Coronavirus Latest Update: With asymptomatic people testing positive for coronavirus becoming a major cause of concern, researchers are finding a new way out to find if there are any indications in a human’s cough that could detect COVID infection. Also Read – ‘Can Call it Third Wave,’ Says Kejriwal as Delhi Marks Over 6,000 Infection For 2nd Day in a Row
Researchers have confirmed that an artificial intelligence (AI) tool that can detect if there are any indications in a human’s cough that could point to a COVID infection, before seeking medical help and further testing. Also Read – US Elections 2020: Milford’s Unmasked Voters Can Cast Ballots, But May Have to Stay Outside
Researchers at the Massachusetts Institute of Technology (MIT) are saying that artificial intelligence (AI) tool can detect covid-19 through human’s cough. According to their research studies, they say that people who are asymptomatic may differ from healthy people in the way that they cough and while differences are not decipherable to the human ear, AI can detect these. Moreover, the researchers are also working to make this tool available to users as an app. Also Read – Alert! Genetic Mutation in Novel Coronavirus May Have Made it More Contagious
In a research article published in the IEEE Journal of Engineering in Medicine and Biology, the researchers say that by recording cough through smartphone or a laptop or PC can help AI detect if there are any changes.
They are also opine that AI tool has accurately identified 98.5 percent of coughs from people who were confirmed to have Covid-19. The AI tool also has 100 per cent accuracy rate for coughs from asymptomatic humans who did not have symptoms but later tested positive for COVID-19. This they are saying after confirming that AI has been trained on tens of thousands of cough recording samples.
“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,” co-author Brian Subirana, a research scientist in MIT’s Auto-ID Laboratory, was quoted as saying by News18.
The smart app, as the researcher are developing, will allow an individual to record the sound of their cough on their phone, and get immediate guidance on whether they might be infected.
They say that it was first trained on a general machine-learning algorithm known as ResNet50 to distinguish and separate sounds associated with different degrees of vocal cord strength. This worked with more than 10000 hours of speech to pick out specific words.
After this, they also did another second level of training on the neural network that distinguishes emotional states that often show up in speech. The final step done in the app was an algorithm that distinguishes between strong and weak coughing, the latter being a sign of muscle weakness.