Your smart watch could soon spot Covid before you do

Wrist-worn health trackers are capable of picking up signs of early symptoms

A team writing in the journal 'BMJ Open' tested the AVA bracelet, a fertility tracker that people can buy online to track the best time to conceive. Photo: Ava
Powered by automated translation

Health trackers worn on the wrist could detect Covid-19 days before symptoms appear, research suggests.

The trackers monitor changes in skin temperature, heart and breathing rates and could be combined with artificial intelligence (AI) to provide a diagnosis, a study has found.

A team writing in the journal BMJ Open tested the AVA bracelet, a fertility tracker that people can buy online to identify the best time to conceive.

It monitors breathing rate, heart rate, heart rate variability, wrist skin temperature and blood flow.

Other heath trackers, such as Fitbit or Apple Watch, do not yet have the capability, but in future it could be possible and extremely useful, researchers said.

Dr Lorenz Risch, president of Switzerland’s Dr Risch Laboratories, told The National the AVA bracelet is a certified medical product, which is also cleared for fertility tracking.

"So far, neither the Apple Watches nor the Fitbit can be regarded as medical products," he said. "As a tracker itself, the AVA bracelet also includes wrist temperature monitoring, which is only included in a minority of other health trackers.

"It could theoretically seem feasible, that the AI-algorithms identified with the AVA bracelet could be adapted to other health trackers monitoring the same or similar physiological parameters. However, this is expected to take into account technical, regulatory as well as standardisation issues.

"Nevertheless, facing the fact that more than 100 million fitness trackers were sold globally in 2021, trying to apply the AVA-algorithm to other health trackers would ultimately allow an increase in the reach and usage of AI-driven health tracker technology in order to powerfully support mastering pandemic situations."

In the study, 1,163 people under the age of 51 in Liechtenstein were followed from the start of the pandemic.

They were asked to wear the AVA bracelet at night, with the device saving data every 10 seconds. People have to sleep for at least four hours for it to work.

The bracelets were synchronised with a smartphone app, with people recording any activities that could affect the results, such as alcohol, prescription medication and recreational drugs.

They also recorded possible Covid-19 symptoms, such as fever.

All those in the study took regular rapid antibody tests for Covid-19 while those with symptoms also took a PCR test.

Overall, 1.5 million hours of physiological data were recorded and Covid-19 was confirmed in 127 people, of which 66 (52 per cent) had worn their device for at least 29 consecutive days and were included in the analysis.

The study found there were significant changes in the body during the incubation period for the infection, the period before symptoms appeared, when symptoms appeared and during recovery, compared with non-infection.

Overall, the tracker and computer algorithm identified 68 per cent of Covid-19 positive people two days before symptoms appeared.

The team, including members from the Cardiovascular Research Institute of Basel, concluded there were limits to the research, including that not all Covid-19 cases were captured.

But they said: “Wearable sensor technology can enable Covid-19 detection during the pre-symptomatic period.

“Wearable sensor technology is an easy-to-use, low-cost method for enabling individuals to track their health and well-being during a pandemic.

“Our research shows how these devices, partnered with artificial intelligence, can push the boundaries of personalised medicine and detect illnesses prior to [symptom occurrence], potentially reducing virus transmission in communities.”

The algorithm is now being tested in a much larger group of 20,000 of people in the Netherlands, with the results expected later this year.

Updated: May 30, 2023, 12:53 PM