How you could be diagnosed with coronavirus by your own PHONE: Scientists are developing an app that uses the device's microphone to 'measure changes in airway sounds linked to COVID-19'

A smartphone app may be able to diagnose coronavirus by using the microphone in the device to measure changes in breathing sounds, the developers claim.

Researchers from the University of Pennsylvania say, if successful, their work would provide a 'low cost solution' to testing an entire population quickly.

It is still at the planning stage so it could be some time before it is available in app stores - the team say they first have to design new 'acoustic waveforms'.

The technology will use artificial intelligence to examine the sound coming from human airways and determine if it matches those from COVID-19 patients.  

When developed the app will use existing hardware and computing power of normal smartphones to provide 'non-invasive at-home testing', developers claim.  

Current testing to see if someone has COVID-19 requires taking a swab of the nose and back of the throat, which is then tested in a lab. The swab can be done from home but has to be sent through the post for testing. 

'In this project, we will develop new mobile sensing and artificial intelligence techniques for in-home evaluation of COVID-19 in an effort to quickly and effectively identify viral disease carriers,' said Wei Gao, lead researcher. 

'We hope this work will also help identify negative cases caused by other diseases with similar symptoms, and therefore, help eliminate unnecessary hospital visits during this pandemic,' he said.

Gao and his team will use smartphones' microphones and speakers to develop acoustic sensing technology that can measure changes in human airway mechanics.  

Users will need to use an adapter as a mouthpiece so that the phone's microphone and speaker can record and transmit acoustic signals from human airways. 

'We will then develop new signal processing techniques for accurate measurements and eventually apply deep learning techniques to create generic models that depict the core characteristics of airway mechanics,' said Gao.

If successful, the researchers say it will allow them to identify cases of COVID-19 without requiring a hospital visit - which could help contain the virus.

This isn't the only project looking to use smartphones to detect signs of coronavirus, a team of researchers in Switzerland are collecting cough sounds.

The AI researchers from Ecole Polytechnique Federale de Lausanne are working on a similar system to the Pennsylvania team.

They are looking at cough sounds from healthy and confirmed COVID-19 patients in a project called Coughvid.

'It seems clear that a high proportion [of coronavirus patients] have this type of dry cough that’s different from the flu or allergies,' lead researcher Tomas Teijeiro told the Wall Street Journal. 

He said it is uncertain just how definite the diagnose will be but hopes through further research they will be able to make it more accurate.  

'It seems clear that a high proportion have this type of dry cough that's different from the flu or allergies,' said Teijeiro.

A new continuous cough is one of the main symptoms of the COVID-19 virus along with a high temperature. People with either are asked to isolate. 

There is concern that using audio to diagnose coronavirus could be unreliable and offer up false positives - potentially sending healthy people to hospitals.