Data Science Faculty Highlight: Jessilyn Dunn and Wearables for Early COVID-19 Detection

By Rabail Baig

The COVID + Data Science Virtual Seminar Series took place across 8 weeks during the summer, from late June through late August 2020. The virtual sessions covered a wide breadth of topics, reflecting the diversity of COVID-related research and activity at Duke.

In the final lecture of the series, which focused on using wearables for early COVID-19 detection, Duke Biomedical Engineering assistant professor Jessilyn Dunn, PhD, discussed how her Big Ideas Lab at Duke is using data from smart phones, smart watches, fitness trackers and other wearable devices to create a screening system for COVID-19.

Jessilyn Dunn, Assistant Professor of Biomedical Engineering

Jessilyn Dunn, PhD, in her office with a display of data from a wearable health monitoring device

The Duke CovIdentify Study, a new and unique research initiative funded by the Duke Clinical & Translational Science Institute, Duke Bass Connections, and Duke MEDx, is primarily a feasibility study to explore the potential of wearables to detect COVID-19 infection.

“CovIdentify is an effort to detect COVID-19 infection early via a person’s fitness tracker or smart phone through daily surveys that take less than 30 seconds to complete,” said Dunn as she introduced the study during her talk. According to Dunn, the CovIdentify study now has more than 5,500 participants from the U.S. and from across the globe.

“The study is helping us get a picture of not only what COVID-19 might look like in super fit populations in certain regions but also people who might purchase wearable devices for other reasons, and may give us a better picture of how our average U.S. citizen or global citizen is faring.”

As our understanding of COVID-19 continues to evolve, Dunn’s team at the Duke Big Ideas Lab has been adjusting the survey setup to accommodate new developments. Ever since its inception, the lab’s overarching role has been to develop and test tools and infrastructure using biomedical and health data for early detection, intervention, and prevention of various diseases. These valuable tools are now being applied to COVID-19 research.

“We want to translate the work we are doing into the development of digital biomarkers of COVID-19,” said Dunn. “Given that we have been successful with developing digital biomarkers for other types of infections, we can adapt those to early detection and monitoring of COVID-19 over time and potentially even more broadly to public health monitoring.”

Dunn sees the ongoing pandemic as a “massive opportunity” for scientists and researchers to use COVID-19 as a learning experience to develop wearable technologies that can be scaled up for population-level disease detection.

“There are preexisting technologies that we have at our fingertips to try and curb the spread of COVID-19,” notes Dunn. “Wearables can provide us the opportunity to automate triage to get the most urgent care to the people who need it the most at the right moment in time.”