LARGE LANGUAGE MODELS IN MENTAL HEALTH TRIAGE: A SYSTEMATIC REVIEW OF ACCURACY, BIAS, AND ETHICAL DEPLOYMENT ACROSS DIGITAL PLATFORMS
DOI:
https://doi.org/10.31435/ijitss.4(52).2026.6752Keywords:
Large Language Models, Mental Health Triage, Algorithmic Bias, Psychiatric Screening, Digital Health Equity, Generative Artificial IntelligenceAbstract
Background: The intersection of a global psychiatric workforce shortage and the rapid advancement of Generative Artificial Intelligence (GenAI) has catalyzed the integration of Large Language Models (LLMs) into digital healthcare. LLMs are increasingly deployed as preliminary triage agents to assess psychological distress, yet their diagnostic reliability, demographic neutrality, and safety protocols in crisis scenarios remain heavily debated within the psychiatric community.
Objective: This review evaluates current research to determine the trustworthiness of large language models (LLMs) used in psychiatric screening. In doing so, it shines a light on the algorithmic biases present in practical use and maps out the necessary ethical standards to ensure digital health services remain safe and fair for all patients.
Methodology: We sourced peer-reviewed publications released between 2023 and 2026 by running a systematic literature search across Google Scholar, PubMed/MEDLINE, and IEEE Xplore. The synthesis focused on comparative accuracy studies, observational evaluations, and sociotechnical analyses of leading LLMs (e.g., GPT-4, Claude 3.5 Sonnet, Gemini 1.5 Pro) applied specifically to psychiatric screening and automated clinical routing.
Results: LLMs demonstrate high diagnostic concordance with human clinicians in structured assessments for high-prevalence conditions like major depressive disorder, effectively parsing unstructured clinical narratives. However, they exhibit a consistent tendency toward conservative over-triage in psychiatric emergencies. Profound algorithmic biases persist; models frequently recommend divergent, often inferior, treatment pathways for marginalized demographic groups and display gender-based stigmatization. Furthermore, models struggle with complex psychopathologies and display inconsistent safety mechanisms during acute suicidal ideation queries.
Conclusion: While LLMs offer substantial utility for scaling preliminary psychiatric screening and reducing administrative triage burdens, their propensity for factual hallucination, demographic bias, and uncalibrated risk escalation currently precludes autonomous clinical deployment. Robust, human-in-the-loop governance and culturally representative training corpora are imperative prior to further integration into global digital health ecosystems.
References
Asman, O., Torous, J., & Tal, A. (2025). Responsible design, integration, and use of generative AI in mental health. JMIR Mental Health, 12, e70439. https://doi.org/10.2196/70439
Bouguettaya, A., Stuart, E. M., & Aboujaoude, E. (2025). Racial bias in AI-mediated psychiatric diagnosis and treatment: A qualitative comparison of four large language models. npj Digital Medicine, 8(1), Article 332. https://doi.org/10.1038/s41746-025-01746-4
Chien, C. W., & Tai, Y. M. (2024). Performances of large language models in detecting psychiatric diagnoses from Chinese electronic medical records: Comparisons between GPT-3.5, GPT-4, and GPT-4o. Taiwanese Journal of Psychiatry, 38(3), 134–141. https://doi.org/10.4103/TPSY.TPSY_24_24
Elyoseph, Z., Levkovich, I., Rabin, E., Shemo, G., Szpiler, T., Hadar Shoval, D., & Levi-Belz, Y. (2025). Applying language models for suicide prevention: Evaluating news article adherence to WHO reporting guidelines. npj Mental Health Research, 4(1), Article 28. https://doi.org/10.1038/s44184-025-00139-5
Guo, Z., Sun, Y., Wang, Y., Zhang, Y., & Chen, J. (2024). Large language models for mental health applications: Systematic review. JMIR Mental Health, 11, e57400. https://doi.org/10.2196/57400
Haber, Y., Levkovich, I., Hadar-Shoval, D., & Elyoseph, Z. (2024). The artificial third: A broad view of the effects of introducing generative artificial intelligence on psychotherapy. JMIR Mental Health, 11, e54781. https://doi.org/10.2196/54781
Hofmann, V., Kalluri, P. R., Jurafsky, D., & King, S. (2024). AI generates covertly racist decisions about people based on their dialect. Nature, 633(8028), 147–154. https://doi.org/10.1038/s41586-024-07856-5
Jin, Z., Liu, Y., Zhao, X., & Wang, H. (2026). Evaluating the efficacy of AI-based interactive assessments using large language models for depression screening: Development and usability study. JMIR Formative Research, 10, e78401. https://doi.org/10.2196/78401
Lauderdale, S. A., Griffin, S. A., Lahman, K. R., Mbaba, E., & Tomlinson, S. (2025). Unveiling public stigma for borderline personality disorder: A comparative study of artificial intelligence and mental health care providers. Personality and Mental Health, 19(2), e70018. https://doi.org/10.1002/pmh.70018
Lauderdale, S. A., Schmitt, R., Wuckovich, B., Dalal, N., Desai, H., & Tomlinson, S. (2025). Effectiveness of generative AI-large language models' recognition of veteran suicide risk: A comparison with human mental health providers using a risk stratification model. Frontiers in Psychiatry, 16, Article 1544951. https://doi.org/10.3389/fpsyt.2025.1544951
Levkovich, I. (2025). Evaluating diagnostic accuracy and treatment efficacy in mental health: A comparative analysis of large language model tools and mental health professionals. European Journal of Investigation in Health, Psychology and Education, 15(1), Article 9. https://doi.org/10.3390/ejihpe15010009
Malgaroli, M., Schultebraucks, K., Myrick, K. J., Loch, A. A., Ospina-Pinillos, L., Choudhury, T., Kotov, R., De Choudhury, M., & Torous, J. (2025). Large language models for the mental health community: Framework for translating code to care. The Lancet Digital Health, 7(4), e282–e285. https://doi.org/10.1016/S2589-7500(25)00004-9
Marengo, D., & Settanni, M. (2025). Using large language models to infer problematic Instagram use from user engagement metrics: Agreement across models and validation with self-reports. Electronics, 14(13), Article 2548. https://doi.org/10.3390/electronics14132548
Perlis, R. H., Goldberg, J. F., Ostacher, M. J., & Schneck, C. D. (2024). Clinical decision support for bipolar depression using large language models. Neuropsychopharmacology, 49(9), 1412–1416. https://doi.org/10.1038/s41386-024-01869-7
Rousmaniere, T., Zhang, Y., Li, X., & Shah, S. (2025). Large language models as mental health resources: Patterns of use in the United States. Practice Innovations, 11(2), 112–126. https://doi.org/10.1037/pri0000262
Settanni, M., Quilghini, F., Toscano, A., & Marengo, D. (2025). Assessing the accuracy and consistency of large language models in triaging social media posts for psychological distress. Psychiatry Research, 351, Article 116583. https://doi.org/10.1016/j.psychres.2025.116583
Shinan-Altman, S., Elyoseph, Z., & Levkovich, I. (2024). The impact of history of depression and access to weapons on suicide risk assessment: A comparison of ChatGPT-3.5 and ChatGPT-4. PeerJ, 12, e17468. https://doi.org/10.7717/peerj.17468
Solaiman, B. (2024). Generative artificial intelligence (GenAI) and decision-making: Legal & ethical hurdles for implementation in mental health. International Journal of Law and Psychiatry, 97, Article 102028. https://doi.org/10.1016/j.ijlp.2024.102028
Taylor, N., Kormilitzin, A., Lorge, I., Nevado-Holgado, A., Cipriani, A., & Joyce, D. W. (2024). Model development for bespoke large language models for digital triage assistance in mental health care. Artificial Intelligence in Medicine, 157, Article 102988. https://doi.org/10.1016/j.artmed.2024.102988
Thotapalli, S., Yilanli, M., McKay, I., Leever, W., Youngstrom, E., & Findling, R. L. (2025). Potential of ChatGPT in youth mental health emergency triage: Comparative analysis with clinicians. Psychiatry and Clinical Neurosciences Reports, 4(3), e70159. https://doi.org/10.1002/pcn5.70159
Voultsiou, E., & Moussiades, L. (2026). A systematic review of large language models in mental health: Opportunities, challenges, and future directions. Electronics, 15(3), Article 524. https://doi.org/10.3390/electronics15030524
Wang, X., Zhou, Y., & Zhou, G. (2025). The application and ethical implication of generative AI in mental health: Systematic review. JMIR Mental Health, 12, e70610. https://doi.org/10.2196/70610
Wang, Y. F., Li, M. D., Wang, S. H., Fang, Y., Sun, J., Lu, L., & Yan, W. (2025). Large language models in clinical psychiatry: Applications and optimization strategies. World Journal of Psychiatry, 15(11), Article 108199. https://doi.org/10.5498/wjp.v15.i11.108199
Wei, X., Kumar, N., & Zhang, H. (2025). Addressing bias in generative AI: Challenges and research opportunities in information management. Information & Management, 62(2), Article 104103. https://doi.org/10.1016/j.im.2025.104103
Xu, W., Yan, Y., & Zhu, Y. (2025). Bias in decision-making for AI's ethical dilemmas: A comparative study of ChatGPT and Claude (arXiv:2501.10484). arXiv. https://doi.org/10.48550/arXiv.2501.10484
Yang, Y., Liu, X., Jin, Q., Huang, F., & Lu, Z. (2024). Unmasking and quantifying racial bias of large language models in medical report generation. Communications Medicine, 4(1), Article 176. https://doi.org/10.1038/s43856-024-00601-z
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Alicja Kwiatkowska, Faustyna Magdalena Kołodziej, Maciej Kamil Majchrzak, Krzysztof Konopka, Michalina Justyna Kozłowska, Eliza Zofia Kabat, Maryan Liasota, Zuzanna Julia Komin, Mateusz Lis, Jakub Juskowiak
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles are published in open-access and licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). Hence, authors retain copyright to the content of the articles.
CC BY 4.0 License allows content to be copied, adapted, displayed, distributed, re-published or otherwise re-used for any purpose including for adaptation and commercial use provided the content is attributed.
