Leveraging data from wearable devices to enhance risk prediction models


About 30 million adults in the United States have diabetes, and nearly 90 million have pre-diabetes with an elevated risk of developing diabetes. Current models to predict changes in glycemic control perform poorly and do not consider daily health behaviors. Automated monitoring of these behaviors could inform enhanced risk prediction models that can detect patients likely to experience a decline in glycemic control. If such patients could be identified, effective approaches could be better targeted to improve outcomes more quickly.


We are exploring ways to use data about daily health behaviors collected by wearable devices to enhance risk prediction models. Participants in this study will be randomly assigned to use a waist-worn or wrist-worn wearable device for six months.


This study is complete. Results are forthcoming.


Center for Health Incentives and Behavioral Economics, Leonard Davis Institute of Health Economics