According to the researchers, wrist health trackers could be used to detect Covid-19 days before symptoms appear.
An increasing number of people around the world are using devices to monitor changes in skin temperature, heart rate and respiratory rate. Now, a new study shows that these data could be combined with artificial intelligence (AI) to diagnose Covid-19 even before the first telltale signs of the disease appear.
“Portable sensor technology may allow the detection of Covid-19 during the presymptomatic period,” the researchers concluded. The findings were published in the journal BMJ Open.
The finding could lead health trackers to adapt with AI to detect Covid-19 early, simply by detecting basic physiological changes. This could help provide an early warning system to users who may be infected, which in turn can help prevent the spread of the disease more widely.
Researchers at Dr. Risch Medical Laboratory in Liechtenstein, the University of Basel in Switzerland, McMaster University in Canada and Imperial College London tested the Ava bracelet, a fertility tracker that people can buy online to keep track of best time to conceive. Controls respiratory rate, heart rate, heart rate variability, wrist skin temperature, and blood flow.
In the study, 1,163 people under the age of 51 in Liechtenstein were followed from the start of the pandemic until April 2021. They were asked to wear the Ava bracelet at night, with the device, which costs £ 249, saving data every 10 seconds. . People need to sleep at least four hours for it to work.
The wristbands were synced with a smartphone app, and people recorded any activity that could affect the results, such as alcohol, prescription drugs, and recreational drugs. They also reported possible symptoms of Covid-19 such as fever.
Sign up for First Edition, our free daily newsletter, every weekday morning at 7:00 BST
All study participants underwent periodic rapid antibody testing for Covid-19, while those with symptoms also underwent a PCR swab test.
In total, 1.5 million hours of physiological data were recorded and Covid-19 was confirmed in 127 people, of whom 66 (52%) had worn the device for at least 29 consecutive days and were included in the analysis.
The study found that there were significant changes in the body during the incubation period of the infection, the period before the onset of symptoms, when the symptoms appeared and during recovery, compared to non-infection. .
Overall, the dual combination of the health tracker and the computer algorithm correctly identified 68% of Covid-19-positive people two days before their symptoms appeared. The team noted that there were limits to the investigation, including that not all Covid cases were captured.
Although a PCR swab test remains the gold standard for confirming Covid-19, the findings “suggest that an informed machine learning algorithm for use may serve as a promising tool for presymptomatic or asymptomatic detection of Covid-19 “, the researchers said.
They added: “Portable sensor technology is an easy-to-use and low-cost method for enabling people to keep track of their health and well-being during a pandemic.
“Our research shows how these devices, combined with artificial intelligence, can push the boundaries of personalized medicine and detect disease before (occurrence of symptoms), potentially reducing the transmission of the virus to communities.”
Typical symptoms of Covid-19 may take several days after infection to appear, during which time an infected person may inadvertently spread the virus.
The algorithm is being tested on a much larger group of 20,000 people in the Netherlands, with expected results later this year.