Skip to Main Content
COVID-19 ISO Insights

Update: Several Smartwatch Studies Seek to Detect Onset of COVID-19

March 8, 2021

By: Christopher Sirota, CPCU

Someday your watch may alert you before your body does about a viral infection, such as COVID-19.

Such an early alert system may not only reportedly benefit the wearer, who can seek medical attention sooner, but also may help mitigate viral transmission because the wearer would be made aware to help avoid other people sooner.

Smartwatch Data

Many of the newer smartwatches can reportedly collect vital signs from the wearer such as breathing rate, sleep routines, activity levels, blood pressure, heart rate and temperature.

Researchers have reportedly been trying to utilize such data to provide health indications, but there have been concerns about data reliability from smartwatches.

To address, in part, the reliability concerns, back in October 2020, we noted, per EurekAlert, that researchers at Purdue University were conducting a study where participants in the study would use a smartwatch and also have a "chest-based biosensor" to be used to collect an electrocardiogram signal; the additional biosensor would reportedly help researchers to develop improved smartwatch software to better detect "subclinical changes" in health metrics.

Subsequently several other related smartwatch studies have reported their findings, reports Knowable.

Scripps Research Translational Institute/DETECT Study

Per Knowable, in this study, about 30,000 participants shared health data via a smartwatch and self-reported symptoms via a smartphone app. The article explains that only when the researchers combined the smartwatch sensor data (resting heart rate, sleep and activity levels) with the self-reported data were they able to derive a statistically significant improvement in detection accuracy. Per the DETECT website, the study will continue for four years. A chart comparing symptoms from COVID-19 tested users, positive and negative, is available in the full study here.

Stanford University

Knowable reports that Stanford researchers examined data from 5,000 participants (full study here). The data reportedly included heart rate and sleep; more specifically:

The Stanford group’s algorithm collects data on three signals, all relative to the person’s baseline — a high resting heart rate (a result of inflammation), a high ratio of resting heart rate to daily steps taken, and increased sleep (one way the body activates immune cells) — and looks for trends.

According to the article, for 32 participants with COVID-19 symptoms, the algorithm identified signals on average four days before reported symptoms. For one COVID-19 case, per a related blog, the researchers detected COVID-19 about nine days before the onset of reported symptoms.

You will soon be redirected to the 3E website. If the page has not redirected, please visit the 3E site here. Please visit our newsroom to learn more about this agreement: Verisk Announces Sale of 3E Business to New Mountain Capital.