基于机器学习的慢性阻塞性肺疾病急性加重预测模型的研究  

Prediction model of acute exacerbation of chronic obstructive pulmonary disease based on machine learning

作　　者：张博超 杨朝 郭立泉 陈静[1,2] 熊大曦[1,2] ZHANG Bochao;YANG Zhao;GUO Liquan;CHEN Jing;XIONG Daxi(School of Biomedical Engineering(Suzhou),Division of Life Sciences and Medicine,University of Science and Tech‐nology of China,Hefei,Anhui 230026,China;Suzhou Institute of Biomedical Engineering and Technology,Chinese Academy of Sciences,Suzhou,Jiangsu 215163,China;Respiratory Department,the Affiliated Suzhou Science and Technology Town Hospital of Nanjing Medical University,Suzhou,Jiangsu 215163,China)

机构地区：[1]中国科学技术大学生物医学工程学院(苏州)生命科学与医学部,安徽合肥市230026 [2]中国科学院苏州生物医学工程技术研究所,江苏苏州市215163 [3]南京医科大学附属苏州科技城医院呼吸内科,江苏苏州市215163

出　　处：《中国康复理论与实践》2022年第6期678-683,共6页Chinese Journal of Rehabilitation Theory and Practice

基　　金：江苏省自然科学基金项目(No.BK20201183);苏州市临床重点病种诊疗技术专项(No.LCZX201931);江苏省"双创人才"项目(No.JSSCRC2021568)。

摘　　要：目的 针对慢性阻塞性肺疾病急性加重期(AECOPD)患者肺功能检测存在误差大、准确性差的问题,开发AECOPD患者的肺功能预测模型,通过比较不同机器学习模型的预测性能,找到最优的模型。方法 选取2018年1月至2020年2月南京医科大学附属苏州科技城医院不同患病程度的慢性阻塞性肺疾病(COPD)患者90例。利用6种机器学习算法(K-最近邻、逻辑回归、支持向量机、朴素贝叶斯、决策树和随机森林)建立预测分类模型,比较受试者工作特征曲线下面积(AUC-ROC)和准确性。采用10折交叉验证对数据集进行验证。结果 基于随机森林的模型相较于其他模型预测性能最佳,准确率达到0.844,AUC-ROC为0.916。结论 基于随机森林的预测模型能够辅助临床医生在难以给出确切诊断时提供决策支持。Objective In view of the problems of large errors and poor accuracy in pulmonary function testing in patients with acute exacerbation of chronic obstructive pulmonary disease(AECOPD),a predictive classification model of pulmonary function in patients with AECOPD was proposed by comparing the prediction performance of different machine learning models to find the optimal model.Methods From January,2018 to February,2020,90 patients with different degrees of COPD from the Affiliated Suzhou Science and Technology Town Hospital of Nanjing Medical University were collected.Six machine learning model algorithms(K-nearest neighbor,logistic regression,support vector machine,naive Bayes,decision tree and random forest) were used to establish AECOPD predictive classification models.Their area under the curve of receiver operating characteristic(AUC-ROC) and accuracy were compared.Ten-fold cross-validation method was used to validate the data set.Results The model based on random forest worked best in predicting and classifying AECOPD patients,with an accuracy rate of 0.844 and an AUC-ROC of 0.916.Conclusion Random forest-based predictive model is a powerful tool for identifying patients with AECOPD,providing decision support when it is difficult to give a definitive diagnosis.

关 键 词：慢性阻塞性肺疾病 急性加重期 机器学习 预测模型 

分 类 号：R562.2[医药卫生—呼吸系统]