Hengqin-RA-v1: Advanced Large Language Model for Diagnosis and Treatment of Rheumatoid Arthritis with Dataset based Traditional Chinese Medicine

2025-01-05

AI Summary

To address cultural bias, clinical inaccuracy, and scarcity of high-quality training data when applying general-purpose large language models (LLMs) to Traditional Chinese Medicine (TCM) — particularly in rheumatoid arthritis (RA) diagnosis and treatment — this study develops the first RA-specific TCM LLM. We propose a novel domain-adaptive pretraining and supervised fine-tuning paradigm, integrating classical medical texts with modern clinical records to construct HQ-GCM-RA-C1, a high-quality instruction-tuning dataset. The resulting model significantly enhances culturally grounded diagnostic reasoning and personalized therapeutic recommendation generation. On TCM-specific RA tasks, it consistently outperforms leading open-source LLMs; in certain scenarios, its diagnostic accuracy surpasses that of experienced TCM practitioners. This work bridges a critical technical gap in vertical-domain LLM development for TCM, establishing a foundational framework for culturally aware, clinically reliable AI in specialized medical domains.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Large language models (LLMs) primarily trained on English texts, often face biases and inaccuracies in Chinese contexts. Their limitations are pronounced in fields like Traditional Chinese Medicine (TCM), where cultural and clinical subtleties are vital, further hindered by a lack of domain-specific data, such as rheumatoid arthritis (RA). To address these issues, this paper introduces Hengqin-RA-v1, the first large language model specifically tailored for TCM with a focus on diagnosing and treating RA. We also present HQ-GCM-RA-C1, a comprehensive RA-specific dataset curated from ancient Chinese medical literature, classical texts, and modern clinical studies. This dataset empowers Hengqin-RA-v1 to deliver accurate and culturally informed responses, effectively bridging the gaps left by general-purpose models. Extensive experiments demonstrate that Hengqin-RA-v1 outperforms state-of-the-art models, even surpassing the diagnostic accuracy of TCM practitioners in certain cases.

Problem

• Chinese Medicine
• Rheumatoid Arthritis
• Language Models

Innovation

• Hengqin-RA-v1
• HQ-GCM-RA-C1
• Rheumatoid Arthritis Diagnosis