AI model detects COVID-19 related symptoms in advance

One of the most daunting aspects of fighting the pandemic is that asymptomatic people can spread the virus without knowing they are infected.

Early results of the first phase of a study by the West Virginia University Rockefeller Neuroscience Institute (RNI) and WVU Medicine, using Oura Ring sensor data and AI models, show that COVID-19 related symptoms can be detected up to three days before they show up. Additionally, the team is gaining a greater understanding of the recovery and treatment of COVID-19.

“The holistic and integrated neuroscience platform developed by the RNI continuously monitors the human operating system, which allows for the accurate prediction of the onset of viral infection symptoms associated with COVID-19,” said Ali Rezai, M.D., executive chair of the WVU Rockefeller Neuroscience Institute. “We feel this platform will be integral to protecting our healthcare workers, first responders, and communities as we adjust to life in the COVID-19 era.

The RNI platform uses a smartphone app, the Oura Ring, and AI-guided models to forecast and predict the onset of COVID-19 related symptoms such as fever, coughing, and breathing difficulties three days in advance with over 90 percent accuracy. This technology can potentially serve as a critical decision-making tool to help contain the spread of the virus, safely re-open communities, strengthen the economy, and facilitate public health containment strategies.

A key part of the study is the Oura Ring by the wearable health tech company Oura Health. Designed to be worn on a finger, the Oura Ring captures body measurements like heart rate, HRV, temperature and sleep. The novel device features infrared LEDs, NTC temperature sensors, an accelerometer, and a gyroscope.

The study to determine if an AI-driven model could be developed to detect symptoms in advance involved the monitoring of 600 healthcare professionals. The study integrated physiologic measures with psychological, cognitive, and behavioral biometrics, including stress and anxiety, to track the mind-body connection in the context of asymptomatic infection.

The RNI will be expanding the study to more than 10,000 participants through national partners including Thomas Jefferson University in Philadelphia, Vanderbilt University in Nashville, and other academic institutions in West Virginia, New York City, and California.

“We are hopeful that Oura’s technology will advance how people identify and understand our body’s most nuanced physiological signals and warning signs, as they relate to infectious diseases like COVID-19,” Harpreet Rai, CEO of Oura Health, said. “Partnering with the Rockefeller Neuroscience Institute on this important study helps fulfill Oura’s vision of offering data for the public good and empowering individuals with the personal insights needed to lead healthier lives.”  

In addition to the platform’s ability to detect symptoms in advance, the research team is now launching the next phase of its study, which will show the location of reported symptoms. The RNI app is now available to the general public. People interested in participating in the study should visit RNI’s  COVID19 webpage.

The Oura ring is also being used in other COVID-19 studies, as reported earlier in FierceElectronics.

RELATED: COVID-19: Wearable goes from tracking activity to tracking a virus