Skip to main content
SearchLoginLogin or Signup

Review 1: "The Acoustic Dissection of Cough: Diving into Machine Listening-based COVID-19 Analysis and Detection"

This preprint reports on a machine learning model for detecting COVID-19 by analyzing patients’ cough sounds. Reviewers deemed the findings potentially informative and promising, with a few limitations that could be addressed.

Published onApr 07, 2022
Review 1: "The Acoustic Dissection of Cough: Diving into Machine Listening-based COVID-19 Analysis and Detection"
1 of 2
key-enterThis Pub is a Review of
The Acoustic Dissection of Cough: Diving into Machine Listening-based COVID-19 Analysis and Detection
Description

AbstractPurposeThe coronavirus disease 2019 (COVID-19) has caused a crisis worldwide. Amounts of efforts have been made to prevent and control COVID-19’s transmission, from early screenings to vaccinations and treatments. Recently, due to the spring up of many automatic disease recognition applications based on machine listening techniques, it would be fast and cheap to detect COVID-19 from recordings of cough, a key symptom of COVID-19. To date, knowledge on the acoustic characteristics of COVID-19 cough sounds is limited, but would be essential for structuring effective and robust machine learning models. The present study aims to explore acoustic features for distinguishing COVID-19 positive individuals from COVID-19 negative ones based on their cough sounds.MethodsWith the theory of computational paralinguistics, we analyse the acoustic correlates of COVID-19 cough sounds based on the COMPARE feature set, i. e., a standardised set of 6,373 acoustic higher-level features. Furthermore, we train automatic COVID-19 detection models with machine learning methods and explore the latent features by evaluating the contribution of all features to the COVID-19 status predictions.ResultsThe experimental results demonstrate that a set of acoustic parameters of cough sounds, e. g., statistical functionals of the root mean square energy and Mel-frequency cepstral coefficients, are relevant for the differentiation between COVID-19 positive and COVID-19 negative cough samples. Our automatic COVID-19 detection model performs significantly above chance level, i. e., at an unweighted average recall (UAR) of 0.632, on a data set consisting of 1,411 cough samples (COVID-19 positive/negative: 210/1,201).ConclusionsBased on the acoustic correlates analysis on the COMPARE feature set and the feature analysis in the effective COVID-19 detection model, we find that the machine learning method to a certain extent relies on acoustic features showing higher effects in conventional group difference testing.

RR:C19 Evidence Scale rating by reviewer:

  • Potentially informative. The main claims made are not strongly justified by the methods and data, but may yield some insight. The results and conclusions of the study may resemble those from the hypothetical ideal study, but there is substantial room for doubt. Decision-makers should consider this evidence only with a thorough understanding of its weaknesses, alongside other evidence and theory. Decision-makers should not consider this actionable, unless the weaknesses are clearly understood and there is other theory and evidence to further support it.

***************************************

Review:

The attempt of the authors in this study is well-appreciated. Not only have the authors tried to distinguish between COVID and non-COVID subjects, but they also focused on the explainability of the models by comparing feature relevance. The limitations of the work are clearly described, particularly those related to the COUGHVID dataset.

  1. The dataset in terms of COVID (n = 210) vs. non-COVID (n = 1201) classes is highly imbalanced, which could affect the performances of the classifiers. Although it is mentioned that balanced class weights were applied to each SVM model in order to mitigate the data imbalance problem, the corrective measures for other models were not applied or described.

  2. The authors used the unweighted average recall to evaluate the classification performance purposefully without considering the data imbalance characteristics. The rationale for this approach should be further elaborated.

  3. The UARs of best models exceed 0.5 by a small degree, albeit with statistical significance. Further improvement is needed before they can be used for automatic detection of COVID-19.

  4. It would be helpful if the authors can discuss the pros and cons of all seven classifier models and which model is most suitable for the task given the nature of the dataset.

  5. The feature analysis in the result section is hard to follow, particularly for readers not well familiar with the feature sets used in the study. More elaboration would be helpful.

Connections
1 of 3
Comments
0
comment

No comments here

Why not start the discussion?