École Polytechnique Fédérale de Lausanne is developing an diagnostic test app called “Coughvid” that would listen to people cough and use AI to determine whether they sound like a COVID-19 patient. The app is aimed to help reduce the number of people going to doctors demanding for a test when they don’t exhibit the symptoms and to understand where the virus is spreading.
- According to WHO, COVID-19 patients exhibt a dry cough — a chirping intake of breath at the end — that differed from typical wet cough people experience with the common cold or allergies.
- AI technology is used to distinguish between different kinds of coughs the same way doctors listen to patients’ cough.
- Volunteers can upload their cough recordings to the project’s website.
- Users are kept anonymous, but they are asked for permission to save their location.
- The app also has instructions on how to properly and safely test your coughing using a phone.
- Although the app has been reported to have a 70% accuracy rate, it’s AI is still in the process of learning from more data sets as more people try it out.
- More than 15,000 audio samples of people coughing have been gathered, 1,000 of which came from people who reported being diagnosed with COVID-19.
- Once completed, the Coughvid app could be used as a tool to recommend whether users should seek out a coronavirus test or further treatment.
Source(s): Slash Gear, Business Insider, WBUR