Using activity data from wearable devices vs. smartphones to predict hospital readmission


Many health systems are searching for ways to better predict hospital readmissions. Current approaches typically use data from inpatient admission or health insurance claims. However, neither of these measures include information on patient behaviors once they leave the hospital. Mobile technologies such as smartphones and wearable devices are growing in adoption. More than 70% of adults own a smartphone and carry it with them frequently. These devices could be used to monitor daily health behaviors.


We designed a clinical trial to use mobile technologies to obtain patient activity data to enhance readmission prediction models. Patients are randomly assigned to track activity using either a smartphone or a wearable device for six months.


The study is complete and results are being evaluated.