MIT working to launch app that uses AI to detect COVID-19 in coughing sound

KGO logo
Monday, November 2, 2020
MIT working on app that can detect COVID-19 in cough
Researchers at MIT say their artificial intelligence model can identify asymptomatic COVID-19 carrier through a smartphone app.

SAN FRANCISCO (KGO) -- Researchers at MIT developed the algorithm for identifying asymptomatic people with COVID-19, with the help of artificial Intelligence.



They say it can differentiate between the forced coughs of asymptomatic people with COVID-19, from those of healthy people.



RELATED: Coronavirus research: Menlo Park lab using robots, AI to find COVID-19 medication



In a paper recently published in the IEEE Journal, the MIT reports they developed an "AI speech processing framework" that uses acoustics to pre-screen for COVID-19 from cough recordings. Testing the model from cough recordings collected from over 5,000 individuals, the model accurately identified 98.5% of coughs from people with confirmed COVID-19, and 100% of coughs from asymptomatic people who tested positive for the virus.



With the use of the AI model, researchers say they can produce a "free, non-invasive, real-time, any-time, instantly distributable, large-scale COVID-19 screening tool" that can help contain the spread of the virus.



MIT is working on a free smartphone app that anyone can use to test themselves daily for COVID-19.




If you have a question or comment about the coronavirus pandemic, submit yours via the form below or here.



Get the latest news, information and videos about the novel coronavirus pandemic here



RELATED STORIES & VIDEOS:


Copyright © 2024 KGO-TV. All Rights Reserved.