Studies on COVID-19 detecting smartwatches haven't produced reliable data

Studies using smartwatches to detect, track and monitor COVID-19 and other illnesses are based on research that is underdeveloped, The Verge reported April 25.

The article cited a study published in The Lancet that looked at data collected by devices like the Apple Watch, Fitbit and Whoop from 12 research studies and 12 proposed study protocols published in 2020 and 2021. 

Here's what it found:

  1. In the weable studies, researchers looked for patterns in wearable data from the few days before a person got sick, rather than following healthy people and trying to predict who would fall ill.

  2. None of the studies were rigorous clinical trials.

  3. None of the existing research tested to see if a wearable device could actually lead to earlier detection of COVID-19.

  4. Most of the algorithms built to divine COVID-19 out of wearable data mainly focused on symptomatic disease.

  5. Most of the studies didn't differentiate between COVID-19 and other illnesses like the flu that have common symptoms.

  6. Many of the studies had poor racial diversity, making it unclear if the models would perform equally as well in nonwhite populations.

  7. Four weable studies tried to detect an infection before a person started to show symptoms, but had varying success.

  8. Wearables were able to detect between 20 percent and 88 percent of infections, but got less accurate the more days in advance they tried to predict illness. 

Researchers concluded devices like smartwatches are not useful as COVID-19 and illness detectors.

 

Copyright © 2022 Becker's Healthcare. All Rights Reserved. Privacy Policy. Cookie Policy. Linking and Reprinting Policy.

 

Featured Whitepapers

Featured Webinars