Temporal convolutional networks predict dynamic oxygen uptake response from wearable sensors across exercise intensities

Oxygen consumption (VO2) provides established clinical and physiological indicators of cardiorespiratory function and exercise capacity. However, VO2 monitoring is largely limited to specialized laboratory settings, making its widespread monitoring elusive. Here, we investigate temporal prediction of VO2 from wearable sensors during cycle ergometer exercise using a temporal convolutional network (TCN). Cardiorespiratory signals were acquired from a smart shirt with integrated textile sensors alongside ground-truth VO2 from a metabolic system on twenty-two young healthy adults. Participants performed one ramp-incremental and three pseudorandom binary sequence exercise protocols to assess a range of VO2 dynamics. A TCN model was developed using causal convolutions across an effective history length to model the time-dependent nature of VO2. Optimal history length was determined through minimum validation loss across hyperparameter values. The best performing model encoded 218 s history length (TCN-VO2 A), with 187 s, 97 s, and 76 s yielding less than 3% deviation from the optimal validation loss. TCN-VO2 A showed strong prediction accuracy (mean, 95% CI) across all exercise intensities (-22 ml.min-1, [-262, 218]), spanning transitions from low-moderate (-23 ml.min-1, [-250, 204]), low-high (14 ml.min-1, [-252, 280]), ventilatory threshold-high (-49 ml.min-1, [-274, 176]), and maximal (-32 ml.min-1, [-261, 197]) exercise. Second-by-second classification of physical activity across 16090 s of predicted VO2 was able to discern between vigorous, moderate, and light activity with high accuracy (94.1%). This system enables quantitative aerobic activity monitoring in non-laboratory settings across a range of exercise intensities using wearable sensors for monitoring exercise prescription adherence and personal fitness.