London, June 24 – Wearable activity trackers that monitor changes in skin temperature and heart and breathing rates, combined with artificial intelligence (AI), might be used to pick up Covid-19 infection days before symptoms start, claimed preliminary research.
Typical Covid-19 symptoms may take several days after infection before they appear, during which time an infected person can unwittingly spread the virus.
But in the study, published in the open access journal BMJ Open, the researchers found that overall the health tracker, in combination with an computer algorithm, correctly identified 68 per cent of Covid positive people two days before their symptoms appeared.
The international team including from University of Basel (Switzerland) and Imperial College London, pointed out that while a PCR swab test remains the gold standard for confirming Covid-19 infection, “our findings suggest that a wearable-informed machine learning algorithm may serve as a promising tool for presymptomatic or asymptomatic detection of Covid-19”.
The team conducted a trial, on a AVA bracelet, and included 1,163 participants all under the age of 51 who wore the tracker at night. The device saves data every 10 seconds and requires at least 4 hours of relatively uninterrupted sleep. The bracelets were synchronised with a complementary smartphone app on waking.
All participants took regular rapid antibody tests for Covid infection. Those with indicative symptoms took a PCR swab test as well.
Some 127 people (11 per cent) developed Covid-19 infection during the study period, of which 66 (52 per cent) had worn their bracelet for at least 29 days before the start of symptoms and were confirmed as positive by PCR swab test, so were included in the final analysis.
The algorithm was ‘trained’ using 70 per cent of the data from day 10 to day 2 before the start of symptoms within a 40 day period of continuous monitoring of the 66 people who tested positive for SARS-CoV-2. It was then tested on the remaining 30 per cent of the data.
Some 73 per cent of laboratory confirmed positive cases were picked up in the training set, and 68 per cent in the test set, up to 2 days before the start of symptoms.
The researchers acknowledge that their results may not be more widely applicable.
But “wearable sensor technology is an easy-to-use, low-cost method for enabling individuals to track their health and wellbeing during a pandemic”, they wrote in the paper.
Further, “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”.