The US Food and Drug Administration has issued emergency use authorization for the first-ever machine learning-based COVID-19 non-diagnostic screening device, the American regulator announced Friday.
Titled the Tiger Tech COVID Plus Monitor, the device is meant to be used by trained medical personnel to identify biomarkers that could indicate infection by the novel coronavirus in asymptomatic patients. It could also detect other biomarkers for conditions like sepsis, cancer, or allergic reactions.
The device is only meant to be used after a temperature reading that does not reach fever level, and is not a substitute for a COVID-19 test.
The Tiger Tech monitor is an armband to be worn on the left arm during use. It functions by using its sensors to detect signals from the blood flow over a three-five minute period. These measurements, with other key features of the signal, are fed into a probabilistic machine-learning model in order to predict if there are signs of certain signals, such as hypercoagulation, a known common abnormality in COVID-19 patients.
Early tests have found that the Tiger Tech COVID Plus Monitor had a high success rate, accurately identifying certain biomarkers 98.6% of the time and correctly identifying a lack of said biomarkers 94.5% of the time.
“The FDA is committed to continuing to support innovative methods to fight the COVID-19 pandemic through new screening tools,” said Jeff Shuren, M.D., J.D., director of the FDA’s Center for Devices and Radiological Health.
“Combining the use of this new screening device that can indicate the presence of certain biomarkers with temperature checks could help identify individuals who may be infected with the virus, thus helping to reduce the spread of COVID-19 in a wide variety of public settings, including healthcare facilities, schools, workplaces, theme parks, stadiums and airports,” he said.