31]]},"article-number":"v5i2e87730"}}