Problem / solution statement (a few sentences)

In the wake of the COVID-19 pandemic, mass coronavirus testing has proven essential to governments in monitoring the spread of the disease, isolating infected individuals, and effectively “flattening the curve” of infections over time [1]. However, this oropharyngeal swab test is physically invasive and must be performed by a trained clinician. This requires patients to travel to a laboratory facility to get tested, thereby potentially infecting others along the way [2]. Ideally, testing would be performed noninvasively at no cost, and administered at the homes of potential patients to minimize contamination risk.

The World Health Organization (WHO) has reported that 67.7% of COVID-19 patients exhibit a “dry cough,” meaning that no mucus is produced, unlike the typical “wet cough” that occurs during a cold or allergies [3]. Dry coughs can be distinguished from wet coughs by the sound they produce, which raises the question of whether COVID-19 can be diagnosed by analyzing patients’ cough sounds. Such cough sounds analysis has proven successful in diagnosing respiratory conditions like pertussis [4], asthma, and pneumonia [5].

What it does

At the Embedded Systems Laboratory (ESL) at EPFL, 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. Test subjects will be able to simply download a mobile application, enter their symptoms, record an audio clip of their cough, and upload the data anonymously to our servers. We will then use state-of-the-art machine learning techniques to classify between cough sounds produced by COVID-19 patients, as opposed to healthy subjects or those with other respiratory conditions.

The application will be finalized at the coming LauzHack Against COVID-19, but in the meantime, we kindly ask that you spread the word about our website, on which people who have been diagnosed with COVID-19 can record the sounds of their coughs:

https://coughvid.epfl.ch/

We thank you for helping us develop tools to facilitate ubiquitous, noninvasive COVID-19 testing worldwide.

Achievements

If you want to know what we have achieved so far, you can check the detailed presentation of our project.

The demo of the app can be seen here.

Skills / competencies needed

Electrical engineering, Computer science, targeting to have a team with the following skills: Android programming, Biosignal processing and analysis, Machine Learning, Website management: HTML+Js, Python CGI scripting.

+ 100 more
Share this project:

Updates