FDA grants emergency authorization to ‘machine learning-based’ COVID detection device

The Food and Drug Administration this week gave emergency-use authorization to a "machine learning-based" device that will reportedly work to detect COVID even in cases in which no immediate symptoms are evident.

The device, manufactured by Tiger Tech Solutions, "identifies certain biomarkers that may be indicative of SARS-CoV-2 infection … in asymptomatic individuals over the age of 5," the FDA said in a press release. 

The device works by reading signals of a patient’s blood flow using an armband. "The sensors first obtain pulsatile signals from blood flow over a period of three to five minutes," the FDA said. 

"Once the measurement is completed," the statement continued. “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."

Hypercoagulation "is known to be a common abnormality in COVID-19 patients," the FDA also says. 

The device will also reportedly be able to detect "other hypercoagulable conditions (such as sepsis or cancer) or hyper-inflammatory states (such as severe allergic reactions)," the agency noted.