Machine learning prediction of pulmonary oxygen uptake from muscle oxygen in cycling

The purpose of this study was to test whether a machine learning model can accurately predict VO₂ across different exercise intensities by combining muscle oxygen (MO₂) 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 VO₂, with model inputs including heart rate, MO₂ in the left (LM) and right legs (RM). All models demonstrated equivalent results, with the accuracy of predicting VO₂ at different exercise intensities varying among different models. The LM+RM+HR model performed the best across all intensities, with low bias in predicted VO₂ for all intensity exercises (0.08 ml/kg/min, 95% limits of agreement: -5.64 to 5.81), and a very strong correlation (r = 0.94, p < 0.001) with measured VO₂. Furthermore, the accuracy of predicting VO₂ using LM+HR or RM+HR was higher than using LM+RM, and higher than the accuracy of predicting VO₂ using LM, RM, or HR alone. This study demonstrates the potential of a machine learning model combining MO₂ and HR to predict VO₂ with minimal bias, achieving accurate predictions of VO₂ for different intensity levels of exercise.