MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosis

TL;DR

MoodAngels is a novel multi-agent AI framework for psychiatric diagnosis that combines clinical data analysis with verification, utilizing a new synthetic dataset to improve accuracy and privacy in mental health assessments.

Contribution

We introduce MoodAngels, the first specialized multi-agent framework for mood disorder diagnosis, and MoodSyn, a synthetic dataset that preserves clinical validity while ensuring privacy.

Findings

MoodAngels outperforms conventional methods with 12.3% higher accuracy.

The system accurately reproduces statistical patterns in the synthetic dataset.

Experimental results show improved diagnostic accuracy over baseline models.

Abstract

The application of AI in psychiatric diagnosis faces significant challenges, including the subjective nature of mental health assessments, symptom overlap across disorders, and privacy constraints limiting data availability. To address these issues, we present MoodAngels, the first specialized multi-agent framework for mood disorder diagnosis. Our approach combines granular-scale analysis of clinical assessments with a structured verification process, enabling more accurate interpretation of complex psychiatric data. Complementing this framework, we introduce MoodSyn, an open-source dataset of 1,173 synthetic psychiatric cases that preserves clinical validity while ensuring patient privacy. Experimental results demonstrate that MoodAngels outperforms conventional methods, with our baseline agent achieving 12.3% higher accuracy than GPT-4o on real-world cases, and our full multi-agent system delivering further improvements. Evaluation in the MoodSyn dataset demonstrates exceptional fidelity, accurately reproducing both the core statistical patterns and complex relationships present in the original data while maintaining strong utility for machine learning applications. Together, these contributions provide both an advanced diagnostic tool and a critical research resource for computational psychiatry, bridging important gaps in AI-assisted mental health assessment.