New Delhi: Use of smartwatches that capture our heart rate, physical activity and sleep patterns can improve the chances of predicting Covid-19, says a paper published in monthly-peer reviewed medical journal Nature Medicine.
While traditional screening for Covid typically includes survey questions about symptoms, travel history and temperature measurements, the researchers have explored how personal sensor data is likely to help identify subtle changes indicating an infection, such as in Covid cases, says the study.
The study — conducted on 30,000 participants between 25 March and 7 June — found that a combination of symptom and sensor data was significantly better for differentiating between Covid-positive and -negative individuals than a model that considers symptoms alone.
The combination was correct in predicting coronavirus cases 80 out of 100 times, whereas data on symptoms alone correctly predicted cases 70 out of 100 times.
“We found that a combination of symptom and sensor data resulted in an area under the curve (AUC) of 0.80 for discriminating between symptomatic individuals who were positive or negative for COVID-19, a performance that is significantly better than a model that considers symptoms alone (AUC = 0.71),” said the paper titled Wearable sensor data and self-reported symptoms for COVID-19 detection published 29 October.
The study, conducted by researchers at the Scripps Research Translational Institute in California, US, found that smartwatches and activity trackers “can improve our ability to objectively characterize each individual’s unique baseline for resting heart rate, sleep and activity”.
“The smart-watch can therefore be used to identify subtle changes in that user’s data that may indicate that they are coming down with a viral illness,” the study said.
How the data was collected
According to the paper, the researchers have developed a smartphone app that collects smartwatch and activity tracker data, as well as self-reported symptoms and diagnostic testing results, from individuals in the US.
Based on the data, the researchers have assessed whether symptom and sensor data can differentiate between Covid-positive and -negative cases in symptomatic individuals.
The data was collected from 30,529 individuals of whom 3,811 reported symptoms. “Of these symptomatic individuals, 54 reported testing positive and 279 negative for COVID-19,” the paper said.
The study showed that “the sleep and activity of COVID-19 positive participants were impacted significantly more than COVID-19-negative participants”.
S.P. Kalantri, director professor of medicine and medical superintendent at the Maharashtra-based Mahatma Gandhi Institute of Medical Sciences in Wardha, said such technology could be useful in “identifying clusters”.
“The study is very exciting and shows the application of artificially intelligent algorithms in diagnosis of Covid-19. The data show a significant increase in prediction of Covid while using information from smartwatch devices.
While the penetration of smartwatches is significantly lower in India compared to that in the US, the technology has a potential to identify a cluster before more spread occurs. It also needs to comply with the privacy of data norms, for artificial intelligence can also put people at risk of their sensitive personal data being used for commercial reasons,” he said.
The study also found that an elevated temperature is not as common as believed, being present in only 12 per cent of individuals who tested positive and just 31 per cent of patients hospitalised.
“Although encouraging, these results are based on a relatively small sample of participants… This method is likely to miss pre-symptomatic or asymptomatic cases, which make up 40–45 per cent of those infected with SARS-CoV-2, and who can still be infectious,” researchers pointed.
The story has been updated with Professor S.P. Kalantri’s quote.
Why news media is in crisis & How you can fix it
India needs free, fair, non-hyphenated and questioning journalism even more as it faces multiple crises.
But the news media is in a crisis of its own. There have been brutal layoffs and pay-cuts. The best of journalism is shrinking, yielding to crude prime-time spectacle.
ThePrint has the finest young reporters, columnists and editors working for it. Sustaining journalism of this quality needs smart and thinking people like you to pay for it. Whether you live in India or overseas, you can do it here.