Development,validation,and transportability of several machine-learned,non-exercise-based VO_(2max)prediction models for older adults

作     者：Benjamin T.Schumacher Michael J.LaMonte Andrea Z.LaCroix Eleanor M.Simonsick Steven P.Hooker Humberto Parada Jr. John Bellettiere Arun Kumar Benjamin T.Schumacher;Michael J.LaMonte;Andrea Z.LaCroix;Eleanor M.Simonsick;Steven P.Hooker;Humberto Parada Jr.;John Bellettiere;Arun Kumar

作者机构：Herbert Wertheim School of Public Health and Human Longevity ScienceUniversity of California San DiegoLa JollaCA 92093USA Department of Epidemiology and Environmental HealthSchool of Public Health and Health ProfessionsUniversity at Buffalo
State University of New YorkBuffaloNY 14214USA Translational Gerontology BranchIntramural Research ProgramNational Institute on AgingNational Institutes of HealthBaltimoreMD 21225USA College of Health and Human ServicesSan Diego State UniversitySan DiegoCA 92182USA Division of Epidemiology and BiostatisticsSchool of Public HealthSan Diego State UniversitySan DiegoCA 92182USA University of California San Diego Moores Cancer CenterLa JollaCA 92093USA Computer Science and Engineering and Halicioglu Data Science InstituteUniversity of California San DiegoLa JollaCA 92093USA 

出 版 物：《Journal of Sport and Health Science》 (运动与健康科学（英文）)

年 卷 期：2024年第13卷第5期

页      面：611-620页

核心收录：

学科分类：0403[教育学-体育学] 1202[管理学-工商管理] 07[理学] 0701[理学-数学] 070101[理学-基础数学] 

基　　金：supported in part by the Intramural Research Program of the National Institute on Aging supported by the National Cancer Institute(K01 CA234317) the San Diego State University/UC San Diego Comprehensive Cancer Center Partnership(U54 CA132384 and U54 CA132379) the Alzheimer's Disease Resource Center for Minority Aging Research at the University of California San Diego(P30 AG059299) 

主　　题：Cardiorespiratory fitness Prediction algorithms Epidemiology Mortality 

摘      要：Background:There exist few maximal oxygen uptake(VO_(2max))non-exercise-based prediction equations,fewer using machine learning(ML),and none specifically for older *** direct measurement of VO_(2max)is infeasible in large epidemiologic cohort studies,we sought to develop,validate,compare,and assess the transportability of several ML VO_(2max)prediction ***:The Baltimore Longitudinal Study of Aging(BLSA)participants with valid VO2_(max)tests were included(n=1080).Least absolute shrinkage and selection operator,linear-and tree-boosted extreme gradient boosting,random forest,and support vector machine(SVM)algorithms were trained to predict VO_(2max)*** developed these algorithms for:(a)the overall BLSA,(b)by sex,(c)using all BLSA variables,and(d)variables common in aging ***,we quantified the associations between measured and predicted VO_(2max)and ***:The age was 69.0±10.4 years(mean±SD)and the measured VO_(2max)was 21.6±5.9 mL/kg/*** absolute shrinkage and selection operator,linear-and tree-boosted extreme gradient boosting,random forest,and support vector machine yielded root mean squared errors of 3.4 mL/kg/min,3.6 mL/kg/min,3.4 mL/kg/min,3.6 mL/kg/min,and 3.5 mL/kg/min,*** quartiles of measured VO_(2max)showed an inverse gradient in mortality *** VO_(2max)variables yielded similar effect estimates but were not robust to ***:Measured VO_(2max)is a strong predictor of *** ML can improve the accuracy of prediction as compared to simpler approaches but estimates of association with mortality remain sensitive to *** studies should seek to reproduce these results so that VO_(2max),an important vital sign,can be more broadly studied as a modifiable target for promoting functional resiliency and healthy aging.