The quest for a COVID-19 digital warning system taps smartwatches, rings and more

A set of so-called “digital biomarkers”—based on nearly imperceptible changes and patterns within a person’s vital sign and activity data, and signals that are more easily separated from the noise by computers than the naked eye—could be used as an early warning system for COVID-19 and its more-obvious symptoms.

Several companies and institutions are pursuing the prospect. Most recently Empatica, a spinoff out of MIT’s Media Lab, inked an agreement with the U.S. Biomedical Advanced Research and Development Authority, known as BARDA, to help prove its wearable sensors and algorithms could work against the coronavirus pandemic.

Empatica previously picked up an FDA clearance for its seizure-detecting smartwatch, Embrace, designed to alert family members and caregivers if it senses physical convulsions. 

Now its medical-grade Aura smartwatch-based system will be tested in the real world, worn by frontline healthcare workers for 30 days and matched up with daily COVID-19 swab tests. The goal is to spot the earliest possible signs that the virus is active and multiplying, with the potential to be spread to others before a person shows respiratory symptoms.

"We anticipate that access to real-time and actionable health information will empower people to seek medical advice and care sooner, or to adopt behavioral changes such as temporary self-isolation that can help reduce the spread of COVID-19 and similar infections,” BARDA’s acting director, Gary Disbrow, said in a statement. Empatica previously began working with BARDA on a digital biomarker project for respiratory infections in February 2019.

RELATED: BARDA taps Evidation Health to digitally monitor healthcare workers for early COVID-19 symptoms

And earlier this month, BARDA began funding similar efforts by Evidation Health, along with backing from the Bill & Melinda Gates Foundation. Evidation has already recruited tens of thousands of study participants through its virtual research app, to also explore the pandemic’s broader impact.

Meanwhile, researchers at Duke University recently expanded their study to sift through the data collected from smartphones, Apple Watches and other devices for any potential signs of the novel coronavirus.

First launched in early April, the CovIdentify project examines changes in a person’s sleep schedule, oxygen level, activity and heart rate. Now, the researchers will deliver devices and a dedicated app to underserved communities, through partnerships with Garmin and Fitbit.

“One of our goals is to expand our data collection capabilities, which will increase our ability to differentiate the COVID-19 infection from other illnesses,” said Ryan Shaw, an associate professor of nursing and director of the university’s Health Innovation Lab. “This differentiation is going to be key, as we expect to see waves of resurgence pop up as the country opens back up, and some of these flare-ups may coincide with flu season.”

RELATED: BARDA loses leader in middle of race to create COVID-19 vaccine

The researchers aim to recruit and follow people at a high risk of contracting the disease through the next year, such as delivery drivers, grocery store workers, nurse aids and hospital cleaning and cafeteria staff. They also plan to deploy the devices in high-density housing like nursing homes, college dorms, military barracks and homeless shelters. 

“The iOS app will ideally simplify the sign-up and survey process, and it expands the tools we can work with,” said Jessilyn Dunn, an assistant professor of biomedical engineering. “The CovIdentify app will be able to pull data from any device that syncs with the Apple Healthkit application, which is a standard app on all iPhones.”

Elsewhere, Oura is looking to leverage its activity-tracking smart ring, in a national study run by West Virginia University’s Rockefeller Neuroscience Institute. Together, they have begun monitoring at least 600 healthcare workers for early warning signs. In late May, they said their digital model could potentially predict the onset of the virus up to three days ahead with 90% accuracy.

Oura is also pursuing studies with the University of California San Francisco and the Scripps Research Institute, and will also distribute its wearable to quarantined NBA players, to track their health signs such as body temperature and heart rate through the upcoming season, according to reports.