Modeling Heart Rate Response to Exercise with Wearable Data

This paper was accepted at the workshop "Learning from Time Series for Health" at NeurIPS 2022.

Heart rate (HR) dynamics in response to workout intensity and duration measure key aspects of an individual’s fitness and cardiorespiratory health. Models of exercise physiology have been used to characterize cardiorespiratory fitness in well-controlled laboratory settings, but face additional challenges when applied to wearables in noisy, real-world settings. Here, we introduce a hybrid machine learning model that combines a physiological model of HR and demand during exercise with neural network embeddings in order to learn user-specific fitness parameters. We apply this model at scale to a large set of workout data collected with wearables. We show this model can accurately predict HR response to exercise demand in new workouts. We further show that the learned embeddings correlate with traditional metrics that reflect cardiorespiratory fitness.