1.南京中医药大学附属南京市中医院, 江苏省南京市秦淮区大明路157号,210022
2.江苏省中医药管理局
3.江苏省卫生健康信息中心
51422503@qq.com
收稿:2025-09-17,
修回:2026-01-16,
纸质出版:2026-04-02
移动端阅览
朱雨欣,赵莉萍,陆家发等.基于多模态大模型的多中心中医肛肠优势病种专病数据平台的构建与应用[J].中医杂志,2026,67(07):770-775.
ZHU Yuxin,ZHAO Liping,LU Jiafa,et al.Construction and Application of a Multicenter Traditional Chinese Medicine Proctology Disease Data Platform Based on Multimodal Large Models[J].Journal of Traditional Chinese Medicine,2026,67(07):770-775.
朱雨欣,赵莉萍,陆家发等.基于多模态大模型的多中心中医肛肠优势病种专病数据平台的构建与应用[J].中医杂志,2026,67(07):770-775. DOI: 10.13288/j.11-2166/r.2026.07.012.
ZHU Yuxin,ZHAO Liping,LU Jiafa,et al.Construction and Application of a Multicenter Traditional Chinese Medicine Proctology Disease Data Platform Based on Multimodal Large Models[J].Journal of Traditional Chinese Medicine,2026,67(07):770-775. DOI: 10.13288/j.11-2166/r.2026.07.012.
构建基于多模态大模型的混合痔中医专病数据集平台并对其进行初步应用验证。平台采用StarRocks建立四级数据仓库体系,实现多源异构数据的汇聚、清洗与标准化;以DeepSeek-R1-Distill-Qwen-7B大模型为基座,通过低秩自适应(LoRA)技术进行领域微调,结合LLaMA-3.3自然语言处理与思维链技术,实现对非结构化中医病历的智能解析与结构化提取,准确识别症状、证候等6大类、28子类实体,微调后模型F1值达93.8%。平台建立了包含超5万份病历的高质量专病数据集,并已应用于一项涉及17 831例患者的真实世界研究,初步验证了中医传承手术的疗效。
This paper has constructed a traditional Chinese medicine (TCM) specialized disease dataset platform for mixed hemorrhoids based on a multimodal large model, and the preliminary application has been validated. The platform uses StarRocks to establish a four-level data warehouse system, enabling the aggregation, cleaning, and standardization of multi-source heterogeneous data. Using DeepSeek-R1-Distill-Qwen-7B as the base model, domain fine-tuning is performed through low-rank adaptation (LoRA) technology. Combined with LLaMA-3.3 natural language processing and reasoning chain techniques, the platform enables intelligent parsing and structured extraction of unstructured TCM medical records. It accurately identifies six major categories and 28 subcategories of entities, including symptoms and syndromes, with a fine-tuned model F1 score of 93.8%. The platform has established a high-quality specialized disease dataset containing more than 50
000 medical records and has been applied in a real-world study involving 17
831 patients, preliminarily verifying the efficacy of TCM heritage surgery.
李冠路 , 高记华 , 徐丹阳 , 等 . 中医硬化注射疗法治疗肛肠疾病现状与进展 [J]. 中华中医药杂志 , 2022 , 37 ( 6 ): 3351 - 3355 .
杨会举 , 刘佃温 . 复方黄柏液涂剂治疗混合痔临床应用专家共识(2025年) [J]. 中国新药杂志 , 2025 , 34 ( 19 ): 2122 - 2128 .
中国中西医结合学会大肠肛门病专业委员会 . 中国痔病诊疗指南(2020) [J]. 结直肠肛门外科 , 2020 , 26 ( 5 ): 519 - 533 .
VAN TOL RR , KLEIJNEN J , WATSON AJM , et al . European Society of ColoProctology: guideline for haemorrhoidal disease [J]. Colorectal Dis , 2020 , 22 ( 6 ): 650 - 662 .
KONG X , PENG R , DAI H , et al . Disease-specific data processing: an intelligent digital platform for diabetes based on model prediction and data analysis utilizing big data technology [J]. Front Public Health , 2022 , 10 : 1053269 . doi: 10.3389/fpubh.2022.1053269 http://dx.doi.org/10.3389/fpubh.2022.1053269 .
OMIYE JA , GUI H , REZAEI SJ , et al . Large language models in medicine: the potentials and pitfalls : a narrative review [J]. Ann Intern Med , 2024 , 177 ( 2 ): 210 - 220 .
JIA J , NISHI H . A flexible two-stage anonymization framework for narrative medical records adapting to various language models [J]. Comput Biol Med , 2025 , 195 : 110624 . doi: 10.1016/j.compbiomed.2025.110624 http://dx.doi.org/10.1016/j.compbiomed.2025.110624 .
BÜTTNER M , LESER U , SCHNEIDER L , et al . Natural language processing: chances and challenges in dentistry [J]. J Dent , 2024 , 141 : 104796 . doi: 10.1016/j.jdent. 2023.104796 http://dx.doi.org/10.1016/j.jdent.2023.104796 .
JIA Q , ZHANG D , YANG S , et al . Traditional Chinese medicine symptom normalization approach leveraging hierarchical semantic information and text matching with attention mechanism [J]. J Biomed Inform , 2021 , 116 : 103718 . doi: org/10.1016/j.jbi.2021.103718 http://dx.doi.org/org/10.1016/j.jbi.2021.103718 .
YANG X , LI S , SHAO Q , et al . Uncertainty-guided man-machine integrated patient-specific quality assurance [J]. Radiother Oncol , 2022 , 173 : 1 - 9 . doi: 10.1016/j.radonc.2022.05.016 http://dx.doi.org/10.1016/j.radonc.2022.05.016 .
DUBEY S , CHAN A , ADEBAJO AO , et al . Artificial intelligence and machine learning in rheumatology [J]. Rheumatology (Oxford) , 2024 , 63 ( 8 ): 2040 - 2041 .
HANNA MG , PANTANOWITZ L , DASH R , et al . Future of artificial intelligence-machine learning trends in pathology and medicine [J]. Mod Pathol , 2025 , 38 ( 4 ): 100705 .
GHOLAP AD , UDDIN MJ , FAIYAZUDDIN M , et al . Advances in artificial intelligence for drug delivery and development: a comprehensive review [J]. Comput Biol Med , 2024 , 178 : 108702 . doi: org/10.1016/j.compbiomed. 2024.108702 http://dx.doi.org/org/10.1016/j.compbiomed.2024.108702 .
SWEENEY SM , HAMADEH HK , ABRAMS N , et al . Challenges to using big data in cancer [J]. Cancer Res , 2023 , 83 ( 8 ): 1175 - 1182 .
中华医学会临床流行病学和循证医学分会中医学组 . 新时代中医药临床研究方法论专家共识 [J]. 协和医学杂志 , 2022 , 13 ( 5 ): 783 - 788 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010102007558号