CAMBRIDGE (CBS) — Could your phone one day tell you if you’re likely to have COVID-19 based on the sound of your cough? That’s what scientists at MIT envision.
Researchers there have discovered that asymptomatic people – those who do not have any coronavirus symptoms – may sound different from healthy people in the way that they cough. MIT says the human ear can’t tell the difference but artificial intelligence can.READ MORE: Massachusetts Reopening Plan: COVID Restrictions Loosen Monday, Including Restaurant Capacity
The research team collected tens of thousands of coughs that people voluntarily submitted through web browsers and phones.
“When they fed the model new cough recordings, it accurately identified 98.5 percent of coughs from people who were confirmed to have Covid-19, including 100 percent of coughs from asymptomatics — who reported they did not have symptoms but had tested positive for the virus,” MIT stated.
Researchers have found that asymptomatic Covid-19 patients may have distinctive coughs. Indecipherable to the human ear, the differences can be picked up by artificial intelligence. Cellphone-recorded coughs could provide a convenient screening tool. https://t.co/OyHqC2KqNk pic.twitter.com/0kYdEIXQkd
— Massachusetts Institute of Technology (MIT) (@MIT) October 29, 2020READ MORE: 'In Like A Lion': March Weather Brings Drastic Swing In Temperatures This Week
The next step is to create an easy-to-use app with the model. Researchers say that it could be a great noninvasive prescreening tool to figure out who is likely to have the coronavirus; they even think it could be incorporated into smart speakers so people could be screened daily.
“Pandemics could be a thing of the past if pre-screening tools are always on in the background and constantly improved,” the researchers said.
Click here to read more about MIT’s research.MORE NEWS: South Attleboro MBTA Station Closes Due To 'Deteriorating' Pedestrian Bridge