基于机器学习的Cat Boost模型在预测重症手足口病中的应用  

Application of CatBoost model based on machine learning in predicting severe hand-foot-mouth disease

作　　者：王斌[1] 冯慧芬[1] 王芳[2] 秦新华 黄平[1] 党德建 赵敬 易佳音 WANG Bin;FENG Hui-fen;WANG Fang;QIN Xin-hua;HUANG Ping;DANG De -jian;ZHAO Jing;YI Jia-yin(Department of Gastroenterology,The Fifth Affiliated Hospital of Zhengzhou University,Zhengzhou 450052,China;Department of Infectious Disease,Children’s Hospital Affiliated to Zhengzhou University,Zhengzhou 450051,China;Department of Healthcare -associated Infection Control,The Fifth Affiliated Hospital of Zhengzhou University,Zhengzhou 450052,China)

机构地区：[1]郑州大学第五附属医院消化内科,河南郑州450052 [2]郑州大学附属儿童医院感染科,河南郑州450051 [3]郑州大学第五附属医院感染控制科,河南郑州450052

出　　处：《中国感染控制杂志》2019年第1期12-16,共5页Chinese Journal of Infection Control

基　　金：国家自然科学基金(81473030);河南省医学科技攻关普通项目(201403130);河南省卫生系统出国研修项目(2015065)

摘　　要：目的通过机器学习算法,探究CatBoost模型在预测重症手足口病(HFMD)中的应用价值。方法收集郑州市某医院2014年1月—2017年6月住院部诊治的2983例HFMD患儿,使用R3.4.3软件进行数据分析,构建CatBoost模型和其他普通模型,评估CatBoost模型的预测性能。结果最终构建的CatBoost模型,预测正确率可达87.6%,人工神经网络模型位居第二(83.8%),其他(决策树、支持向量机、logistic回归、贝叶斯网络)模型预测正确率<80%。CatBoost算法模型ROC曲线下面积、灵敏度、特异度均高(分别为0.866、80.80%、92.33%),其中居前3位的预测变量依次为呕吐、肢体抖动和病原学结果。结论CatBoost模型可以用于预测重症HFMD,相比于其他传统算法,具有较高的预测正确率和诊断价值。Objective To explore the value of CatBoost model in predicting severe hand-foot-mouth disease (HFMD) by the machine learning algorithm.Methods A total of 2 983 children with HFMD diagnosed and treated in a hospital in Zhengzhou from January 2014 to June 2017 were collected,data were analyzed with R 3.4.3 software,CatBoost model and other common models were constructed,prediction performance of CatBoost model was evaluated.Results The predictive accuracy of the finally constructed CatBoost model was 87.6%,artificial neural network model ranked second (83.8%),other models (decision tree,support vector machine,logistic regression,Bayesian network) had predictive accuracy less than 80%.The area under receiver operating characteristic (ROC) curve,sensitivity,and specificity of CatBoost algorithm model were all high (0.866,80.80% and 92.33% respectively),the top three predictive variables were vomiting,limb jitter,and pathogenic results.Conclusion CatBoost model can be used to predict severe HFMD,which has higher accuracy and diagnostic value than other traditional algorithms.

关 键 词：手足口病 重症手足口病 机器学习 CatBoost 预测 

分 类 号：R512.5[医药卫生—内科学]