A team of researchers from the West Virginia University (WVU) Rockefeller Neuroscience Institute (RNI), together with WVU’s Department of Medicine and Oura Health staff have developed a platform that they say can be used to anticipate the onset of COVID-19 symptoms in otherwise healthy people up to three days in advance. This can help with screening pre-symptomatic individuals, the researchers suggest, allowing for earlier testing and potentially reducing the risk of exposure among frontline healthcare workers and essential workers.
The study involved using biometric data collected by the Oura Ring, a wearable consumer that looks like a normal metallic ring but which includes sensors for monitoring a number of physiological parameters, including body temperature, sleep patterns, activity, heart rate, and more. RNI and WVU Medical researchers from around 600 healthcare workers and first responders combined these data with physiological, cognitive, and behavioral biometric info.
The study participants wore the Oura Ring and received additional data that were then used to build AI-based models to predict symptom initiation before physically manifesting. While these are early results from a Phase One study and yet to be peer-reviewed, the researchers say their results showed a 90 percent accuracy rate of predicting the onset of symptoms including fever, coughing, breathing difficulty, fatigue, and more, all of which could indicate that somebody contracted COVID-19. While that doesn’t mean people have the disease, a platform flag could mean they ‘re looking for tests up to three days before symptoms appear, that, in turn, would mean three fewer days of potential exposure to infection by others around them.
Next, the study hopes to expand to cover as many as 10,000 participants in multiple states across a number of different institutions, with other academic partners on board to support the expansion. The study was fully funded by the RNI and its supporters, with Oura strictly joining in facilitating capacity, and assisting with deployment hardware.
Many projects have been undertaken to see if predictive models could help to anticipate the onset of COVID-19 before symptom expression, or in individuals who present as being mostly or entirely asymptomatic based on general observation.