Relationship Between Intensive Passive Data Signals and Patterns of Binge-Eating Behaviors: From a Dynamical-System Approach.

Abstract

In this study, we investigate using passive data, specifically, heart rate and actigraphy, for individuals with binge-type eating disorders such as bulimia nervosa (BN) and binge-eating disorder (BED). By applying dynamical-system theory and incorporating advancements in technology-based health care, we explored the relationship between passive data patterns as potential indicators of binge-eating episodes. Over 30 days, 1,019 participants with BN or BED symptoms used the Recovery Record app on iPhone and Apple Watches for real-time eating-behavior logging. Apple Watches simultaneously recorded heart rate and actigraphy. Results show no marked difference in heart and step averages 2 hr before a binge versus a control period. However, significant momentum and stability differences emerged when examining the changing dynamics leading up to a binge event. These findings suggest that the stability of step, rather than their average value, may serve as a detectable indicator of approaching binge events.