Imagine if you could open an app on your smartphone and simply cough to discover right there and then if you have COVID-19.
Researchers at the Massachusetts Institute of Technology (MIT) say they have developed such a method, which could be used as part of broader measures to get the virus under control.
The breakthrough research involved analyzing around 70,000 submitted audio samples of people’s coughs, among them around 2,500 recordings of people confirmed to have the virus at the time.
Using the gathered data, the research team created an artificial intelligence (A.I.) algorithm that it says is capable of telling if someone has the virus simply from the sound of their cough — even if they have no symptoms.
Conducting tests on a group of people already diagnosed with the virus, the algorithm had a success rate of 98.5%, while among an asymptomatic group whose coughs were forced, the rate increased to 100%.
A MIT news report said the cough of a COVID-infected individual is not the same as a cough by a healthy individual, but the difference is so subtle that it’s inaudible to the human ear. Technology using artificial intelligence, however, is able to spot the difference and, with a high degree of accuracy, determine if the person has the virus.
If the Food and Drug Administration allows MIT to incorporate the technology into a mobile app, the software could play a vital role in helping to quickly identify asymptomatic COVID-infected individuals, as well as those with symptoms. It would mean that something as simple as a daily cough into your smartphone could help to slow the spread of the virus as it would allow identified carriers to immediately isolate, thereby protecting others from infection.
MIT’s research team said, “A.I. techniques can produce a free, non-invasive, real-time, any-time, instantly distributable, large-scale COVID-19 asymptomatic screening tool to augment current approaches in containing the spread of COVID-19.”
In a research paper published online, it added: “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 team at MIT isn’t the only one developing this kind of technology, with researchers from Carnegie Mellon University in Pennsylvania, and Cambridge University in the U.K., working on separate though similar projects.
In other efforts, researchers have been training dogs to sniff out COVID-19 infections, with the animal in many cases able to identify coronavirus carriers even if they display no symptoms.