The COVID-19 pandemic has highlighted the important role wearable devices can play in detecting illness early. To ensure that new infections and clusters are identified before they promote viral spread, case-finding tools are needed to target diagnostic testing of individuals suspected to be infected. 

Previous research has demonstrated that there are changes in physiologic and behavioral parameters measured by wearables in the setting of influenza infection, including high resting heart rate, low heart rate variability, decreased blood oxygen saturation, disturbed sleep, decreased physical activity and changes in wear habits. Together, these “digital biomarkers” form a signature of infection. 

in April 2020, Duke launched CovIdentify, a platform that integrates information from widely used wearables with simple daily electronic self-reports on symptoms and social distancing. The objective was to implement existing digital biomarkers and establish new ones by using the new platform to develop, validate and translate CovIdentify as a continuous screening tool. Results have been positive.

Building on the work of a previous team, this project team created an online infection detection platform that populates and translates wearable data from a variety of sources in an easy-to-use manner. Team members created an iOS-based application that allows users to approve the collection of their HealthKit data for research and send it to a cloud database for analysis.

The team also created a front-end website for users to learn about the project and create accounts to share wearable device data. They are continuing to develop an Android-based application and test the scalability of their work.

Building a Platform for Wearable Device Health Data

Poster by Peining Yang, Sarah Jiang, James Wang, Phijae Chang, Shun Sakai, Ashley Chompre, Danica Bajaj, Adam Kaakati, Bill Chen, Lauren Lederer, Karnika Singh, Peter Cho, Ali Roghanizad, Jessilyn Dunn