Machine learning prediction of pulmonary oxygen uptake from muscle oxygen in cycling.
Journal:
Journal of sports sciences
PMID:
39109877
Abstract
The purpose of this study was to test whether a machine learning model can accurately predict VO across different exercise intensities by combining muscle oxygen (MO) with heart rate (HR). Twenty young highly trained athletes performed the following tests: a ramp incremental exercise, three submaximal constant intensity exercises, and three severe intensity exhaustive exercises. A Machine Learning model was trained to predict VO, with model inputs including heart rate, MO in the left (LM) and right legs (RM). All models demonstrated equivalent results, with the accuracy of predicting VO at different exercise intensities varying among different models. The LM+RM+HR model performed the best across all intensities, with low bias in predicted VO for all intensity exercises (0.08 ml/kg/min, 95% limits of agreement: -5.64 to 5.81), and a very strong correlation ( = 0.94, < 0.001) with measured VO. Furthermore, the accuracy of predicting VO using LM+HR or RM+HR was higher than using LM+RM, and higher than the accuracy of predicting VO using LM, RM, or HR alone. This study demonstrates the potential of a machine learning model combining MO and HR to predict VO with minimal bias, achieving accurate predictions of VO for different intensity levels of exercise.