Audio feature ranking for sound-based COVID-19 patient detection

TL;DR

This study systematically ranks 15 audio features for sound-based COVID-19 detection, significantly improving classification accuracy and aiding the development of reliable non-invasive screening tools.

Contribution

It provides a comprehensive comparison and ranking of audio features for COVID-19 detection, identifying the most effective features to enhance model accuracy.

Findings

Top features improved accuracy by up to 17% on Cambridge dataset.

Top features increased accuracy by up to 10% on Coswara dataset.

The study offers a validated feature ranking for future COVID-19 audio classification models.

Abstract

Audio classification using breath and cough samples has recently emerged as a low-cost, non-invasive, and accessible COVID-19 screening method. However, a comprehensive survey shows that no application has been approved for official use at the time of writing, due to the stringent reliability and accuracy requirements of the critical healthcare setting. To support the development of Machine Learning classification models, we performed an extensive comparative investigation and ranking of 15 audio features, including less well-known ones. The results were verified on two independent COVID-19 sound datasets. By using the identified top-performing features, we have increased COVID-19 classification accuracy by up to 17% on the Cambridge dataset and up to 10% on the Coswara dataset compared to the original baseline accuracies without our feature ranking.