Research on COVID-detecting smartwatches still hasn’t panned out

Illustration by Alex Castro / The Verge

Wearable tech companies and smartwatch advocates thought the devices could help with illness detection in the early days of the COVID-19 Pandemic. They wanted to flag people who might be sick with the disease with their heart rate and oxygen levels. The strategy could still be a reasonable way to track illness, but two years later, the promise hasn't panned out, according to a new review.

The review looked at 12 research studies and 12 proposed study protocols that tried to find patterns in the data collected by devices like the Apple Watch. People who had already tested positive for COVID-19 were the focus of most of the studies. Researchers looked for patterns in data from the few days before a person got sick, rather than following healthy people and trying to predict who would get sick. The authors of the new study noted that there were no rigorous clinical trials in the studies. None of the existing research was able to see if a Wearable device could lead to earlier detection of COVID-19.

The study found that most of the software that was built to divine COVID-19 was focused on the symptoms of disease. They were able to detect between 20 and 88 percent of infections if they tried to detect them before a person started to show symptoms. The models got less accurate as the days went by. It would make the devices less useful because they would be less useful as COVID-19 detectors.

There is good evidence that signals like body temperature, heart rate variability, and other metrics are associated with someone coming down with an illness. Most of the studies in this review didn't differentiate between COVID-19 and the flu, and that includes other illnesses as well. I think it's going to be difficult, because the data on the flu and COVID-19 overlaps.

The authors of the new review wrote that there are equity issues in using Wearable devices as COVID-19 or other illness detectors. The studies included in the analysis had poor racial diversity, so it is not clear if the models would perform as well in nonwhite populations. That's even more of a concern because research shows that wearables can work differently on darker skin tones. Even though there are changes in body temperature and other variables associated with different stages of the menstrual cycle, none of the models evaluated took it into account.

Despite the limitations of existing research, it is possible that Wearables could be a good way to track and monitor illness. There needs to be better research done to prove it and to figure out the best way to use the devices. Even a basic tool that could alert someone that they might be getting sick is still useful, according to experts.

It's just a heads up that something is out of your normal range, and it could be something to keep an eye on.