COVID-19 ISO Insights

Researchers Explore Smartwatch Data to Alert Users of Potential COVID-19 Infection

October 26, 2020

By: Christopher Sirota, CPCU

A September 2020 article in PLOS notes that most COVID-19 patients will eventually develop symptoms. The World Health Organization (WHO) website explains that "evidence suggests that SARS-CoV-2 RNA can be detected in people 1-3 days before their symptom onset […]."

What if a COVID-19 patient could be alerted before symptoms develop?

According to EurekAlert, that's what researchers at Purdue University are exploring through the use of a smartwatch system that can collect biometric data.

Per the article, the researchers are planning to ascertain if a smartwatch system could be reliable enough to collect the biometric data needed to forecast a possible COVID-19 infection in the wearer.

The researchers reportedly plan to collect heart rate and breathing rates from participants because there are some studies suggesting that changes in these physiological rates could precede COVID-19 symptoms.

To be clear, the researchers do not reportedly expect the data to confirm a COVID-19 infection, but hope that the data might trigger an alert to the wearer that they may be getting sick and should probably get tested.

Per the article, one of the researchers explained:

Previous studies have shown that viral infections increase resting heart and respiration rates and decrease heart rate variability before a patient develops a fever […]. It's not yet known if these indicators, particularly respiration rate, can be measured reliably enough at the wrist to imply infection.

"An increased heart rate or respiration rate means something different if it increased while you were resting as opposed to running, but most smartwatches have difficulty distinguishing that. So it is really recovery and resting periods that we are focused on with this approach […]."

The article notes that the participants in the study will also have a "chest-based biosensor" to be used to collect an electrocardiogram signal. From signal data, the researchers will then reportedly use an algorithm to derive heart rate, heart rate variability and respiration rate to create a dataset for comparison with the smartwatch data.

Of interest, one of the goals of the study is reportedly to develop improved smartwatch software to better detect "subclinical changes in metrics unique to the individual by ‘learning’ from large amounts of data continuously collected while wearing the watch."