Abstract
Digital mass testing for COVID-19 via a mobile phone application could be made possible through machine learning and its ability to identify patterns in data. COVID-19 appears to confer unique features in the audio produced by infected individuals,1 and machine learning COVID-19 detection from breath, cough, and speech audio recordings has yielded promising results.2–4 In this critique, we present seven major issues with this research and argue that further investigation is needed before conclusions about the detectability of COVID-19 from audio can be made.
Highlights
Digital mass testing for COVID-19 via a mobile phone application could be made possible through machine learning and its ability to identify patterns in data
We present seven major issues with this research and argue that further investigation is needed before conclusions about the detectability of COVID-19 from audio can be made
Many of these issues relate to a single question: are the learnt audio representations, which correlate with COVID-19 in the various collected datasets, truly audio biomarkers caused by COVID-19?
Summary
Digital mass testing for COVID-19 via a mobile phone application could be made possible through machine learning and its ability to identify patterns in data. COVID-19 appears to confer unique features in the audio produced by infected individuals,[1] and machine learning COVID-19 detection from breath, cough, and speech audio recordings has yielded promising results.[2,3,4] In this critique, we present seven major issues with this research and argue that further investigation is needed before conclusions about the detectability of COVID-19 from audio can be made. One concern is that machine learning algorithms may distinguish between healthy individuals and individuals who are generally unwell, rather than detecting COVID-19 itself.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have