Wearable health devices can identify Covid-19 cases earlier than the onset of symptoms, according to researchers.
Existing wrist-worn health trackers monitor skin temperature, and heart and breathing rates. Combined with artificial intelligence (AI), this data could be used to diagnose Covid-19 even before the first tell-tale signs of the disease appear, the study finds.
“Wearable sensor technology can enable Covid-19 detection during the presymptomatic period,” the researchers concluded. The complete findings are published in the BMJ Open medical journal.
The results could lead to the adaption of health trackers with AI to detect Covid-19 earlier than traditional diagnostic methods, which can provide early warnings and improve the management of the disease.
Researchers from the 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 used to identify the best time to conceive.
The device, which costs $279 (or PHP 15, 200), is worn overnight and monitors skin temperature, breathing rate, heart rate, heart rate variability, and blood flow.
1,163 participants under the age of 51 in Liechtenstein were followed from the start of the pandemic, with the data used in the analysis being collected through March 2021.
Their bracelets were synchronized with a smartphone app, and the participants were also asked to record possible Covid-19 symptoms (such as fever) and any activities that could affect the results, including alcohol, prescription medications, and recreational drugs.
All those in the study took regular rapid antibody tests for Covid-19 while those with symptoms also took a PCR swab test.
The researchers found there were significant changes in the body during the incubation period for the infection, the pre-symptomatic period, when symptoms appeared, and during recovery, compared to non-infection.
For the most part, the hand-in-hand combination of the health tracker and computer algorithm correctly identified 68% of Covid-19 positive people two days before their symptoms appeared. However, the team pointed out that not all Covid cases were captured by the program.
While a PCR swab test remains the most reliable standard for confirming Covid-19, the findings “suggest that a wearable-informed machine learning algorithm may serve as a promising tool for presymptomatic or asymptomatic detection of Covid-19.”
“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 researchers concluded.