Researchers are working on an app that could potentially detect COVID-19 in a user based on the sound of their cough.
Called Coughvid, the app from EPFL’s (Ecole Polytechnique Fédérale de Lausanne) Embedded Systems Laboratory, a technology research institute located in Switzerland, would ideally be able to distinguish a typical “wet cough,” such as one that person has from a normal cold or seasonal allergies, from a COVID-19 cough, which has a dry characteristic.
The EPFL claims that the app, which is still under development, would have a 70% success rate in determining if a cough was indicative of COVID-19. However, researchers do not claim the app to be a substitute for seeking help from a medical professional.
“The app targets to reach a 70% accuracy rate when enough data from a broad spectrum of patients is collected and used for testing,” said David Atienza, a professor at EPFL’s School of Engineering who is also the head of ESL and a member of the Coughvid development team. “That said, people who think they may have the disease should still go see their doctor. Coughvid is not a substitute for a medical exam.”
The World Health Organization says that a dry cough is one of the most common symptoms of COVID-19 among fever and tiredness. Researchers developing Coughvid say that dry coughs can be detected by the sound they produce.
A website has been dedicated by the organization in collecting audio recordings of coughs from people who have been diagnosed with COVID-19. Those submitting the sound of their cough will be able to do so by using your smartphone provided by the institute.
The app is still being developed as more cough samples are needed.
The World Health Organization says that a dry cough is one of the most common symptoms of COVID-19 among fever and tiredness and researchers developing Coughvid say that dry coughs can be detected by the sound they produce.
Researchers add that cough sound analysis has proven successful in diagnosing other respiratory conditions such as asthma and pneumonia.
“We propose to leverage signal processing, pervasive computing, and machine learning to develop an Android application and website to automatically screen COVID-19 from the comfort of people’s homes,” the institute said in a press release.
“We’ll release the app once we’ve accumulated enough data. It could take a few more weeks,” said Atienza.
As of April 17, there have been over 3.4 million people who have been tested for the novel coronavirus in the United States, according to the most recent data from Johns Hopkins Coronavirus Resource Center. There are more than 2.4 million confirmed cases across the world.