Originally published in FindBiometrics
Digital medicine company physIQ and Purdue University have announced a partnership to jointly develop an algorithm that can detect early signs of COVID-19 from data gleaned from a biometric smartwatch.
physIQ, a Purdue-affiliated company based in Chicago that has support from the Purdue Research Foundations’ Foundry investment Fund, will develop the new software with data gathered from a study conducted by Purdue researchers that will look at whether continuously collected data from a biometric smartwatch offers any indication that an asymptomatic person should get tested for COVID-19.
The use of biometric wearables to help fight the spread of the virus has grown in recent months. In June, the NBA announced it would be making the biometric sensor-laden Oura ring available to players, staff and personnel for the league’s restart in a ‘bubble’ environment in Florida.
Similarly, earlier this month the US military announced it has been conducting a study that uses kits consisting of the Oura ring and a Garmin smartwatch to track signs of the virus among field personnel.
Experts do caution, however, that biometric wearables on their own are not substitutes for diagnostic tests used by physicians and researchers in clinics and hospitals.
Biometric sensors embedded in smartwatches collect a wide array of physiological data, and researchers will be looking to see if incorporating metrics like heart rate, heart rate variability and respiration rate can offer insights into whether COVID-19 can be detected at its earliest possible stages.
“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, Purdue’s Leslie A. Geddes Associate Professor of Biomedical Engineering.
Previous studies have shown that viral infections increase resting heart and respiration rates and decrease heart rate variability before a patient develops a fever, Goergen said. 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,” Goergen said.
Georgen’s team will use a group of 100 participants — consisting of Purdue students, staff, and faculty — to initially see if wearing a smartwatch to collect the necessary data is practical, unobtrusive and user-friendly.
Participants will receive a Samsung Galaxy smartwatch with the physIQ software loaded to collect the needed data, FDA-cleared chest biosensors to collect single-lead electrocardiogram signals, as well as a Samsung Galaxy smartphone to use for five days of continuous monitoring.
Georgen’s lab will analyze the data collected from the app remotely using physIQ’s cloud-based accelerateIQ platform, with data collected from the chest sensors processed by physIQ’s AI-based algorithms. The data gleaned from this process will be considered a ‘gold standard’ for referencing against the data simply collected from smartwatches.
“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 healthcare delivery.”
Researchers hope to eventually open the study to include an expanded group of individuals that are considered high-risk of contracting COVID-19.