Ensuring generalizability and clinical utility in mental health care applications: Robust artificial intelligence‐based treatment predictions in diverse psychosis populations
Psychiatry and Clinical Neurosciences · 2026-01 · 80 (1) · 64-75
DOI: 10.1111/pcn.13914 ↗Kurz gefasst
Fachartikel in der Zeitschrift Psychiatry and Clinical Neurosciences, online erschienen am 06.11.2025. Verfasst von Fiona Coutts und 10 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK. Hauptthemen laut MEDLINE: Antipsychotic Agents, Artificial Intelligence, Machine Learning, Outcome Assessment, Health Care. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIMH NIH HHS, National Institute of Mental Health (NIMH), European Group for Research in Schizophrenia (EGRIS).
Abstract (Originalsprache)
Aim
Artificial Intelligence (AI)‐based prediction models of treatment response promise to revolutionize psychiatric care by enabling personalized treatment, but very few have been thoroughly tested in different samples or compared to current clinical standards. Here we present models predicting antipsychotic response and assess their clinical utility in a robust methodological framework.
Methods
Machine learning models were trained and cross‐validated on clinical and sociodemographic data from 594 individuals with established schizophrenia (NCT00014001) and 323 individuals with first episode psychosis (NCT03510325). Models predicted four measures of antipsychotic response at 3 months after baseline. Clinical utility was assessed using decision curve and calibration curve analyses. Model performance was tested in a reduced feature space and across sex, ethnicity, antipsychotic, and symptom change subgroups to investigate model fairness.
Results
Models predicting total symptom severity ( r = 0.4–0.68) and symptomatic remission (BAC = 62.4%–69%) performed well in both samples and externally validated successfully in the opposing cohort ( r = 0.4–0.5, BAC = 63.5%–65.7%). Performance remained significant when the models were reduced to 8–9 key variables ( r = 0.53 for total symptom severity, BAC = 65.3% for symptomatic remission). Models predicting symptomatic remission had a net benefit across risk thresholds of 0.5–0.9 and were moderately well‐calibrated (ECE = 0.16–0.18). Model performance different across sex, ethnicity and medication subgroups.
Conclusions
We present a robust framework for training and assessing the clinical utility of prediction models in psychiatry. Our models generalize across different psychosis populations and show promising calibration and net benefit. However, performance disparities across demographic and treatment subgroups highlight the need for more diverse clinical samples to ensure equitable prediction.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK.
- Department of Psychiatry, Psychotherapy, Psychosomatics and Medical Psychology, Medical University of Innsbruck, Innsbruck, Austria.
- Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
- Department of Psychiatry, New York State Psychiatric Institute, Columbia, New York, USA.
- University College of Physicians and Surgeons, New York City, New York, USA.
- Department of Psychiatry and Psychotherapy, Klinikum der Universität München, Ludwig- Maximilians-University, Munich, Germany.
ORCID-Profile: Fiona Coutts
Förderung
- NIMH NIH HHS
- National Institute of Mental Health (NIMH)
- European Group for Research in Schizophrenia (EGRIS)
Zitieren
APA
Coutts, F., Mena, S., Ucur, E., Fleischhacker, W. W., Kahn, R., Lieberman, J., Hasan, A., Howes, O., Correll, C., Koutsouleris, N., & Lalousis, P. A. (2026). Ensuring generalizability and clinical utility in mental health care applications: Robust artificial intelligence‐based treatment predictions in diverse psychosis populations. Psychiatry and Clinical Neurosciences, 80(1), 64-75. https://doi.org/10.1111/pcn.13914
Vancouver
Coutts F, Mena S, Ucur E, Fleischhacker WW, Kahn R, Lieberman J, et al. Ensuring generalizability and clinical utility in mental health care applications: Robust artificial intelligence‐based treatment predictions in diverse psychosis populations. Psychiatry and Clinical Neurosciences. 2026;80(1):64-75. doi:10.1111/pcn.13914
BibTeX
@article{Coutts2026,
author = {Coutts, Fiona and Mena, Sergio and Ucur, Esin and Fleischhacker, W Wolfgang and Kahn, Rene and Lieberman, Jeffrey and Hasan, Alkomiet and Howes, Oliver and Correll, Christoph and Koutsouleris, Nikolaos and Lalousis, Paris Alexandros},
title = {Ensuring generalizability and clinical utility in mental health care applications: Robust artificial intelligence‐based treatment predictions in diverse psychosis populations},
journal = {Psychiatry and Clinical Neurosciences},
year = {2026},
volume = {80},
number = {1},
pages = {64--75},
doi = {10.1111/pcn.13914}
}
EUVIMED