Skip to main content

The asymptomatic covid-19 patients are more difficult to trace as these people do not know that they are sick. However to overcome this problem, MIT has found out a solution the answer to which lies in the use of Artificial Intelligence. In this direction, Researchers at Massachusetts Institute of Technology (MIT) in one of their latest researches have found out that asymptomatic cases of COVID-19 may differ from healthy individuals in the way they cough. The study shows that an AI model can detect asymptomatic covid cases by analysing the sound of their coughs.

To conduct the study, researchers used forced-cough recording submitted by volunteers via smartphones, laptops and web browsers. Using this collected information, the AI model was then trained using tens of thousands of spoken words and coughs. The AI model is based on four algorithms which analysed the data and resultantly it accurately identified 98.5% of coughs from confirmed cases of COVID-19 and detected those cases who had no symptoms but tested positive with 100% accuracy. The study is published in the IEEE Journal of Engineering in Medicine and Biology. The asymptomatic covid-19 patients are more difficult to trace as these people do not know that they are sick. Ho

The uniqueness of this model lies in the fact that it can detect who may be a carrier of COVID-19 even without any visible physical symptoms, just by hearing the way a person coughs. The human ear cannot differentiate between the cough of a healthy person and that of an unhealthy one but this can be picked up by Artificial Intelligence.

The study also emphasises that a person’s sentiment is embedded in the way he/she coughs. AI by analysing one’s cough easily pick up things like the person’s mother tongue, gender or even emotional state. In the long term, the research team intends to incorporate this AI model into a user- friendly application so that it can be made accessible to a large number of people. In the form of an application this model can be convenient, free and non-invasive screening tool for coronavirus.


InnoHEALTH magazine digital team

Author InnoHEALTH magazine digital team

More posts by InnoHEALTH magazine digital team

Leave a Reply