Researchers from Massachusetts Institute of Technology (MIT) in the US have developed an Artificial Intelligence (AI) model to diagnose asymptomatic COVID infections through cell-phone recordings of forced coughs.
Even though asymptomatic people do not exhibit any evident symptoms of the disease, the scientists have said that the way that they cough differs from healthy people - which may not be discernible to the human ear, PTI reported.
People had voluntarily submitted the cough recordings through web browsers on phones or laptops, described the paper published in the IEEE Journal of Engineering in Medicine and Biology.
The model identified 98.5% of coughs from people who were confirmed to have COVID-19, including 100% of those from asymptomatic people.
The scientists aim to incorporate the model into an app once approved and adopted as a free and non-invasive pre-screening tool for diagnosis, reported PTI. A person could log in, cough into the device and get an instant result which would inform them if they need a formal confirmation test.
Brian Subirana, a research scientist in MIT's Auto-ID Laboratory, said, "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.”
“We think this shows that the way you produce sound, changes when you have Covid, even if you are asymptomatic,” Subirana said.
(With inputs from PTI)
(At The Quint, we question everything. Play an active role in shaping our journalism by becoming a member today.)