1 min read

Purdue Researching Smartwatch Algorithms

Originally published in Inside Indiana Business

Researchers at Purdue University have begun a study they say will help determine if smartwatch data could be used to reliably and accurately detect symptoms of COVID-19 early. The university says the data could indicate that a potentially asymptomatic user should get tested for COVID-19.

Purdue says data from the study will help create new algorithms to be developed by physIQ, a Purdue-affiliated digital health technology company based in Chicago. The university says certain changes in a person’s heart and breathing rates will be monitored, which are possible early signs of COVID-19.

“There won’t be a point where a smartwatch can tell you that you’re COVID-19 positive, but it could potentially say, ‘Within the next couple of days, you might be getting sick and should go get tested,’” said Craig Goergen, an associate professor of biomedical engineering at Purdue.

Purdue says Goergen’s team will first determine whether wearing a smartwatch to collect these indicators is practical, unobtrusive and user-friendly. Up to 100 Purdue students, staff and faculty will be recruited as study participants.

“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,” Goergen said.

Each participant will be mailed a smartwatch with a physIQ app loaded to collect data, FDA-cleared adhesive chest-based biosensors that collect a single-lead electrocardiogram signal, and a smartphone to use for five days of continuous monitoring. Meanwhile, Purdue says Goergen’s lab will analyze data from the app remotely.

Researchers led by Fengqing Maggie Zhu, assistant professor of electrical and computer engineering at Purdue, will analyze data collected by Goergen’s lab. Zhu’s team will determine how much of it could be used to train algorithms for developing smartwatch software aimed at detecting these metrics better.

“We recognize this work as the first step in enabling advanced personalized analytics for continuous monitoring of individuals using smartwatch data,” said Stephan Wegerich, physIQ’s chief science officer. “This could lead to a solution that is applicable to many physiological monitoring applications in both clinical trial markets as well as in health care delivery.”

Purdue says the study’s ultimate goal is that the software would show subclinical changes in metrics unique to the individual by “learning” from large amounts of data continuously collected while wearing the watch.

The researchers say they plan to eventually expand the study to include individuals at high risk of contracting COVID-19.