The 2024 Nudges in Health Care Symposium will take place September 26–27 in Philadelphia. Learn more and register



Leveraging data from wearable devices to enhance risk prediction models

Project status

Pilot/study with results


Kevin Volpp, MD, PhD 

Daniel Polsky, PhD 

Dylan Small, PhD 

Innovation leads


Center for Health Incentives and Behavioral Economics, University of Pennsylvania

Leonard Davis Institute of Health Economics, University of Pennsylvania


Nearly 90 million adults in the United States have prediabetes, with an elevated risk of developing diabetes in the future.  

Current models to predict changes in glycemic control perform poorly and do not consider daily health behaviors such as exercise. Automated monitoring of daily health behaviors could inform enhanced risk prediction models that detect patients likely to experience a decline in glycemic control. And if such patients could be identified effectively, providers would be better equipped to intervene and improve outcomes sooner. 


We conducted a randomized trial with adults with prediabetes to explore if data from wearables could help inform risk prediction models. Participants were randomly assigned to use a waist-worn or wrist-worn wearable to track activity patterns over six months. We tested three models to predict continuous changes in glycemic control during this time. Way to Health was used to administer the study. 


In all three models, prediction improved when machine learning was used vs. traditional regression, when baseline information with wearable data was used vs. baseline information alone, and when wrist-worn wearables were used vs. waist-worn wearables.  

Our findings indicate that predictive models can accurately identify changes in glycemic control among prediabetic adults and, therefore, could be leveraged to better allocate resources and target interventions to prevent the progression of diabetes. 

Way to Health Specs

Learn more about the platform
Activity monitoring
Arms and randomization
Criteria-based rules
Dashboard view
Device integration
EHR integration
Multiple languages
Patient portal messaging
Patient-reported outcomes capture
Photo messaging
Remote patient monitoring
Schedule-based rules
Survey administration
Two-way texting
Vitals monitoring