Using longitudinal temperature data, wearable devices can predict the onset of illnesses even without recognizable symptoms, according to new research published in Scientific Reports.

The paper included data from only 50 participants, and researchers stressed that the findings are a proof-of-concept effort, suggesting the need for further research into the role of wearable sensors in early illness detection.

Researchers used the commercially available Oura Ring smart device to collect all physiological data.

TOP-LINE DATA

The temperature data collected by the Oura Ring was able to reliably detect the onset of fevers, one of the most common symptoms associated with COVID-19 and the flu. In the study, the ring detected early signs of fever in 93% of the cases an average of three days before symptoms showed. 

Because the wearable could detect the onset of illness using digital biomarkers when some participants didn’t report symptoms, researchers believed that wearables could pose an important role in identifying asymptomatic cases.

This is particularly significant for COVID-19 because as many as 40% of infections are asymptomatic, according to the Centers for Disease Control and Prevention’s current best estimate.

The study also supported the importance of longitudinal, high temporal-resolution data gathered within individuals instead of single time-point measures.

A person’s temperature varies throughout the day, so spot checks offer about the same reliability of catching a syllable per minute in a conversation, rather than whole sentences, according to Benjamin Smarr, a corresponding author for the paper.

Researchers concluded that using multiple biomarkers provide superior illness prediction than single-metric models. When they looked at changes in participants’ temperature, other biomarkers were also impacted, such as heart rate, heart rate variability and respiratory rate.

However, the authors noted that the changes were not always an exact corresponding match. Meaning that sometimes a person’s temperature would spike, but not their heart rate, and vice versa.

“The key challenges can be summarized as follows: people are different, and so are physiological systems,” the authors said in the paper. “Taking examples displayed within this manuscript, the amplitude of daily rhythm, stability across days, correlation across variables, and stability of those correlations all change within and across individuals, both in and out of reported illness.”

METHODS

The 50 subjects all owned Oura rings and had had COVID-19 before joining the study.

Most participants (66%) lived in the United States, with an additional six participants in the U.K., three in Finland, and one each in Austria, Canada, Germany, Honduras, Italy, The Netherlands, Norway and Sweden.

A majority (66%) identified as male and the average age was 43.7 years. Of the 48 participants who indicated their race or ethnicity, the majority (81%) identified as Caucasian or White, eight as Hispanic or Latino, one as Middle Eastern, one as Asian, one as South Asian and three as “other.”

THE LARGER TREND

This report represents early findings from the larger TemPredict study, which includes 65,000 participants with the goal of developing an algorithm that can predict the onset of symptoms such as fever, cough and fatigue, which are characteristic of COVID-19. Researchers say they hope to achieve that goal by the end of the year.

Oura Rings are also being used in the DETECT (Digital Engagement & Tracking for Early Control & Treatment) Study, headed by the Scripps Research Translational Institute. The project aims to not only identify areas with viral outbreaks such as COVID-19 more quickly but to "develop more individualized approaches to health care" using person-specific vital-sign readings, according to the study's enrollment website.

The health tracker Fitbit also recently released findings from its study that used biometrics to predict the onset of COVID-19. It outlines predictors for the severity of illness, symptom prevalence, illness duration among male and female participants and estimations of the need for hospitalization.

Notably, the Fitbit study found that fevers were only present in 59.4% of males and 52% of females, indicating that temperature screening alone may not be enough to measure infection rates.

Outside of research, this year Oura raised $28 million in a Series B funding round. It also partnered with both the NBA and WNBA to help players and staff monitor their health while they completed their seasons.

ON THE RECORD

“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 the principal investigator of the study, in a statement. “In this way, an ounce of prevention may be worth even more than a pound of cure.”