Smart diagnostics: AI tech can hear COVID in a cough

Full article issued by RMIT University.

An ARC Discovery Projects grant has supported a ground-breaking advance in detecting COVID-19 from the way people cough, which could pave the way to a new generation of diagnostic mobile phone apps.

The new research by computer scientists at RMIT University reveals an AI model that can hear the effects of COVID in the sound of a forced cough, even when people are asymptomatic.

Lead researcher, Dr Hao Xue, said with further development, their algorithm could power a diagnostic mobile phone app.  

'We’ve overcome a major hurdle in the development of a reliable, easily-accessible and contactless preliminary diagnosis tool for COVID-19,' said Dr Xue, who is a Research Fellow in RMIT’s School of Computing Technologies. 

'A mobile app that can give you peace of mind during community outbreaks or prompt you to seek a COVID test could have significant benefit in slowing the spread of the virus by those who have no obvious symptoms.'

Co-researcher Professor Flora Salim said previous attempts to develop this type of technology, like those at MIT and Cambridge, relied on huge amounts of meticulously-labelled data to train the AI system, a limitation that had proven a challenge for this technology’s practical application in the real world, until now.  

'What’s most exciting about our work is we have overcome this problem by developing a method to train the algorithm using unlabelled cough sound data,' says Professor Salim.

Dr Xue says that the method they developed could also be extended for other respiratory diseases.

'With just a little tweaking and suitable data, we could use this to test for Tuberculosis or other respiratory illnesses, or even design it for combined multi-diseases detection or classification system.'

 

Image Credit: Pixabay (Public Domain).