Estimating Personal Resting Heart Rate from Wearable Biosensor Data

Abstract

To date, there has not been a comprehensive evaluation of how to best characterize resting heart rate (RHR), which varies over time and between individuals with different activity/rest habits. Current methods for obtaining RHR require hands-on clinical measurements or utilize proprietary methods based on wearable device data. To increase the accessibility of RHR as a digital biomarker and to move toward a standardized and consistent RHR calculation method, we propose a novel model for estimating personal RHR from consumer wearable device data. Motivated by previous literature on how the magnitude and deviation of heart rate changes with different physical activity levels, this model uses optimal daytime activity-related parameter values to estimate RHR. Additionally, we propose several metrics for evaluating this model and conclude that our model contributes a reasonable starting point for systematically estimating personal RHR from wearable biosensor data.