A Retrieval-Augmented Multi-Agent Framework for Psychiatry Diagnosis

2025-06-04

AI Summary

To address core challenges in mood disorder diagnosis—including high subjectivity, symptom overlap, and data scarcity due to privacy constraints—this study proposes MoodAngels, a retrieval-augmented multi-agent diagnostic framework. Methodologically, it introduces (1) the first psychiatric multi-agent collaboration paradigm, integrating fine-grained clinical assessment with structured validation; (2) MoodSyn, the first open-source synthetic dataset comprising 1,173 cases, rigorously validated for statistical fidelity and complex relational preservation relative to real-world clinical data; and (3) a hybrid reasoning architecture combining clinical knowledge graph–guided inference with Retrieval-Augmented Generation (RAG) to ensure diagnostic interpretability, verifiability, and iterative refinement. Evaluated on real clinical cases, MoodAngels achieves a 12.3% higher diagnostic accuracy than GPT-4o. This work establishes a novel, privacy-preserving paradigm for AI-assisted psychiatric diagnosis.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Multiagent Systems: Other Foundations of Multi Agent Systems
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• Addressing subjective mental health assessments in AI diagnosis
• Overcoming symptom overlap across psychiatric disorders
• Ensuring privacy while improving diagnostic accuracy

Innovation

• Multi-agent framework for mood disorder diagnosis
• Granular-scale analysis with structured verification
• Open-source synthetic dataset preserving clinical validity