As early as the early days of the outbreak of the new crown pneumonia epidemic, smart watch manufacturers and wearable technology companies wanted to mark the population with indicators such as heart rate and blood oxygen, although there has been no significant progress so far, but some studies have shown that wearable devices are still an effective way to track the symptoms of new crown pneumonia.
Researchers at Utrecht University in the Netherlands retrieved research articles and protocols published between 2020 and July 27, 2021 on the use of wearable devices to identify COVID-19 infections, identified and screened the records, analyzed 12 of them and published relevant papers, which will be open access in The Lancet on May 1.
The study found that the research teams in 12 studies all used different methods to judge the ability of wearable devices to detect COVID-19 infection, and nine of the studies used machine learning algorithms to identify biological data to detect COVID-19 infection.
Although there is ample evidence that when a person is infected with COVID-19, there are differences in physiological signals such as body temperature changes and heart rate variations, most algorithms that predict COVID-19 from wearable data mainly focus on symptomatic diseases, and the ability of algorithms to detect pre-diagnosis infection varies greatly from 14 days before symptoms to 1 day before diagnosis.
And most of the current studies use retrospective data, the sample size is small, most of the authors only focus on the symptoms of new crown pneumonia, ignoring the physiological differences and ethnic diversity of new crown symptoms and other diseases such as influenza, and the models evaluated in the review do not take into account changes in women's menstrual body temperature, so there is not enough evidence to show that wearable devices can detect new crown pneumonia infection earlier.
However, as technology advances, wearables are becoming more and more versatile in the field of health monitoring, subtle fluctuations in physiological parameters such as body temperature, respiratory rate, heart rate, and blood oxygen saturation can all be expressed through smart watches, smart rings, and fitness trackers.
Studies have shown that the peripheral temperature measured by wearables shows higher sensitivity than oral measurements in detecting subtle temperature changes above 0.2 °C, and the wrist temperature is equally stable and less susceptible to environmental influences than the forehead temperature.
So, despite these limitations today, evidence on the use of wearables to detect COVID-19 suggests that the study is promising, but still in its infancy.
(7913829)