摘要
目的本研究旨在利用中医临床医案数据和知识蒸馏技术,构建具备推理能力强、可信度高的中医辨证论治智能诊疗模型。方法以GPT4o为教师模型,对中医医案数据进行知识蒸馏,生成高质量的中医辨证论治指令数据集,并基于Qwen2.5-7b模型采用LoRA方法进行监督微调,以增强其中医诊疗推理能力和个体化辨证论治能力。结果本研究提出的知识蒸馏微调方法大幅提升了中医诊疗推理过程的透明性和可解释性,并保留处方推荐的精准性,表明模型生成的文本可读性更高,诊疗推理能力更强。结论采用知识蒸馏的中医辨证论治大模型能有效提升诊疗推理和个体化辨证论治能力,为中医智能化诊疗和临床辅助决策提供了新思路。
Objective This study aims to develop an intelligent diagnosis model for Traditional Chinese Medicine(TCM)syndrome differentiation and treatment with strong reasoning capabilities and high reliability,using clinical case data and knowledge distillation techniques.Methods The GPT4o was employed as the teacher model to perform knowledge distillation on TCM clinical case data,thereby generating a high-quality TCM syndrome differentiation instruction dataset.Subsequently,the Qwen2.5-7b model was fine-tuned using the LoRA method under supervised learning to enhance its reasoning ability in TCM diagnosis and individualized syndrome differentiation.Results The proposed knowledge distillation fine-tuning approach significantly improved the transparency and interpretability of the TCM diagnostic reasoning process,while maintaining the precision of prescription recommendations.The results indicate that the generated text has higher readability and that the model exhibits stronger diagnostic reasoning capabilities.Conclusion The TCM model enhanced by knowledge distillation effectively improves diagnostic reasoning and individualized syndrome differentiation,offering a novel approach for intelligent TCM diagnosis and clinical decision support.
作者
王欣宇
杨涛
孙晓荷
谢佳东
章益烔
胡孔法
WANG Xinyu;YANG Tao;SUN Xiaohe;XIE Jiadong;ZHANG Yitong;HU Kongfa(School of Artificial Intelligence and Information Technology,Nanjing University of Chinese Medicine,Nanjing 210023,China;Dept of Information Management,Nanjing University,Nanjing 210023,China;Jiangsu Provincial Research Institute of Chinese Medicine Schools,Nanjing 210023,China;School of First Clinical Medical,Nanjing University of Chinese Medicine,Nanjing 210023,China;Jiangsu Provincial Engineering Research Centre for Intelligent Traditional Chinese Medicine Health Services,Nanjing 210023,China;Tang Zhongying Traditional Chinese Medicine Epidemic Disease Research Centre at Nanjing University of Chinese Medicine,Nanjing 210023,China)
出处
《世界科学技术-中医药现代化》
北大核心
2026年第1期296-304,共9页
Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology
基金
国家自然科学基金委员会面上项目(82575255):融合多模态知识图谱和大模型的中医辨证论治智能方法研究,负责人:胡孔法
江苏省前沿技术研发计划(BF2025076):中医垂直领域大模型关键技术研发,负责人:胡孔法
江苏省研究生科研创新计划(KYCX25_2342):基于大模型技术的中医智能辅助诊疗方法研究,负责人:王欣宇。
关键词
中医
辨证论治
大语言模型
知识蒸馏
监督微调
Traditional Chinese medicine
Syndrome differentiation and treatment
Large language model
Knowledge distillation
Supervised fine-tuning
