researchers at MIT have created an artificial intelligence model that detects asymptomatic COVID-19 infections through cellphone-recorded coughs. the study has found out that asymptomatic patients may differ from healthy individuals in the way they cough and that these differences are not decipherable to the human ear but it turns out they can be picked up by AI.


until now, we know that COVID-19 asymptomatic patients don’t show, by definition, discernible symptoms of the disease. following some researches, MIT scientists have found that these people may show the symptoms in the way they cough. published in the IEEE journal of engineering in medicine and biology, the paper reports on an AI model that distinguishes asymptomatic people from healthy ones through forced-cough recordings. for it to work, the researches trained the model with tens of thousands of cough samples to the point that it is able to accurately identify 98.5% of coughs from COVID-19-infected people.

researchers at MIT create AI model that detects asymptomatic COVID-19 infections
image by christine daniloff, MIT



‘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,’ says co-author brian subirana, a research scientist in MIT’s auto-ID laboratory.


currently, the team is working on incorporating the model into a user-friendly app with the aim of having it approved by the FDA so that it can be used on a large scale. this potentially free, convenient and noninvasive prescreening tool could help identify the asymptomatic, which can be later on confirmed with a formal test.


‘the sounds of talking and coughing are both influenced by the vocal cords and surrounding organs. this means that when you talk, part of your talking is like coughing, and vice versa. it also means that things we easily derive from fluent speech, AI can pick up simply from coughs, including things like the person’s gender, mother tongue, or even emotional state. there’s in fact sentiment embedded in how you cough,’ subirana says. ‘so we thought, why don’t we try these alzheimer’s biomarkers [to see if they’re relevant] for covid.’



project info:


name: artificial intelligence model detects asymptomatic covid-19 infections through cellphone-recorded coughs

researches: MIT