Towards AI

Psychiatric disorders are heterogeneous, and care depends on interpreting unstructured longitudinal narratives, creating variability that hinders standardization. A study now shows that a psychiatry-specific large language model (LLM) may help clinicians to deliver more consistent, high-quality care.

This is a preview of subscription content, access via your institution

Prices may be subject to local taxes which are calculated during checkout

Hua, Y. et al. NPJ Digit. Med. 8, 230 (2025).

Wang, R. et al. Nat. Mach. Intell. 8, 690–707 (2026).

Stein, D. J. et al. World Psychiatry 21, 393–414 (2022).

Gorelik, A. J., Radin, A. S., Bogdan, R. & Stamatis, C. A. NEJM AI 2, AIp2500045 (2025).

Kim, J. et al. NPJ Digit. Med. 8, 580 (2025).

Chen, Z. S., Schultebraucks, K. & Wu, W. Transl. Psychiatry 16, 136 (2026).

Bean, A. M. et al. Nat. Med. 32, 609–615 (2026).

Sharma, D. et al. NPJ Digit. Med. 9, 252 (2026).

J.K. is supported by the National Institutes of Health (NIH; grant K01MH137386).

Stanford Center for Digital Health, Stanford School of Medicine, Stanford, CA, USA

Department of Psychiatry and Behavioral Sciences, Stanford School of Medicine, Stanford, CA, USA

Search author on:PubMed Google Scholar

The authors have no competing interests.

Kim, J., Rodriguez, C.I. Towards AI-augmented decision making in psychiatry. Nat Mach Intell (2026). https://doi.org/10.1038/s42256-026-01256-2

Version of record: 12 June 2026

DOI: https://doi.org/10.1038/s42256-026-01256-2