Smartwatches Alert Wearers to Body Stress, Including COVID-19 | Information Center

Using data from smart watches, a new algorithm reads heart rate as an indicator of physiological or mental stress, potentially alerting wearers that they are getting sick before they have symptoms.

Researchers led by Michael snyder, PhD, professor and chair of genetics, have enrolled thousands of participants in a study that uses the algorithm to look for prolonged periods when the heart rate is higher than normal – a telltale sign that something is wrong.

But figuring out what’s wrong takes a bit of a detective. During the study, many stressors triggered an alert. Some people received them on a trip; some running a marathon; others after having abused the bar.

The most exciting finding, Snyder said, was that the algorithm was able to detect 80% of confirmed cases of COVID-19 before or when participants were symptomatic.

“The idea is that people end up using this information to decide whether to take a COVID-19 test or to self-isolate,” Snyder said. “We’re not there yet – we have yet to test this in clinical trials – but that’s the ultimate goal.”

The algorithm cannot tell the difference between someone who has received a little too much, someone who is stressed from work, and someone who has a virus. Although he polled users who had COVID-19, further refinement is needed before people can rely on their smartwatches to warn them of an impending infection with SARS-CoV-2 or other viruses.

An article detailing the study was published online in Natural medicine November 29. Snyder, Stanford W. Ascherman, MD, FACS, professor of genetics, and Amir Bahmani, PhD, lecturer and director of Stanford Deep Data Research Computing Center, are co-lead authors. Arash Alavi, PhD, research and development manager at Stanford Deep Data Research Computing Center; research scientist Meng Wang, PhD; and post-docs Gireesh Bogu, PhD, Ekanath Srihari Rangan, doctorate and Andrew brooks, PhD, share primary authorship. The warning system was built using MyPHD, a scalable and secure platform for health data.

Stress detection

During the study, which lasted about eight months in 2020 and 2021, 2,155 participants donned smartwatches, which tracked mental and physical “stress events” via heart rate. When notified of a stressful event, via an alert associated with an app on their phone, participants recorded what they were doing. To trigger an alert, their heart rate had to be elevated for more than a few hours, so a quick jog around the block or a loud, sudden noise didn’t trigger it.

“What’s great about it is that people can contextualize their alerts,” Snyder said. “If you’re traveling on an airline and you get an alert, you know air travel is probably the culprit. “