From Metaphor to Mechanism: How LLMs Decode Traditional Chinese Medicine Symbolic Language for Modern Clinical Relevance

2025-03-04

AI Summary

This study addresses the semantic gap between traditional Chinese medicine (TCM) metaphorical language and Western medicine (WM) anatomical–pathological concepts, which impedes automated interpretation and clinical translation. We propose the first multi-agent chain-of-thought (CoT) reasoning framework specifically designed for decoding TCM metaphors, integrating dual-domain expert collaboration (TCM and WM), structured CoT prompting, cross-paradigm metaphor translation theory, and domain-adapted large language models. Leveraging a high-quality, manually curated TCM metaphor corpus, the framework enables interpretable and verifiable terminology mapping between TCM and WM concepts. It establishes the first systematic, semantically grounded alignment between TCM metaphors and biomedical pathology mechanisms. Experimental results demonstrate significant improvements in both accuracy and transparency of metaphor-to-pathology mapping. This work provides a reusable technical foundation for clinical decision support, integrative medical education, and evidence-based TCM research.

Technology Category

• Cognitive Modeling & Cognitive Systems: Analogy
• Multiagent Systems: Mechanism Design
• Search and Optimization: Metareasoning and Metaheuristics

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: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

Metaphorical expressions are abundant in Traditional Chinese Medicine (TCM), conveying complex disease mechanisms and holistic health concepts through culturally rich and often abstract terminology. Bridging these metaphors to anatomically driven Western medical (WM) concepts poses significant challenges for both automated language processing and real-world clinical practice. To address this gap, we propose a novel multi-agent and chain-of-thought (CoT) framework designed to interpret TCM metaphors accurately and map them to WM pathophysiology. Specifically, our approach combines domain-specialized agents (TCM Expert, WM Expert) with a Coordinator Agent, leveraging stepwise chain-of-thought prompts to ensure transparent reasoning and conflict resolution. We detail a methodology for building a metaphor-rich TCM dataset, discuss strategies for effectively integrating multi-agent collaboration and CoT reasoning, and articulate the theoretical underpinnings that guide metaphor interpretation across distinct medical paradigms. We present a comprehensive system design and highlight both the potential benefits and limitations of our approach, while leaving placeholders for future experimental validation. Our work aims to support clinical decision-making, cross-system educational initiatives, and integrated healthcare research, ultimately offering a robust scaffold for reconciling TCM's symbolic language with the mechanistic focus of Western medicine.

Problem

• Interpret TCM metaphors for modern clinical relevance
• Map TCM symbolic language to Western medical concepts
• Develop a multi-agent framework for cross-paradigm medical integration

Innovation

• Multi-agent framework interprets TCM metaphors
• Chain-of-thought prompts ensure transparent reasoning
• Domain-specialized agents map TCM to Western medicine