First Machine-learning Covid Screening Device Authorized
FDA has granted Tiger Tech Solutions an emergency use authorization for the first machine learning-based Covid-19 non-diagnostic screening device that identifies certain biomarkers that are indicative of some types of conditions, such as hypercoagulation. The device identifies certain biomarkers that may be indicative of Covid-19 infection as well as other hypercoagulable conditions (sepsis or cancer) or hyper-inflammatory states (severe allergic reactions), in asymptomatic individuals aged 5 year and older. The device is intended for use following a temperature reading that does not meet criteria for fever in settings where temperature check is being conducted. The agency says the device is not a substitute for a Covid-19 diagnostic test and is not intended for use in individuals with Covid symptoms.
The device comprises an armband with embedded light sensors and a small computer processor. “The sensors first obtain pulsatile signals from blood flow over a period of three to five minutes,” an FDA release says. “Once the measurement is completed, the processor extracts some key features of the pulsatile signals, such as pulse rate, and feeds them into a probabilistic machine learning model that has been trained to make predictions on whether the individual is showing certain signals, such as hypercoagulation in blood...The result is provided in the form of different colored lights used to indicate if an individual is demonstrating certain biomarkers, or if the result is inconclusive.”