A mobile app that can detect COVID-19 from the sound of your voice has been developed by researchers from Maastricht University in the Netherlands. The app is claimed to detect infections “more accurately than lateral flow tests”.
The app is available on Google Play and Apple’s App Store and it’s called the COVID-19 Sounds App.
COVID-19 causes inflammation in the respiratory tract and vocal cords, which results in a change in the voice of the patient.
The team of scientists investigated whether they could use these symptoms to accurately diagnose the disease. They used artificial intelligence (AI) with an accuracy rate of more than 89% which makes the app more reliable than rapid antigen tests. The app’s model was trained and tested using data from over 893 audio samples gathered from 4,352 healthy and non-healthy participants. A total of 308 patients turned out to be positive for COVID-19.
Wafaa Aljbawi, a researcher at the Institute of Data Science, Maastricht University said:
“These promising results suggest that simple voice recordings and fine-tuned AI algorithms can potentially achieve high precision in determining which patients have Covid-19 infection. Such tests can be provided at no cost and are simple to interpret. Moreover, they enable remote, virtual testing and have a turnaround time of less than a minute.”
A voice analysis technique, Mel-spectrogram analysis, diagnoses voice features such as loudness, power, and variation over time is used in the app.
