Your fitness device can do something even more important than monitoring your activity and heart rate. It can provide health data crucial to tracking COVID-19 infections.

Wearable activity trackers like the Fitbit or Apple Watch can help identify cases of COVID-19 by providing data on changes in heart rate, sleep and activity levels, a study finds. Fitness tracker data used along with self-reported symptom data can make it possible to identify SARS-CoV-2 cases earlier and with greater accuracy than is possible by looking at symptoms alone.

“What's exciting here is that we now have a validated digital signal for COVID-19. The next step is to use this to prevent emerging outbreaks from spreading.”

“Roughly 100 million Americans already have a wearable tracker or smartwatch and can help us; all we need is a tiny fraction of them -- just 1 percent or 2 percent -- to use the app,” Eric Topol, director and founder of the Scripps Research Translational Institute, said in a statement.

Researchers analyzed fitness tracker data collected from people who developed symptoms and were tested for the novel coronavirus. By focusing on those with positive COVID test results, the researchers were able to get a clearer idea of the specific changes that seemed to predict COVID-19, as opposed to other illnesses.

Health data collected by wearable fitness devices enabled the team to identify whether a person who reported symptoms was likely to have COVID-19 with roughly 80 percent prediction accuracy, a significant improvement over models using only self-reported symptoms.

Over 30,000 people from all 50 states had enrolled in the study by early June 2020. More than 3800 participants reported symptoms; 54 tested positive for the coronavirus; and 279 tested negative.

Sleeping more and being less active than usual were two of the most significant predictors of coronavirus infection.

Identifying these early COVID-19 warning signs should give healthcare professionals a leg-up on the disease, making it easier to slow its spread. “We know that common screening practices for the coronavirus can easily miss pre-symptomatic or asymptomatic cases,” lead researcher, Jennifer Radin, an epidemiologist at Scripps, said. “And infrequent viral tests, with often-delayed results, don't offer the real-time insights we need to control the spread of the virus.”

The ability to quickly identify, trace and isolate infected individuals is one of the biggest hurdles to containing the pandemic. “That's the ultimate goal,” first author, Giorgio Quer, director of artificial intelligence at Scripps, said. People who are pre-symptomatic or even asymptomatic can potentially be even more infectious during this period.

“What's exciting here is that we now have a validated digital signal for COVID-19,” Topol added. “The next step is to use this to prevent emerging outbreaks from spreading.”

The study appears in Nature Medicine.