JingFang: A Traditional Chinese Medicine Large Language Model of Expert-Level Medical Diagnosis and Syndrome Differentiation-Based Treatment

2025-02-04

AI Summary

Current large language models (LLMs) for Traditional Chinese Medicine (TCM) exhibit significant limitations in diagnostic coverage, syndrome differentiation accuracy, and therapeutic rationality. To address these challenges, this paper introduces JingFang—a domain-expert LLM specifically designed for TCM clinical diagnosis and treatment. JingFang pioneers a Multi-agent Dynamic Collaborative Chain-of-Thought Mechanism (MDCCTM), integrating a syndrome-specific agent with a Two-Stage Retrieval Scheme (TSRS) to enable closed-loop optimization across symptom inquiry, syndrome differentiation, and treatment formulation. The model incorporates syndrome knowledge enhancement, chain-of-thought reasoning, and rigorous domain-specific fine-tuning. Empirical evaluation on multiple TCM-specialized benchmarks demonstrates that JingFang achieves performance comparable to human clinical experts—markedly improving diagnostic comprehensiveness, syndrome differentiation accuracy, and prescription rationality. This work establishes a novel, trustworthy paradigm for AI-assisted clinical decision-making in TCM.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Other Foundations of Multi Agent Systems

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Traditional Chinese medicine (TCM) plays a vital role in health protection and disease treatment, but its practical application requires extensive medical knowledge and clinical experience. Existing TCM Large Language Models (LLMs) exhibit critical limitations of uncomprehensive medical consultation and diagnoses, and inaccurate syndrome differentiation-based treatment. To address these issues, this study establishes JingFang (JF): a novel TCM Large Language Model that demonstrates the expert-level capability of medical diagnosis and syndrome differentiation-based treatment. We innovate a Multi-agent Dynamic Collaborative Chain-of-Thought Mechanism (MDCCTM) for medical consultation, enabling JF with effective and accurate diagnostic ability. In addition, a Syndrome Agent and a Dual-Stage Retrieval Scheme (DSRS) are developed to significantly enhance the capacity of JF for disease treatment based on syndrome differentiation. JingFang not only facilitates the application of LLMs but also promotes the effective practice of TCM in human health protection and disease treatment.

Problem

• Enhances Traditional Chinese Medicine diagnosis
• Improves syndrome differentiation-based treatments
• Innovates multi-agent dynamic consultation mechanism

Innovation

• Multi-agent Dynamic Collaborative Chain-of-Thought Mechanism
• Syndrome Agent for enhanced treatment accuracy
• Dual-Stage Retrieval Scheme for syndrome differentiation