A comparative study of antihypertensive drugs prediction models for the elderly based on machine learning algorithms

作者全名："Wang, Tiantian; Yan, Yongjie; Xiang, Shoushu; Tan, Juntao; Yang, Chen; Zhao, Wenlong"

作者地址："[Wang, Tiantian; Yang, Chen; Zhao, Wenlong] Chongqing Med Univ, Sch Med Informat, Chongqing, Peoples R China; [Yan, Yongjie] Army Med Univ, Med Records & Stat Off, Affiliated Hosp 3, Chongqing, Peoples R China; [Xiang, Shoushu] Chongqing Med Univ, Affiliated Banan Hosp, Med Records & Stat Room, Chongqing, Peoples R China; [Tan, Juntao] Chongqing Med Univ, Operat Management Off, Affiliated Banan Hosp, Chongqing, Peoples R China"

通信作者："Zhao, WL (通讯作者)，Chongqing Med Univ, Sch Med Informat, Chongqing, Peoples R China."

来源：FRONTIERS IN CARDIOVASCULAR MEDICINE

ESI学科分类：　

WOS号：WOS:000898425800001

JCR分区：Q2

影响因子：3.6

年份：2022

卷号：9

期号：　

开始页：　

结束页：　

文献类型：Article

关键词：elderly hypertension; ML; LightGBM; personalized medicine; antihypertensive drug

摘要："BackgroundGlobally, blood pressure management strategies were ineffective, and a low percentage of patients receiving hypertension treatment had their blood pressure controlled. In this study, we aimed to build a medication prediction model by correlating patient attributes with medications to help physicians quickly and rationally match appropriate medications. MethodsWe collected clinical data from elderly hypertensive patients during hospitalization and combined statistical methods and machine learning (ML) algorithms to filter out typical indicators. We constructed five ML models to evaluate all datasets using 5-fold cross-validation. Include random forest (RF), support vector machine (SVM), light gradient boosting machine (LightGBM), artificial neural network (ANN), and naive Bayes (NB) models. And the performance of the models was evaluated using the micro-F1 score. ResultsOur experiments showed that by statistical methods and ML algorithms for feature selection, we finally selected Age, SBP, DBP, Lymph, RBC, HCT, MCHC, PLT, AST, TBIL, Cr, UA, Urea, K, Na, Ga, TP, GLU, TC, TG, gamma-GT, Gender, HTN CAD, and RI as feature metrics of the models. LightGBM had the best prediction performance with the micro-F1 of 78.45%, which was higher than the other four models. ConclusionLightGBM model has good results in predicting antihypertensive medication regimens, and the model can be beneficial in improving the personalization of hypertension treatment."

基金机构："College of Medical Informatics, Chongqing Medical University, China, Student Research and Innovation Experiment Project [YJSZHYX202120]"

基金资助正文："This study has been financially supported by the College of Medical Informatics, Chongqing Medical University, China, Student Research and Innovation Experiment Project (YJSZHYX202120)."