Fertility tracking and COVID-19 detection may have more in common that one might assume. That connection prompted a study using the Ava bracelet, which is FDA-cleared for the U.S. market and CE-certified for Europe. Designed for fertility monitoring, the device tracks and analyzes the wearer’s heart rate variability (HRV), resting pulse rate, skin temperature and skin perfusion, nighttime breathing rate, and sleep quality; these also are some of the bio-signals that could be affected by the onset of COVID-19. Funded by the government of Liechtenstein, researchers conducted a study in which a cohort of 1,163 participants wore Ava bracelets nightly.
During the study, which collected around 1.5 million hours of physiological data over nearly one year, 127 participants contracted COVID-19, confirmed by PCR tests. And the Ava bracelet picked up the telltale signs in many of these individuals. The majority of the participants who got COVID-19 showed significant changes in key indicators — five of the seven physiological parameters that the bracelet measures for — including heart rate, temperature, and respiratory alterations. On average, the symptoms lasted for 8.5 days.
The data that researchers were most interested in was the physiological information from before the onset of symptoms. Using real-time continuous physiological data that the bracelets collected from between 2 and 10 days before participants started feeling symptoms, researchers developed and trained a machine-learning algorithm to detect COVID-19. The results? The study found that the algorithm detected 68% of COVID-19 cases up to 2 days before the onset of symptoms.
So how does the Ava bracelet work? One sensor on the underside of the bracelet’s face measures skin temperature, a key reading for both COVID-19 and fertility. A separate optical sensor gauges changes in blood volume, which are used to track parameters including breathing rate and resting pulse. And the Ava bracelet’s accelerometer monitors the wearer’s physical movements, offering a window into sleep duration and quality. Data is saved every 10 seconds and syncs to an app on the wearer’s smartphone. In the study, participants also used the app to report activity that could affect the data — such as medication and alcohol use — as well as potential COVID-19 symptoms.
The study’s authors write, “Wearable sensor technology is an easy-to-use, low-cost method for enabling individuals to track their health and well-being during a pandemic. Our research shows how these devices, partnered with artificial intelligence, can push the boundaries of personalized medicine and detect illnesses prior to [symptom onset], potentially reducing virus transmission in communities.” But admit there’s still work to do. “We acknowledge that our sensitivity was less than 80%. We expect to improve the algorithm’s performance further in a larger cohort within the setting of [our next] study.”