Bracelets attached to “health” trackers are used for a variety of reasons, first to know your heart rate, your muscle and fat mass, your skin temperature or even your stress level and the number of steps taken each day. Enough to know almost everything about his health condition from now on, a study has revealed British Medical JournalThis shows that this information can be combined with artificial intelligence (AI) to diagnose Covid-19 disease before the first symptoms appear. The researchers based their findings on wearers using controlled, commercially available fertility tracker bracelet codenamed “Ava”, which monitors respiratory rate, heart rate, heart rate variability, wrist skin temperature and blood flow, as well as sleep volume and quality. It’s been several months now, the scientific team explains “The focus is on the potential of activity trackers and smartwatches to detect all levels of COVID-19 infection, from incubation to recovery, to facilitate isolation and testing of infected individuals.. A
Common symptoms of COVID-19 can take several days after infection, during which time an infected person may inadvertently spread the virus. The Ministry of Health indicates that: The incubation period of Covid-19 (the period between contamination and the appearance of the first symptoms, if they are seen) is usually 3 to 5 days, but it can be extended up to 14 days. During this time, the matter can become contagious: he may carry the virus before the onset of symptoms or before the onset of weak signals. The researchers therefore sought to see if physiological changes, monitored by an activity tracker, could be used to create a machine learning algorithm to detect COVID-19 infection before symptoms began. In the study, 1,163 people under the age of 51 were tracked from the onset of the epidemic until April 2021. They were told to wear the Ava bracelet at night, the device records data every 10 seconds so you get at least four hours of sleep. This tool is not randomly selected: its operation is based on a machine learning algorithm to detect ovulation days with 90% accuracy.
A difference between several physiological parameters before the onset of symptoms
After waking up, the wristbands were synchronized with a companion smartphone app, which participants used to record any activity of the central nervous system, such as alcohol, prescription drugs and recreational drugs, and any symptoms of COVID-19. Each of them regularly took rapid antibody tests for SARS-CoV-2, the virus was responsible for the COVID-19 infection, and those who showed indicative symptoms also underwent RT-PCR tests. Finally, additional information such as age, gender, smoking status, blood type, number of children, exposure to family acquaintances or colleagues who tested positive for COVID-19 and status vaccine were considered. The study found that 127 people became infected during the study, in part because most of them said they had contact with family members, relatives or co-workers. Who tested positive for a COVID-19 infection.
Also to discover: Here is the most common and most feminine watch in the market
A total of 1.5 million hours of physiological data were recorded and confirmed Covid-19 out of 127 people, of whom 66 (52%) kept their device for at least 29 days and were included for analysis. Surveillance data showed significant changes in five physiological indicators during incubation, pre-signs, symptoms, and recovery of Covid-19 compared to the baseline system, with symptoms lasting an average of 8.5 days. The scientific team estimated that 68% of people tested positive for Covid-19 two days before the onset of symptoms using health trackers and algorithms, and that the tool’s accuracy was close to 80%. How can the usefulness of this technology for such screening be explained? It has been shown that the onset of COVID-19 infection may be characterized by an abnormal decrease in oxygenation in the blood, a phenomenon that can cause heart and respiratory rhythms to be detected by the attached bracelet. However, researchers acknowledge that this study has limitations.
First, the results were based on a small sample of people who were relatively young, therefore less likely to have severe symptoms of Covid-19 and who were not racially diverse. This led him to confirm that a PCR test must be used as a reference to confirm the infection. But this combination of trackers, mobile apps and algorithms is currently being tested in a much larger group of 20,000 people across the Netherlands, with results expected later this year. Based on these first observations, researchers are hopeful that it is a highly promising tool for the presymptomatic or even asymptomatic identification of Covid-19. ” This is an easy-to-use, low-cost way for people to track their health and well-being during an epidemic. Our research shows how these devices, combined with artificial intelligence, can push the boundaries of personalized drugs and detect diseases before symptoms appear, potentially reducing viral infections. “, They conclude.