Smart Ring Accurate Predictor of Fever Linked to COVID-19

Smart Ring Accurate Predictor of Fever Linked to COVID-19
While not an FDA registered healthcare device, the Oura ring monitors a range of signals, including continuous temperature, heart rate, respiration rate and activity. Initial analysis suggests that a destabilization of temperature happens a couple of days before coronavirus symptoms manifest. The Oura ring detects this pattern. [Source: Oura Ring]

A wearable smart ring can accurately predict body temperature elevations linked to COVID-19, suggest results from a University of California San Diego and San Francisco study.

Research suggests that more than half of those infected with SARS-CoV-2 experience a raise in their core temperature as one of the symptoms of infection. However, one-off measures of temperature are not always very accurate, as a lot of factors influence body temperature and some people have a naturally higher body temperature than others.

Several studies have shown that data from smart watches and fitness trackers can predict SARS-CoV-2 infection, particularly when combined with self-reported symptoms, but relatively few devices measure body temperature and the accuracy of those that do compared with medical thermometers has not been well investigated.

For this study, researchers from the University of California San Diego, University of California San Francisco and Baruch College in New York, decided to test the Oura ring to see if temperature measures from the ring could predict illness. The ring is made by the Finnish startup Oura and continuously measures heart and respiratory rates and temperature, as well as sleep and wakefulness.

The team distributed the ring device to 3400 healthcare workers in March and also invited people already using the ring to share their data as part of the TemPredict study, which now has 65,000 participants. This study just looked at the first 50 people to report COVID-19 in the group, but the team plans to analyze the bigger dataset by the end of the year with a view to accurately predicting SARS-CoV-2 infection using temperature and other wearable data.

As reported in the journal Scientific Reports, all 50 participants were pre-existing Oura ring users who had been infected with SARS-CoV-2. They agreed to shared their device data from the time of infection with the research team so they could evaluate how accurate the temperature sensors were at predicting infection while they were sick.

Overall, 38 individuals in the group reported having a fever. The research team found that the average body temperature of these individuals, as measured by the ring, did go up significantly by an average of 0.63°C while they were sick, confirming suggestions that the device can identify fever.

Notably, the devices often picked up increases in body temperature before people actually reported symptoms of fever, suggesting they could be good for giving early warning of infections.

“If wearables allow us to detect COVID-19 early, people can begin physical isolation practices and obtain testing so as to reduce the spread of the virus,” said Ashley Mason, Ph.D., a professor at University of California San Francisco and principal investigator on the study.

However, the researchers also noted a big difference in average body temperature between those in the group of up to 1.7°C, which suggests one-time measures of temperature, such as those taken at airports, may have limited predictive accuracy.

“Temperature varies not only from person to person but also for the same person at different times of the day,” said Benjamin Smarr, Ph.D., an assistant at University of California San Diego who was first author on the study.

This early data confirms suggestions that continuous temperature monitoring can provide valuable health information around fever onset. However, more data is needed to improve the accuracy of predictions. “We need to make sure that our algorithms work for everyone,” said Smarr.

The team also wants to assess how accurately smart wearables such as the Oura ring can predict the onset of other infections such as the flu.