Do you have a connected bracelet, like Xiaomi’s latest Smart Band 7? These activity trackers really don’t cost that much anymore. And according to researchers, infusing them with a little AI would be enough for them to take a leading role in health — particularly in screening for the coronavirus (COVID-19).
In a study published in BMJ Open, researchers at the Dr. Rish Mediacal Laboratory (Lichtenstein) actually assumes it “Wearable sensor technologies can help detect Covid-19 in the period before symptoms appear.”
Researchers use connected wristbands to better detect COVID-19 earlier
In fact, under certain conditions, machine learning models are capable of making complex connections between data from biometric markers and a patient’s health status. For example, we recall screening experiments that could identify people with COVID-19 by analyzing the sound of their cough.
With the added bonus of fairly high reliability. The idea is to adapt the same logic based on the data that current smartbands can already collect – without adding an additional sensor. By aggregating this data in a machine learning model for COVID-19 screening, your watch could display an alert in the event of a suspected infection.
This allows the carrier to take a lab test immediately and isolate themselves sooner, which can drastically reduce the spread of the virus. To reach this conclusion, the researchers tested the capabilities of the “Ava” bracelet: a tracker usually intended for women who want to know the ideal fertility window to get pregnant.
The device collects data on respiratory rate, heart rate, heart rate variability, wrist skin temperature, and blood flow. The researchers thus followed 1,163 patients under the age of 51 from the beginning of the pandemic until April 2021.
Everyone had to wear the bracelet at night – and the bracelet was connected to an application in which the user had to mention anything that could falsify the measurement (consumption of alcohol, drugs, medication, etc.). They also had to report any symptoms indicative of Covid-19. At the same time, the participants had to carry out regular antigen tests (and PCR in the case of sick people).
The researchers thus demonstrated the existence of significant physiological changes in the period before the onset of symptoms. However, thanks to an algorithm, 68% of the participants who eventually contracted COVID-19 were alerted two days before the first symptoms appeared.
The researchers are currently continuing their study to confirm the results and refine their algorithm. The new study analyzes physiological data from 20,000 patients residing in the Netherlands. The results should be available by the end of the year.