Tue 9 Mar 21
Scientists have created a rapid primary screening tool for COVID-19 which can accurately diagnose people with the virus just by the sound of their cough.
This research, led by the University of Essex and published in the IEEE Transactions on Service Computing, could herald a quicker, cheaper and less invasive way of preliminary testing for the virus.
What sets this research apart from previous studies into COVID-19 coughs is the fact it has proved highly accurate at detecting the infection using more than 8,000 clinically validated samples which have been tested from certified laboratories. Other studies have used primarily crowdsourced samples captured through the internet or small samples of clinically validated samples.
Using 8,380 clinically-validated samples from hospitals in Spain and Mexico since April last year - 2,339 COVID-19 positive and 6,041 COVID-19 negative – the DeepCough3D screening tool proved to be 98% accurate in identifying whether the samples were positive or negative.
Lead researcher Dr Javier Andreu-Perez, of the Smart Health Technologies Group at the Centre for Computational Intelligence, said: ”We are delighted with the promising results of this novel screening tool, which could prove a real game-changer and essential addition to our arsenal of tools to combat the pandemic as it is far less invasive than most other COVID-19 tests and also offers rapid results, paving the way to point-of-need pre-screening testing solutions.”
The research involved using advanced methods of artificial intelligence and pattern recognition to analyse the sounds in time-frequency representations that are beyond the human perception, and the research team has been able to recognise symptomatic and asymptomatic coughs which are the result of this type of virus.
“This work highlights new evidence that it is worth pursuing intelligent biometric systems, such us from coughing sounds analysis, as a valuable rapid preliminary screening tool for COVID-19,” added Dr Andreu-Perez.
In addition to developing the COVID-19 recognition test using coughs, the researchers investigated utilising the tool to also recognise the extent of the infection in COVID-19 positive participants. They were able to classify the coughs into three severity levels to some degree, which could help with the effective management of healthcare facilities during a pandemic, such as ventilators.
The next phase of the project will be looking for health collaborations to carry out interventional field studies using the developed technologies and tools (web-app test service), and support for a wider release and certification.
Oracle Corp’s program Oracle for Research is providing support to the project.