发表机构
Tsinghua Shenzhen International Graduate School, Tsinghua University; Guangdong Provincial Laboratory of Traditional Chinese Medicine Hengqin（清华大学深圳国际研究生院; 广东省中医药横琴实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对中医诊断难以量化的问题，提出UFMD框架统一多模态数据，并构建LingLan-14B模型模拟望闻问切流程，诊断准确率相对提升103.5%，F1达82%。
AI 中文摘要
尽管人工智能（AI）日益变革现代医学，但其在中医（TCM）中的整合相对缓慢，这主要归因于中医依赖整体性、主观性的诊断方法——即望、闻、问、切（I-AOI-P）——这些方法难以与量化、标准化的医疗体系对齐。在本工作中，我们提出了一种多模态数据统一框架（UFMD），该框架自动将舌象和脉象图像处理为结构化的、临床标准的描述，将多源诊断信息整合到I-AOI-P过程的统一数字记录中。基于这些结构化数据，我们构建了LingLan-14B，一个通过监督学习微调的中医专用大语言模型，以模拟I-AOI-P过程的诊断逻辑和工作流程。实验结果表明，我们的方法显著提升了诊断准确性，相对基线实现了103.5%的提升（62.72%对比30.82%），并达到了高达82%的F1分数。
英文摘要
Though artificial intelligence (AI) increasingly transforms modern medicine, its integration into Traditional Chinese Medicine (TCM) has been relatively slow, primarily due to TCM's reliance on holistic, subjective diagnostic methods---namely Inspection, Auscultation and Olfaction, Inquiry, and Palpation(I-AOI-P)---which are difficult to align with quantitative, standardized medical systems. In this work, we introduce a Unification Framework for Multimodal Data (UFMD), which automatically processes tongue and pulse images into structured, clinically standard descriptions, integrating multi-source diagnostic information into a unified digital record of I-AOI-P process. Building on this structured data, we create LingLan-14B, a TCM-specific large language model fine-tuned via supervised learning to emulate the diagnostic logic and workflow of I-AOI-P process. Experimental results show that our method significantly enhances diagnostic accuracy, achieving a relative improvement of 103.5% over the baseline (62.72% vs. 30.82%) and reaching an F1-score of up to 82%.
Comments6 pages, 5 figures
