神经网络模型和logistic回归在预测慢性阻塞性肺疾病中的应用研究  

Application of neural network model and logistic regression in the prediction of chronic obstructive pulmonary disease

作　　者：唐雨萌[1] 张岚[1] 李茜[1] 洪杰[2] 李建华 祝淑珍[1] TANG Yumeng;ZHANG Lan;LI Qian;HONG Jie;LI Jianhua;ZHU Shuzhen(Institute of Chronic and Non-communicable Disease Control and Prevention,Hubei Provincial Center for Disease Control and Prevention,Wuhan 430079,China;Gong’an Center for Disease Control and Prevention,Jingzhou,Hubei 434300,China;Yingcheng Center for Disease Control and Prevention,Xiaogan 432400,China)

机构地区：[1]湖北省疾病预防控制中心慢性病防治研究所,武汉430079 [2]湖北省公安县疾病预防控制中心 [3]湖北省应城市疾病预防控制中心

出　　处：《公共卫生与预防医学》2021年第2期12-16,共5页Journal of Public Health and Preventive Medicine

基　　金：湖北省卫生健康委面上项目(基于神经网络的湖北省慢性阻塞性肺疾病预测模型研究WJ2019M250)。

摘　　要：目的应用神经网络和logistic回归分析方法建立慢性阻塞性肺疾病(chronic obstructive pulmonary disease,COPD)数学预测模型。方法通过横断面调查收集2015年湖北省2400人的COPD流行病学资料,按7∶3的比例随机分为训练组与验证组,应用神经网络和logistic回归分别建立慢性阻塞性肺疾病预测模型,比较两个模型的预测性能。结果可用于研究的样本共1569例,其中训练组1099例,验证组470例。神经网络模型的训练组和验证组ROC曲线下面积AUC分别为0.80和0.78。logistic的训练组和验证组的AUC分别为0.75和0.74。结论将神经网络模型和logistic回归应用于COPD的预测均是可行的,其预测结果可为COPD防治提供科学依据。Objective To establish a mathematical prediction model for chronic obstructive pulmonary disease(COPD)by applying an artificial neural network(ANN)and logistic regression analysis method.Methods A cross-sectional survey was conducted in 2015 to collect epidemiological data of COPD of 2400 residents from Hubei Province.Subjects were randomized into training group and test group at a ratio of 7∶3.The prediction models of COPD were established using ANN and logistic multiple regression.The predictive performance of the two models was compared.Results Information from a total of 1569 subjects was valid and analyzed,including 1099 cases in the training group and 470 cases in the test group.The area under curve(AUC)of ANN for training group and test group was 0.80 and 0.78,respectively.The AUC of logistic regression for training group and test group was 0.75 and 0.74,respectively.Conclusion It is feasible to apply ANN and logistic regression models to predict COPD,which can provide scientific evidence for COPD prevention and treatment.

关 键 词：慢性阻塞性肺疾病 神经网络模型 LOGISTIC回归 预测研究 

分 类 号：R181[医药卫生—流行病学]