Recent advances in machine learning for maximal oxygen uptake (<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" altimg="si1.svg"><mml:mrow><mml:mi>V</mml:mi><mml:msub><mml:mi>O</mml:mi><mml:mn>2</mml:mn></mml:msub></mml:mrow></mml:math> max) prediction: A review

Maximal oxygen uptake (VO2 max) is the maximum amount of attainable by a person during exercise. VO2 max used in different domains including sports and medical sciences usually measured an incremental treadmill or cycle ergometer test. The drawback directly measuring using maximal test that it expensive requires fixed controlled protocol. During last decade, various machine learning models have been developed for prediction numerous studies attempted to predict data from submaximal non-exercise tests. This article gives overview over past five years (2016–2021) max. Multiple linear regression, support vector machine, artificial neural network multilayer perceptron are some techniques build predictive combinations predictor variables. Model performance generally assessed correlation coefficient (R-value), standard error estimate (SEE) root mean squared (RMSE), computed between ground truth predicted values. findings this review indicate ANN typically outperform other techniques. Moreover, variables model large influence on model's performance.