What the study found
Reasoning-based large language models were able to predict 12-week remission in people with depressive disorder taking antidepressant monotherapy. The best-performing model was Claude 3.7 Sonnet using 32,000 reasoning tokens and a referencing of deep research prompt.
Why the authors say this matters
The authors conclude that these models could serve as interpretable adjunctive tools in treatment planning for depressive disorder. They also state that prospective validation in real-world clinical settings remains essential.
What the researchers tested
The researchers analyzed data from 390 patients in the MAKE Biomarker discovery study who were receiving first-step antidepressant monotherapy. They tested three large language models, ChatGPT o1, o3-mini, and Claude 3.7 Sonnet, using prompting strategies including zero-shot chain-of-thought, atom-of-thoughts, and a novel referencing of deep research prompt. Performance was measured with balanced accuracy, sensitivity, specificity, positive predictive value, and negative predictive value, and three psychiatrists rated model outputs on 5-point Likert scales for clinical validity.
What worked and what didn't
Claude 3.7 Sonnet with 32,000 reasoning tokens and the referencing of deep research prompt had the highest reported performance, with balanced accuracy of 0.6697, sensitivity of 0.7183, and specificity of 0.6210. Medication-specific analysis showed negative predictive values of 0.75 or higher across major antidepressants, which the abstract says suggests utility in identifying likely nonresponders. Psychiatrists gave favorable mean ratings for correctness, consistency, specificity, helpfulness, and human likeness.
What to keep in mind
The study used data from a single biomarker discovery cohort and excluded patients with uncommon medications or missing biomarker data. The abstract does not describe other limitations beyond the need for prospective validation in real-world clinical settings.
Key points
- The study tested whether reasoning-based large language models could predict 12-week remission in depressive disorder.
- Claude 3.7 Sonnet with a referencing of deep research prompt had the highest reported performance.
- Medication-specific negative predictive values were 0.75 or higher across major antidepressants.
- Three psychiatrists rated the model outputs favorably for correctness, consistency, specificity, helpfulness, and human likeness.
- The authors say prospective validation in real-world clinical settings is still needed.
Disclosure
- Research title:
- Large language models predicted 12-week antidepressant remission
- Authors:
- Jin-Hyun Park, Hee‐Ju Kang, Ji Hyeon Jeon, S W Kang, Ju-Wan Kim, Jae-Min Kim, HwaMin Lee�
- Institutions:
- Chonnam National University, Chonnam National University, Chonnam National University, Chonnam National University, Chonnam National University, Korea University, Korea University
- Publication date:
- 2026-01-23
- DOI:
- 10.2196/83352
- OpenAlex record:
- View
Get the weekly research newsletter
Stay current with scholarly research without reading academic papers — one filtered digest, every Friday.