The Massachusetts Institute of Technology (MIT) has developed an algorithm that accurately spots those infected with coronavirus based on their cough.
The algorithm was able to correctly identify 98.5 percent of people who showed symptoms and had confirmed cases of COVID-19. Additionally, the success rate of the algorithm was 100 percent in case of asymptomatic COVID-19 carriers.
The researchers would need regulatory approval to develop it into an app.
The team pointed out, "People who are asymptomatic may differ from healthy individuals in the way that they cough. These differences are not decipherable to the human ear. But it turns out that they can be picked up by artificial intelligence."
The recordings used to train the artificial intelligence (AI) model were submitted by volunteers over 70,000 samples and about 2,500 of the total volunteers were confirmed to have COVID-19.
MIT's team comprises of Brian Subirana, Jordi Laguarta and Ferran Hueto from MIT's Auto ID Laboratory.
"The effective implementation of this group diagnostic tool could diminish the spread of the pandemic if everyone uses it before going to a classroom, a factory, or a restaurant." said Subirana.
Currently, MIT is working with several hospitals that will provide additional recordings to improve the model further.
This AI model is based on studies exploring how coughs and alterations in the speech patterns can indicate other diseases including Alzheimer's.