Schizophrenia risk prediction following antecedent psychosis using deep learning
Schizophrenia is a debilitating psychiatric disorder in which earlier clinical recognition would enhance monitoring and treatment planning. We developed a deep learning model using administrative claims data to predict diagnostic transition to schizophrenia among individuals with a history of psychosis. We included 158,704 individuals from a Medicaid claims database (2008–2022) with a history of psychosis, of whom 13,437 (8.5%) were subsequently diagnosed with schizophrenia. Individuals with at least 3 years of continuous observation and at least one non-schizophrenia psychosis diagnosis prior to the censor date were included in the cohort. We used a validated phenotype to predict the individual-level likelihood of future incipient schizophrenia by leveraging temporal patterns of clinical features. Diagnostic transition was predicted using structured features, including conditions, medications, laboratory events, procedures, and visit timing. An encoder-only transformer architecture trained to learn the temporal signal of a patient’s trajectory performed the best on internal validation data compared to other architectures. External validity of this model was assessed using an independent, commercially insured cohort. The transformer model exhibited an AUROC of 0.791 [95% CI: 0.788, 0.794] and transported well to the external dataset (AUROC: 0.763 [0.751, 0.772]). Psychiatric care and healthcare utilization features were assessed to be the most predictive. Overall, we find promising performance for schizophrenia risk stratification among individuals with a history of psychosis. Features related to psychiatric care, particularly prescriptions and diagnoses, and healthcare utilization in outpatient settings were the most predictive of a future schizophrenia diagnosis.
Authors
- Andrey Rzhetsky (ORCID: https://orcid.org/0000-0001-6959-7405)
- Todd Lencz (ORCID: https://orcid.org/0000-0001-8586-338X)
- Steven A. Kushner (ORCID: https://orcid.org/0000-0002-9777-3338)
- Sander Markx (ORCID: https://orcid.org/0000-0002-7483-0352)
- Michael C. Zody (ORCID: https://orcid.org/0000-0001-6594-7199)
- Molly T. Finnerty (ORCID: https://orcid.org/0000-0003-2035-5637)
- Noémie Elhadad (ORCID: https://orcid.org/0000-0001-9721-5240)
- Aparajita Kashyap (ORCID: https://orcid.org/0000-0002-5660-2778)
- Vaidehi Jobanputra (ORCID: https://orcid.org/0000-0003-0962-7873)
- Paul S. Appelbaum (ORCID: https://orcid.org/0000-0002-1940-0042)
- Shalmali D. Joshi (ORCID: https://orcid.org/0009-0007-0397-1346)
- Matthew S. Lebowitz (ORCID: https://orcid.org/0000-0002-5381-3000)
- Thomas Lehner (ORCID: https://orcid.org/0000-0002-1889-1214)
- COPPER Working Group
- Caline Karam
Institutions
- Northwell Health (US)
- University of Chicago (US)
- New York Genome Center (US)
- Igenbio (United States) (US)
- New York University (US)
- Columbia University (US)
Publication Details
- Journal
- Schizophrenia
- Published
- 2026-11-19
- DOI
- https://doi.org/10.1038/s41537-026-00828-w
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00