AI Psychiatrist Assistant: An LLM-based Multi-Agent System for Depression Assessment from Clinical Interviews

Adam Greene, Neviah Blair, Samin Mahdipour Aghabagher, Simmi Kumari, Michael W Schlund, Alex Fedorov, Vince D. Calhoun, Xinhui Li, Rogers F Silva

Keywords: Large Language Models, Agents, Mental Health, Depression

TL;DR: We propose an LLM-based multi-agent system to diagnose depression symptoms from clinical interview transcripts.

Track: Proceedings

Abstract: Depression is one of the most common mental disorders yet remains underdiagnosed. Large language models (LLMs) have shown promise in their ability to understand the semantic meaning behind medical text and automate clinical workflows through collaborative agents. Here, we propose an LLM-based multi-agent system to diagnose depression symptoms from clinical interview transcripts. Our system integrates four agents: (1) a qualitative assessment agent that identifies symptoms and risk factors, (2) a judge agent that evaluates qualitative assessment through iterative self-refinement, (3) a quantitative assessment agent that predicts clinical scores using a novel embedding-based few-shot prompting approach, and (4) a meta-review agent that integrates outputs into a comprehensive overview of a patient's mental state. The qualitative assessment agent provided coherent, specific, and reasonably accurate assessment, as evaluated by both the human expert and the judge agent. The quantitative assessment agent with few-shot prompting showed an average mean absolute error of $0.619$ for symptom prediction versus $0.796$ in zero-shot prompting, while the meta-review agent achieved a binary classification accuracy of $78\\%$, comparable to that of a human expert. Our system could serve as a consultant for psychiatrists and psychologists, offering an alternative perspective on patients' mental health conditions, and thus establishing a foundation for future work on agent-aided clinical support.

General Area: Applications and Practice

Specific Subject Areas: Active & Continual Learning, Explainability & Interpretability, Natural Language Processing, Public & Social Health, Foundation Models

Data And Code Availability: Yes

Ethics Board Approval: No

Entered Conflicts: I confirm the above

Anonymity: I confirm the above

Code URL: https://github.com/trendscenter/ai-psychiatrist

Submission Number: 39