Researchers identify Covid-19 infected by the sound of their cough

Researchers in Spain have said they can tell whether someone has Covid-19 by the sound of their cough.

The system, created by experts from Pompeu Fabra University in Barcelona, uses a database of coughs from people who have tested positive and negative for the virus.

An artificial intelligence-based program then matches new recordings to check for features of a coronavirus cough, identifying people suffering from Covid-19.

"Based on these data, we have developed and evaluated two different neural networks that, using one second of audio, predict positive or negative Covid-19," said the authors.

It is not the first time AI has been used in this way, said Helena Cuesta, a member of the research team.

Other studies have detected respiratory conditions by analysing coughs and sneezes with AI.

Late last year, researchers from the Massachusetts Institute of Technology in the US developed an algorithm that was able to correctly identify people with Covid-19 by their coughs.

The program, which analyses sound patterns, achieved a 98.5 per cent success rate in tests involving people with a Covid-19 diagnosis.

In asymptomatic patients with confirmed Covid-19, the figure rose to 100 per cent.

The systems are able to identify coronavirus patients accurately because the virus changes the way a person produces sound, although the difference is not detectable by human ears.

The PCR swab remains the gold standard for Covid-19 testing, but it is not the only screening tool at governments’ disposal.

Sniffer dogs, which are said to be highly accurate at picking out sufferers from a crowd, have been stationed at airports across the UAE.

The Emirates also recently started using scanners at shopping malls, some residential areas and at all land and air entry points. These measure electromagnetic waves, which change when RNA particles of the virus are present in a person’s body.

UAE Covid-19 scanners - in pictures