It has 98.5 per cent accuracy
As many parts of the world head into a second lockdown, researchers at MIT have developed an algorithm that can differentiate between the coughs of asymptomatic people who have COVID and those of healthy people.
The research, which is published in the IEEE Journal of Engineering in Medicine and Biology, was originally used to detect Alzheimers, but has been adapted to recognise coronavirus.
The idea is that the AI could pick up these differences in the coughs caused by neuromuscular impairment and other symptoms between healthy people and asymptomatic people with coronavirus – differences that those asymptomatic people would not be able to notice themselves.
Building on a pre-existing AI that’s been trained to pick up on biomarkers like vocal cord strength, lung capacity, and neuromuscular degeneration, a special COVID-specific assessment uses 4,000 cough samples, half from healthy people, half from asymptomatic coronavirus patients. According to the research, the AI correctly identified 98.5 per cent of the coughs from people with COVID.
Currently, the researchers are working on a free app that would enable anyone to cough into their smartphone and, essentially, get a pre-screening of whether they have COVID or not, even if they don’t have symptoms. Pretty impressive stuff.
Elsewhere, a robot has been built to fight coronavirus with UV light, while the YouTube ASMR community is cosplaying as nurses and doctors to perform mock POV coronavirus tests on viewers. Someone’s also designed a PPE rave suit for safe socialising in the club. It’s a Brave New World, people.