OpenTCM: A GraphRAG-Empowered LLM-based System for Traditional Chinese Medicine Knowledge Retrieval and Diagnosis

2025-04-28

AI Summary

Semantic parsing of classical Chinese medical texts and weak modeling of concept relationships hinder knowledge retrieval and pattern-differentiation reasoning in Traditional Chinese Medicine (TCM). Method: We construct the first large-scale, multi-relational TCM knowledge graph integrating gynecological classics—comprising 48,000 entities and 152,000 relations—and propose a novel LLM-coordinated extraction and verification framework tailored for classical Chinese. Further, we introduce GraphRAG, the first domain-specific RAG paradigm for TCM, leveraging multi-hop graph reasoning to enhance retrieval without model fine-tuning. Contribution/Results: The knowledge graph achieves 98.55% precision and 99.55% F1 score. Expert evaluation shows significant improvements in herb retrieval (4.5/5.0) and pattern-differentiation Q&A (3.8/5.0) over state-of-the-art methods.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Knowledge Acquisition

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Traditional Chinese Medicine (TCM) represents a rich repository of ancient medical knowledge that continues to play an important role in modern healthcare. Due to the complexity and breadth of the TCM literature, the integration of AI technologies is critical for its modernization and broader accessibility. However, this integration poses considerable challenges, including the interpretation of obscure classical Chinese texts and the modeling of intricate semantic relationships among TCM concepts. In this paper, we develop OpenTCM, an LLM-based system that combines a domain-specific TCM knowledge graph and Graph-based Retrieval-Augmented Generation (GraphRAG). First, we extract more than 3.73 million classical Chinese characters from 68 gynecological books in the Chinese Medical Classics Database, with the help of TCM and gynecology experts. Second, we construct a comprehensive multi-relational knowledge graph comprising more than 48,000 entities and 152,000 interrelationships, using customized prompts and Chinese-oriented LLMs such as DeepSeek and Kimi to ensure high-fidelity semantic understanding. Last, we integrate OpenTCM with this knowledge graph, enabling high-fidelity ingredient knowledge retrieval and diagnostic question-answering without model fine-tuning. Experimental evaluations demonstrate that our prompt design and model selection significantly improve knowledge graph quality, achieving a precision of 98. 55% and an F1 score of 99. 55%. In addition, OpenTCM achieves mean expert scores of 4.5 in ingredient information retrieval and 3.8 in diagnostic question-answering tasks, outperforming state-of-the-art solutions in real-world TCM use cases.

Problem

• Interpreting obscure classical Chinese texts in TCM
• Modeling intricate semantic relationships among TCM concepts
• Enhancing TCM knowledge retrieval and diagnostic accuracy

Innovation

• GraphRAG-enhanced LLM for TCM knowledge retrieval
• Multi-relational knowledge graph with 48,000 entities
• Chinese-oriented LLMs ensure high-fidelity semantic understanding