Empowering Medical Multi-Agents with Clinical Consultation Flow for Dynamic Diagnosis

2025-03-19

AI Summary

Conventional AI-based medical systems predominantly rely on single-modality data and struggle to support multi-turn interaction and continuous information acquisition during dynamic diagnosis, often leading to premature decision-making. Method: We propose a multi-agent framework tailored for dynamic diagnosis that emulates real-world clinical consultation workflows, enabling progressive collection and fusion of multimodal clinical data through iterative agent collaboration. We introduce a hierarchical action space grounded in clinical consultation protocols and medical textbooks, and incorporate clinical-knowledge-guided reinforcement learning to enhance state-adaptive decision-making. Contribution/Results: Evaluated on a public dynamic diagnosis benchmark, our approach significantly outperforms existing baselines and achieves state-of-the-art performance among foundation-model-based methods, effectively overcoming inherent limitations of static models in diagnostic persistence and interactive capability.

Technology Category

• Multiagent Systems: Multiagent Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Traditional AI-based healthcare systems often rely on single-modal data, limiting diagnostic accuracy due to incomplete information. However, recent advancements in foundation models show promising potential for enhancing diagnosis combining multi-modal information. While these models excel in static tasks, they struggle with dynamic diagnosis, failing to manage multi-turn interactions and often making premature diagnostic decisions due to insufficient persistence in information collection.To address this, we propose a multi-agent framework inspired by consultation flow and reinforcement learning (RL) to simulate the entire consultation process, integrating multiple clinical information for effective diagnosis. Our approach incorporates a hierarchical action set, structured from clinic consultation flow and medical textbook, to effectively guide the decision-making process. This strategy improves agent interactions, enabling them to adapt and optimize actions based on the dynamic state. We evaluated our framework on a public dynamic diagnosis benchmark. The proposed framework evidentially improves the baseline methods and achieves state-of-the-art performance compared to existing foundation model-based methods.

Problem

• Enhancing dynamic diagnosis with multi-agent clinical consultation flow
• Overcoming single-modal data limitations for accurate medical diagnosis
• Improving multi-turn interactions and persistent information collection in AI healthcare

Innovation

• Multi-agent framework simulating clinical consultation flow
• Hierarchical action set from medical consultation flow
• Reinforcement learning for dynamic diagnosis optimization