Algorithm can identify people with Covid by the sound of their cough
An algorithm has been developed that can identify people with coronavirus only by the sound of their coughs.
The Massachusetts Institute of Technology (MIT) lab developed the artificial-intelligence algorithm that claims to have a 98.5% success rate. Researchers said that people with coronavirus produce sound differently which can be picked up by the technology but not human ears.
Co-author of the paper and scientist Brian Subirana said: ‘The way you produce sound changes when you have Covid, even if you’re asymptomatic. Practical use cases could be for daily screening of students, workers and public, as schools, jobs, and transport reopen, or for pool testing to quickly alert of outbreaks in groups,’
The MIT lab has collected around 70,000 audio samples of different coughs with 2,500 coughs from confirmed coronavirus patients.
Visit our live blog for the latest updates Coronavirus news live
It will help the artificial intelligence to learn to detect Covid-19 coughs just as doctors fed ‘a machine a lot of X-rays so it learnt to detect cancer’ said Artificial-intelligence expert Calum Chace.
MIT is not the first to undertake such research, with Cambridge University, Carnegie Mellon University and UK health start-up Novoic all been working on similar initiatives.
Cambridge’s sound project reported an 80% success rate in July and it now says it had about 30,000 cough and breath samples.
Mr Chace said: ‘It’s an example of AI being helpful.
‘And, for once, I don’t see a lot of downside in this.’
Get in touch with our news team by emailing us at [email protected]
For more stories like this, check our news page.
Source: Read Full Article