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

Autor: Schumacher BT; Herbert Wertheim School of Public Health and Human Longevity Science, University of California San Diego, La Jolla, CA 92093, USA. Electronic address: BTS70@pitt.edu., LaMonte MJ; Department of Epidemiology and Environmental Health, School of Public Health and Health Professions, University at Buffalo-State University of New York, Buffalo, NY 14214, USA., LaCroix AZ; Herbert Wertheim School of Public Health and Human Longevity Science, University of California San Diego, La Jolla, CA 92093, USA., Simonsick EM; Translational Gerontology Branch, Intramural Research Program, National Institute on Aging, National Institutes of Health, Baltimore, MD 21225, USA., Hooker SP; College of Health and Human Services, San Diego State University, San Diego, CA 92182, USA., Parada H Jr; Division of Epidemiology and Biostatistics, School of Public Health, San Diego State University, San Diego, CA 92182, USA; University of California San Diego Moores Cancer Center, La Jolla, CA 92093, USA., Bellettiere J; Herbert Wertheim School of Public Health and Human Longevity Science, University of California San Diego, La Jolla, CA 92093, USA., Kumar A; Computer Science and Engineering and Halicioglu Data Science Institute, University of California San Diego, La Jolla, CA 92093, USA.
Jazyk: angličtina
Zdroj: Journal of sport and health science [J Sport Health Sci] 2024 Sep; Vol. 13 (5), pp. 611-620. Date of Electronic Publication: 2024 Feb 29.
DOI: 10.1016/j.jshs.2024.02.004
Abstrakt: Background: There exist few maximal oxygen uptake (VO 2max ) non-exercise-based prediction equations, fewer using machine learning (ML), and none specifically for older adults. Since 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 algorithms.
Methods: The Baltimore Longitudinal Study of Aging (BLSA) participants with valid VO 2max 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 values. We developed these algorithms for: (a) the overall BLSA, (b) by sex, (c) using all BLSA variables, and (d) variables common in aging cohorts. Finally, we quantified the associations between measured and predicted VO 2max and mortality.
Results: The age was 69.0 ± 10.4 years (mean ± SD) and the measured VO 2max was 21.6 ± 5.9 mL/kg/min. Least 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, respectively. Incremental quartiles of measured VO 2max showed an inverse gradient in mortality risk. Predicted VO 2max variables yielded similar effect estimates but were not robust to adjustment.
Conclusion: Measured VO 2max is a strong predictor of mortality. Using ML can improve the accuracy of prediction as compared to simpler approaches but estimates of association with mortality remain sensitive to adjustment. Future 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.
(Copyright © 2024. Production and hosting by Elsevier B.V.)
Databáze: MEDLINE
Externí odkaz: