问诊症状特征选择方法  

Methods of inquiry symptom feature selection

作　　者：陈瑞 刘璐 张春柯 王忆勤[1,2] 燕海霞 郭睿[1,2] CHEN Rui;LIU Lu;ZHANG Chun-ke;WANG Yi-qin;YAN Hai-xia;GUO Rui(School of Basic Medicine,Shanghai University of Traditional Chinese Medicine,Shanghai 201203,China;Shanghai Key Laboratory of Health Identification and Evaluation,Shanghai 201203,China)

机构地区：[1]上海中医药大学基础医学院,上海201203 [2]上海市健康辨识与评估重点实验室,上海201203

出　　处：《中华中医药杂志》2021年第4期2161-2164,共4页China Journal of Traditional Chinese Medicine and Pharmacy

基　　金：国家自然科学基金项目(No.81302913,No.81673880,No.82074332);上海市科学技术委员会科研计划(No.19441901100);上海市中医药科技创新项目(No.ZYKC201701017)。

摘　　要：问诊是中医四诊之一,是获取患者生理病理信息的重要途经。随着中医四诊客观化、标准化研究的不断推进,中医问诊建模工程迫在眉睫。实际上,问诊建模就是从海量的问诊信息中获取最佳的特征子集,这一过程的实现本质上就是特征选择的结果。随着数据挖掘、机器学习等领域不断地深入研究,特征选择方法层出不穷,文章就问诊特征选择方法研究做一论述,以冀对中医问诊客观化、标准化研究有所帮助。Inquiry is one of the four diagnoses of traditional Chinese medicine,and it is an important way to obtain the physiological and pathological information of patients.With the development of the research on the objective standardization of the four diagnostic methods of traditional Chinese medicine,the modeling project of the four diagnostic methods of traditional Chinese medicine is imminent.In fact,inquiry modeling is to obtain the best feature subset from the mass of inquiry information.The realization of this process is essentially the result of feature selection.With the continuous in-depth research in data mining,machine learning and other fields,feature selection methods emerge in endlessly.This paper makes a discussion on the research of feature selection methods in order to help the research of objective standardization of traditional Chinese medicine.

关 键 词：问诊 症状 特征选择 方法 中医 诊断 

分 类 号：R241[医药卫生—中医诊断学]