Fitness Tracker Data May Predict COVID-19 Better Than Symptoms Alone
When it comes to potential COVID-19 cases, doctors generally ask whether the patient was in contact with someone known to have the disease, what symptoms they're experiencing, and — when possible — they collect a nasal swab to test for the virus. Unfortunately, many people still struggle to get access to testing, which leaves doctors to evaluate potential cases based on symptoms alone — and that's where fitness tracker data may prove useful.
Fitness trackers, including smartwatches that feature fitness and activity-tracking capabilities, collect a variety of data throughout the day and night that can shed light on one's health, including any changes that may hint at a condition. A number of studies have evaluated fitness tracker data for its potential to reveal underlying concerns.
The latest study of this sort comes from Scripps Research Institute, which evaluated fitness tracker data to determine whether it is useful for predicting whether someone will test positive for COVID-19. The results are in and the answer is yes, according to an announcement from the institute, which says that it launched its DETECT study on March 25.
The DETECT study involved a mobile app that fitness tracker owners in the US could voluntarily use to contribute data for the researchers. Based on that data, in addition to self-reported symptoms, the study found that some of the changes detected by wearables improved COVID-19 prediction when compared to evaluation based on symptoms alone.
Scripps Research executive VP Eric Topol, MD, explained:
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.
The study predicted COVID-19 with around 80-percent accuracy, with things like getting more sleep and less activity than usual correlating to a higher likelihood of infection.