A systematic review on the detection of COVID-19 through wearables was published in The Lancet.
The monitoring of physiological parameters such as heart rate, respiratory rate, body temperature, is important to detect the presence of infections and cases of COVID-19. These parameters are perceptible by mobile devices such as wearables, which can act as "digital biomarkers" in the early detection of infections.
In The Lancet, a systematic review was published that collects and evaluates the performance of statistical and algorithmic models that use data from wearables for the possible detection of COVID-19.
For investigators, they searched databases such as MEDLINE, Embase, Web of Science, CENTRAL, International Clinical Trials Registry Platform, and ClinicalTrials.gov. And of 3 thousand 196 identified studies, they analyzed 12 articles and 12 study protocols.
"Some authors relied on statistical analysis to detect differences between or within participants, while others used machine learning algorithms," the review explains.
Although the accuracy of the algorithms varied (AUC 0 52–0 92), they were able to identify the symptoms most frequently associated with COVID-19 infection. For example, heart rate, temperature and respiratory rate. Likewise, these were the most analyzed variables in practically all the studies.
Likewise, the authors of the review recognized that the evidence around wearables and the early detection of COVID-19 is still at a very early stage, so larger and more controlled studies are needed, with the participation of populations. larger and more diverse.
The authors conclude that “although wearable devices could help, this systematic review highlights the need for well-designed and controlled studies to robustly identify whether wearable devices can accurately detect SARS-CoV-2 infection before the onset of SARS-CoV-2 infection. symptoms or in asymptomatic people compared to the current gold standard diagnostic method.
This is due to the fact that some studies had health professionals as participants, who had easier access to PCR tests; other studies were based on statistical models rather than algorithms; and even some studies did not use conventional devices that are placed on the wrist, but rather rings or devices that were placed in the throat area.