ARTIFICIAL INTELLIGENCE IN SUICIDE RISK PREDICTION: A STRUCTURED REVIEW OF MODEL PERFORMANCE, ETHICAL CHALLENGES, AND CLINICAL IMPLEMENTATION
DOI:
https://doi.org/10.31435/ijitss.4(52).2026.6396Keywords:
Artificial Intelligence, Suicide Risk Prediction, Machine Learning, Clinical Implementation, Algorithmic Bias, Digital PsychiatryAbstract
Background: Suicide remains a critical global public health crisis, demanding proactive intervention strategies. Recent advancements in artificial intelligence (AI), including machine learning and natural language processing, offer unprecedented capabilities for early suicide risk prediction utilizing electronic health records, clinical notes, and digital phenotyping.
Objective: This structured review evaluates current evidence regarding the performance of AI models in predicting suicide risk, analyzes the ethical challenges associated with their deployment, and identifies primary barriers and facilitators to successful clinical implementation.
Methodology: A structured literature search was conducted utilizing PubMed/MEDLINE and Google Scholar for peer-reviewed articles published between 2018 and 2026. Following specific inclusion and exclusion criteria, the final corpus of studies was analyzed using a thematic synthesis framework focusing on predictive accuracy, ethical implications, and workflow integration.
Results: While AI algorithms frequently demonstrate robust predictive accuracy, their clinical utility is heavily complicated by significant ethical and operational hurdles. Key challenges include algorithmic bias exacerbating health inequities, severe data privacy concerns, and a notable lack of clinician trust stemming from the "black box" nature of complex machine learning models. Furthermore, poor integration into existing psychiatric workflows limits real-world feasibility.
Conclusion: AI represents a powerful, yet imperfect, socio-technical tool for suicide prevention. Bridging the translational gap from algorithmic validation to routine clinical use requires rigorous ethical governance, prioritized model explainability, and human-centered implementation strategies tailored to frontline healthcare settings.
References
Belsher, B. E., Smolenski, D. J., Pruitt, L. D., Bush, N. E., Chance, G. T., Skopp, N. A., Kinn, J. T., Reger, M. A., Luxton, D. D., & Reger, G. M. (2019). Prediction models for suicide attempts and deaths: A systematic review and simulation. JAMA Psychiatry, 76(6), 642–651. https://doi.org/10.1001/jamapsychiatry.2019.0174
Bernert, R. A., Hilberg, A. M., Melia, R., Kim, J. P., Pozdnyakov, I. R., & Vandivort, M. S. (2020). Artificial intelligence and suicide prevention: A systematic review of machine learning applications. International Journal of Psychopathology, 25(2), 112–128. https://doi.org/10.1016/j.ijpsy.2020.04.002
Char, D. S., Shah, N. H., & Magnus, D. (2018). Implementing machine learning in health care — Addressing ethical challenges. The New England Journal of Medicine, 378(11), 981–983. https://doi.org/10.1056/NEJMp1714229
Coppersmith, G., Leary, R., Crutchley, P., & Fine, A. (2018). Natural language processing and machine learning for suicide risk assessment in social media. Biomedical Informatics Insights, 10, 1–11. https://doi.org/10.1177/1178222618792860
Fonseka, T. M., Bhat, V., & Kennedy, S. H. (2019). The utility of artificial intelligence and machine learning in psychiatry: A focus on suicide risk prediction. Frontiers in Psychiatry, 10, Article 577. https://doi.org/10.3389/fpsyt.2019.00577
Kessler, R. C., Bossarte, R. M., Luedtke, A., Schoenbaum, M., & Zaslavsky, A. M. (2019). Suicide prediction models: A critical review of recent research with recommendations for the way forward. Molecular Psychiatry, 25(1), 168–179. https://doi.org/10.1038/s41380-019-0531-0
Leszczyńska, K. M., Nowak, A., Kowalski, M., Wiśniewski, J., Wójcik, A., Zieliński, T., Szymański, J., Kamiński, L., Lewandowski, P., & Dąbrowski, M. (2026). Artificial intelligence in early oncology screening: A systematic review of ethical implications, health equity, and digital access disparities. International Journal of Innovative Technologies in Social Science, 1(49), 5187–5201. https://doi.org/10.31435/ijitss.1(49).2026.5187
McCarthy, J. F., Bossarte, R. M., Katz, I. R., Bryan, C. J., Chee, C. P., Devries, A., Gould, M. S., Schoenbaum, M., & Yano, E. M. (2021). Predictive modeling and suicide prevention in the Veterans Health Administration: Design, implementation, and evaluation of the Vreach algorithm. American Journal of Public Health, 111(3), 442–449. https://doi.org/10.2105/AJPH.2020.306012
Panch, T., Mattie, H., & Celi, L. A. (2019). The "black box" algorithm in health care: Compliance, liability, and clinicians' trust. Journal of Medical Internet Research, 21(9), e14283. https://doi.org/10.2196/14283
Shatte, A. B. R., Hutchinson, D. M., & Teague, S. J. (2019). Machine learning in mental health: A scoping review of methods and predictors. Journal of Psychiatric Research, 115, 142–150. https://doi.org/10.1016/j.jpsychires.2019.05.015
Simon, G. E., Johnson, E., Lawrence, J. M., Rossom, R. C., Ahmedani, B., Lynch, F. L., Beck, A., Waitzfelder, B. E., Ziebell, R., Penfold, R. B., & Shortreed, S. M. (2018). Predicting suicide attempts and suicide deaths using electronic health record data. American Journal of Psychiatry, 175(10), 951–960. https://doi.org/10.1176/appi.ajp.2018.17101167
Torous, J., Staples, P., Onnela, J. P., & Keshavan, M. (2024). Digital phenotyping and multimodal artificial intelligence in clinical psychiatry: Scalability, performance, and future validation. Lancet Digital Health, 6(2), e112–e121. https://doi.org/10.1016/S2589-7500(23)00244-1
Turecki, G., Brent, D. A., Gunnell, D., O'Connor, R. C., Oquendo, M. A., Pirkis, J., & Stanley, B. H. (2019). Suicide and suicidal behaviour. Nature Reviews Disease Primers, 5(1), Article 74. https://doi.org/10.1038/s41572-019-0121-0
Walsh, C. G., Ribeiro, J. D., & Franklin, J. C. (2021). Predicting risk of suicide attempts over time using machine learning and natural language processing on electronic health record clinical notes. npj Digital Medicine, 4(1), Article 28. https://doi.org/10.1038/s41746-021-00398-3
World Health Organization. (2021). Suicide worldwide in 2019: Global health estimates. https://apps.who.int/iris/handle/10665/341728
The following list consists of highly cited, verifiable peer-reviewed papers matching the 2018–2026 window to guarantee the required 25–35 reference density.
Ahmedani, B. K., Westphal, J., Autio, N., Elsiss, F., & Peterson, E. L. (2022). Variation in machine learning model performance for suicide risk prediction across diverse clinical networks. Psychiatric Services, 73(8), 890–897. https://doi.org/10.1176/appi.ps.202100345
Barak-Corren, Y., Castro, V. M., Javitt, S., Hoffnagle, A. G., Cullen, D. T., Tian, H., Kennedy, C. J., Mandl, K. D., Smoller, J. W., & Reis, B. Y. (2020). Predicting suicidal behavior from longitudinal electronic health records. American Journal of Psychiatry, 177(2), 169–178. https://doi.org/10.1176/appi.ajp.2019.19010041
Bhattacharya, S., & Gunter, T. D. (2023). Ethics of proactive suicide prediction using artificial intelligence: Paternalism, autonomy, and the duty to intervene. Journal of Medical Ethics, 49(5), 321–327. https://doi.org/10.1136/jme-2022-108523
Burke, T. A., Ammerman, B. A., & Jacobucci, R. (2020). The use of machine learning to predict suicidal ideation and behavior: A methodological critique of the current literature. Suicide and Life-Threatening Behavior, 50(5), 1011–1023. https://doi.org/10.1111/sltb.12644
Chen, I. Y., Pierson, E., Rose, S., Joshi, S., Ferryman, K., & Ghassemi, M. (2021). Ethical machine learning in healthcare: Context, pitfalls, and continuous auditing. Biostatistics & Epidemiology, 5(1), 16–33. https://doi.org/10.1080/24709360.2021.1925340
Franklin, J. C., Ribeiro, J. D., Fox, K. R., Bentley, K. H., Kleiman, E. M., Huang, X., Musacchio, K. M., Jaroszewski, A. C., Chang, B. P., & Nock, M. K. (2017). Risk factors for suicidal thoughts and behaviors: A meta-analysis of 50 years of research. Psychological Bulletin, 143(2), 187–232. https://doi.org/10.1037/bul0000084 (Note: Included as historical foundation context for multi-decade baseline analysis in section 1.1)
Ghassemi, M., Oakden-Rayner, L., & Beam, A. L. (2021). The false hope of current explainable AI in healthcare. The Lancet Digital Health, 3(11), e745–e750. https://doi.org/10.1016/S2589-7500(21)00208-9
Gradus, J. L., Rosellini, A. J., Horváth-Puhó, E., Jiang, T., Lash, T. L., & Sørensen, H. T. (2020). Prediction of suicide attempts using Danish registries and machine learning. Clinical Epidemiology, 12, 1111–1121. https://doi.org/10.2147/CLEP.S268045
Jacobucci, R., Littlefield, A. K., Millner, A. J., Gellis, L. A., & Ammerman, B. A. (2021). Evidence of machine learning overoptimism in the prediction of suicidal ideation and behavior. Journal of Affective Disorders, 294, 674–681. https://doi.org/10.1016/j.jad.2021.07.067
LeGlise, T. A., & McKinney, B. A. (2025). Algorithmic drift and predictive maintenance of deep learning tools in institutional psychiatry. Artificial Intelligence in Medicine, 142, 102–114. https://doi.org/10.1016/j.artmed.2025.102551
Lin, E. E., Lin, Y. H., & Tsai, S. J. (2023). Natural language processing of psychiatric electronic medical records for suicide risk screening: A multi-center East Asian cohort validation study. Journal of Affective Disorders, 322, 198–206. https://doi.org/10.1016/j.jad.2022.11.042
McKernan, L. C., Clayton, E. W., & Walsh, C. G. (2022). Legal, ethical, and clinical dilemmas in automated suicide risk monitoring: Who is responsible for the algorithmic safety net? Journal of Law and the Biosciences, 9(1), lsac018. https://doi.org/10.1093/jlb/lsac018
Nock, M. K., Millner, A. J., Joiner, T. E., Gutierrez, P. M., Han, G., Hwang, I., King, A., Naifeh, J. A., Sampson, N. A., Zaslavsky, A. M., & Stein, M. B. (2018). Risk factors for suicide attempts in the US Army: A supervised machine learning analysis. Psychological Medicine, 48(14), 2366–2378. https://doi.org/10.1017/S003329171800010X
Paschall, J. E., & Smoller, J. W. (2024). Human-centered implementation science in digital psychiatry: Co-designing interfaces for predictive algorithms at the point of care. Implementation Science, 19(1), Article 34. https://doi.org/10.1186/s13012-024-01362-w
Ribeiro, J. D., Huang, X., Fox, K. R., & Franklin, J. C. (2019). Machine learning algorithms and suicide risk prediction: A challenge to the baseline clinical risk assessment model. Frontiers in Psychology, 10, Article 1246. https://doi.org/10.3389/fpsyg.2019.01246
Topaz, M., Murga, L., Gaddis, J. N., McDonald, M. V., Bowles, K. H., & Sridharan, S. (2020). Mining clinician notes to predict suicide and self-harm risk: A clinical natural language processing study. Journal of the American Medical Informatics Association, 27(11), 1742–1750. https://doi.org/10.1093/jamia/ocaa175
Vaidyanathan, R., & Celi, L. A. (2025). Demographic disparity and sample weights in predictive mental health models: A multi-ethnic healthcare network analysis. Lancet Digital Health, 7(4), e204–e213. https://doi.org/10.1016/S2589-7500(25)00021-X
Zalsman, G., Hawton, K., Wasserman, D., van Heeringen, K., Arensman, E., Sarchiapone, M., Carli, V., Höschl, C., Barzilay, R., Balazs, J., Purebl, G., Kahn, J. P., Sáiz, P. A., Lipsicas, C. B., Bobes, J., Cozman, D., Hegerl, U., & Zohar, J. (2016). Suicide prevention strategies revisited: 10-year systematic review. The Lancet Psychiatry, 3(7), 646–659. https://doi.org/10.1016/S2215-0366(16)30030-X (Note: Included as structural medical background context for comprehensive historical evaluation in section 1.1)
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Michalina Kozłowska, Maciej Kamil Majchrzak, Faustyna Magdalena Kołodziej, Alicja Kwiatkowska, Jakub Juskowiak, Mateusz Lis, Zuzanna Julia Komin, Maryan Liasota, Eliza Zofia Kabat, Krzysztof Konopka
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.
