Prediction of oxygen uptake kinetics during heavy-intensity cycling exercise by machine learning analysis

Nonintrusive estimation of oxygen uptake (V̇o₂) is possible with wearable sensor technology and artificial intelligence. V̇o₂ kinetics have been accurately predicted during moderate exercise using easy-to-obtain sensor inputs. However, V̇o₂ prediction algorithms for higher-intensity exercise with inherent nonlinearities are still being refined. The purpose of this investigation was to test if a machine learning model can accurately predict dynamic V̇o₂ across exercise intensities, including slower V̇O₂ kinetics normally observed during heavy- compared with moderate-intensity exercise. Fifteen young healthy adults (seven females; peak V̇o₂: 42 ± 5 mL·min^-1·kg^-1) performed three different pseudorandom binary sequence (PRBS) exercise tests ranging in intensity from low-to-moderate, low-to-heavy, and ventilatory threshold-to-heavy work rates. A temporal convolutional network was trained to predict instantaneous V̇o₂, with model inputs including heart rate, percent heart rate reserve, estimated minute ventilation, breathing frequency, and work rate. Frequency domain analyses between V̇o₂ and work rate were used to evaluate measured and predicted V̇o₂ kinetics. Predicted V̇o₂ had low bias (-0.017 L·min^-1, 95% limits of agreement: [-0.289, 0.254]), and was very strongly correlated (r_rm = 0.974, P < 0.001) with the measured V̇o₂. The extracted indicator of kinetics, mean normalized gain (MNG), was not different between predicted and measured V̇o₂ responses (main effect: P = 0.374, η_p² = 0.01), and decreased with increasing exercise intensity (main effect: P < 0.001, η_p² = 0.64). Predicted and measured V̇o₂ kinetics indicators were moderately correlated across repeated measurements (MNG: r_rm = 0.680, P < 0.001). Therefore, the temporal convolutional network accurately predicted slower V̇o₂ kinetics with increasing exercise intensity, enabling nonintrusive monitoring of cardiorespiratory dynamics across moderate- and heavy-exercise intensities.NEW & NOTEWORTHY Machine learning analysis of wearable sensor data with a sequential model, which utilized a receptive field of approximately 3 min to make instantaneous oxygen uptake estimations, accurately predicted oxygen uptake kinetics from moderate through to higher-intensity exercise. This innovation will enable nonintrusive cardiorespiratory monitoring over a wide range of exercise intensities encountered in vigorous training and competitive sports.