Researchers from the Embedded Systems Laboratory of École polytechnique fédérale de Lausanne (EPFL), Switzerland are working on a mobile app that uses AI to detect COVID-19 infection by analyzing coughing sounds. According to researchers, they were inspired to develop the app after seeing reports from doctors about COVID-19 positive patients having coughs with a distinctive sound. The app currently has a 70% accuracy rate but, to further train and increase its AI’s accuracy, the team is asking for submissions of cough recordings from COVID-19 positive patients to increase its database.
“The idea is not new. Doctors already listen to their patients’ coughs to diagnose whooping cough, asthma and pneumonia,” David Atienza, a professor at EPFL’s School of Engineering and head of EPFL said. “We wanted to develop a reliable, easy-to-use system that could be deployed for large-scale testing. The app has a 70% accuracy rate,” he added.
The team expects to release the mobile app in the next few weeks, but until then, patients who wish to contribute to the project can record their cough at the coughvid website. Since coughing in this situation is a dangerous activity, the team doesn’t recommend having COVID-19 positive patients to cough directly on their phones. Rather, they included instructions on how to properly cough while recording the sound.