Researchers at the Massachusetts Institute of Technology (MIT) have designed an artificial intelligence (AI) algorithm to identify Coronavirus patients only by the sound of their coughs.
MIT researchers have said that even if a Coronavirus patient does not exhibit any symptoms of the disease, their cough sounds slightly different from the cough of a healthy individual because of the impact of the virus on their lungs and vocal cords.
These subtle differences are inaudible to the human ear. However, with an accuracy of 98.5%, the AI algorithm successfully distinguishes between the cough of a Coronavirus patient and a healthy person.
Moreover, Coronavirus is extremely difficult to spot when patients do not exhibit any symptoms. The AI algorithm gives 100% accurate results in the case of asymptomatic Coronavirus patients.
According to the Centers for Disease Control and Prevention (CDC), almost 40% of the total Coronavirus patients have been asymptomatic.
The researchers have argued that the algorithm will allow healthcare authorities to track down asymptomatic Coronavirus cases before they spread the disease.
MIT scientist, Brian Subirana, has said:
The effective implementation of this diagnostic tool could diminish the spread of the pandemic if everyone uses it before going to a classroom, a factory, or a restaurant.
MIT researchers are hopeful that the AI algorithm, after receiving approval from the Food and Drug Administration (FDA), will be transformed into a free application that will check users for Coronavirus and report suspicious coughs to healthcare authorities for further testing.