Using ECG Data to Predict Positive Distance Running Experiences

Abstract

The feeling of going on a run can vary dramatically from person to person and even from day to day, with some runs feeling like flying and others like an uphill battle. But what causes these drastic differences in running experience, and, more importantly, is there something we can do to change this? Biomechanical parameters have been correlated with positive running experiences, while the potential relationship between ECG (heart rate) parameters and running experiences provides a promising avenue for additional discovery, due to the heart rate’s link to exercise and emotion. In this study, we investigated the relationship between ECG data and good feelings on a run in order to assess the promise of ECG data for use in a wearable biofeedback system for improving distance running experiences. Specifically, we used preliminary pilot ECG and feeling data from three runs and performed a visual time series analysis inspecting for any obvious relationships, as well as correlation testing. We found no evident relationship from visual inspection of the time series data as well as no significant correlations (maximum across all features tested had R = 0.09, p = 0.01). However, there were a variety of limiting factors in this analysis that may have inhibited our ability to discover a relationship, including novel application of preprocessing techniques and a limited data set, suggesting that additional data collection and perhaps more complex analysis methods may be needed to uncover a potential relationship.