基于TabNet的周仲瑛教授辨治甲状腺功能亢进病机预测模型及用药规律研究  

Research on A TabNet-Based Predictive Model and Medication Patterns in the Diagnosis and Treatment of Hyperthyroidism by Professor Zhou Zhongying

作　　者：杨晓娜 朱垚[1] 幸享玲 周作建 佘侃侃[1,2] YANG Xiaona;ZHU Yao;XING Xiangling;ZHOU Zuojian;SHE Kankan(School of Artificial Intelligence and Information Technology,Nanjing University of Chinese Medicine,Nanjing 210023,China;Jiangsu Smart Traditional Chinese Medicine Health Service Engineering Research Center,Nanjing 210023,China)

机构地区：[1]南京中医药大学人工智能与信息技术学院,江苏南京210023 [2]江苏省智慧中医药健康服务工程研究中心,江苏南京210023

出　　处：《南京中医药大学学报》2024年第5期534-542,共9页Journal of Nanjing University of Traditional Chinese Medicine

基　　金：国家自然科学基金青年科学基金项目(82004498);南京中医药大学自然科学基金青年项目(NZY82004498);江苏高校“青蓝工程”优秀青年骨干教师培养计划(2022);国家级非物质文化遗产代表性项目(205Ⅸ-2);南京市非物质文化遗产代表性项目(NJⅧ-20);江苏省六大人才高峰项目(RJFW-40);江苏省科技型企业技术创新资金项目(BC2015022);江苏省卫生健康委员会项目(Z2020024)。

摘　　要：目的以周仲瑛教授治疗甲状腺功能亢进(甲亢)的临床病案为研究对象,探索运用基于神经网络的TabNet模型发现甲亢的诊疗规律,为传承名老中医学术思想、辅助临床诊疗提供方法参考。方法基于周仲瑛教授及其团队的临床甲亢诊疗医案,构建标准化、结构化训练数据,研究基于注意力机制和稀疏特征选择机制的算法,通过输入标准化临床表现,标准化舌象、脉象构建病机预测模型,分析核心症状、病机和药物以及三者之间的联系。结果通过训练好的预测模型对肝郁、肝火、痰饮、肾虚、阴虚、瘀血6个病机进行预测,与决策树、随机森林等经典算法构建的多标签分类模型相比,本模型分类和预测指标均较好。通过决策树算法进行挖掘,总结6个核心病机对应中药社团:醋柴胡、夏枯草、牡蛎、炙鳖甲、玄参、天冬、麦冬等。结论在临床医案数据上运用TabNet算法,构建基于临床表现、舌象和脉象的病机预测模型,可有效地预测核心病机,进而发现“症-机-药”之间的联系,为名老中医学术思想的传承和临床辅助诊疗决策提供方法学参考。OBJECTIVE Taking Professor Zhou Zhongying's clinical cases of treating hyperthyroidism as the research object,this article explored the use of the TabNet model based on neural networks to discover the diagnosis and treatment rules of hyperthyroidism,providing a method reference for inheriting the academic thoughts of famous veteran traditional Chinese medicine practitioners and assisting clinical diagnosis and treatment.METHODS Based on the clinical diagnosis and treatment cases of hyperthyroidism of Professor Zhou Zhongying and his team,standardized and structured training data were constructed;algorithms based on attention mechanism and sparse feature selection mechanism were studied;a pathogenesis prediction model was constructed by inputting standardized clinical manifestations,standardized tongue and pulse conditions;core symptoms,pathogenesis and medication were analyzed,as well as the relationship between the three.RESULTS The trained prediction model was used to predict the 6 pathogenesis of liver stagnation,liver fire,phlegm fluid,kidney deficiency,yin deficiency,and blood stasis.Compared with multi-label classification models constructed by classic algorithms such as decision trees and random forests,this model had better classification and prediction indicators.Mining was carried out through the decision tree algorithm,and 6 core pathogenesis corresponding Chinese medicine groups were summarized:vinegar-baked Bupleurum chinense,prunella vulgaris,oyster,processed Carapax trionycis,Scrophularia ningpoensis,Asparagus cochinchinensis,Ophiopogon japonicus,etc.CONCLUSION Using the TabNet algorithm on clinical medical record data to build a pathogenesis prediction model based on clinical manifestations,tongue and pulse conditions can effectively predict the core pathogenesis,and then discover the connection between symptoms,pathogenesis and medication,providing methodological references for the inheritance of academic ideas of famous veteran traditional Chinese medicine practitioners and clinical auxiliary di

关 键 词：甲状腺功能亢进 TabNet 神经网络 症-机-药 国医大师 周仲瑛 病机预测 用药规律 

分 类 号：R2-03[医药卫生—中医学]