Cargando…
COVID-19 cough classification using machine learning and global smartphone recordings
We present a machine learning based COVID-19 cough classifier which can discriminate COVID-19 positive coughs from both COVID-19 negative and healthy coughs recorded on a smartphone. This type of screening is non-contact, easy to apply, and can reduce the workload in testing centres as well as limit...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier Ltd.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8213969/ https://www.ncbi.nlm.nih.gov/pubmed/34182331 http://dx.doi.org/10.1016/j.compbiomed.2021.104572 |
_version_ | 1783709965493469184 |
---|---|
author | Pahar, Madhurananda Klopper, Marisa Warren, Robin Niesler, Thomas |
author_facet | Pahar, Madhurananda Klopper, Marisa Warren, Robin Niesler, Thomas |
author_sort | Pahar, Madhurananda |
collection | PubMed |
description | We present a machine learning based COVID-19 cough classifier which can discriminate COVID-19 positive coughs from both COVID-19 negative and healthy coughs recorded on a smartphone. This type of screening is non-contact, easy to apply, and can reduce the workload in testing centres as well as limit transmission by recommending early self-isolation to those who have a cough suggestive of COVID-19. The datasets used in this study include subjects from all six continents and contain both forced and natural coughs, indicating that the approach is widely applicable. The publicly available Coswara dataset contains 92 COVID-19 positive and 1079 healthy subjects, while the second smaller dataset was collected mostly in South Africa and contains 18 COVID-19 positive and 26 COVID-19 negative subjects who have undergone a SARS-CoV laboratory test. Both datasets indicate that COVID-19 positive coughs are 15%–20% shorter than non-COVID coughs. Dataset skew was addressed by applying the synthetic minority oversampling technique (SMOTE). A leave-p-out cross-validation scheme was used to train and evaluate seven machine learning classifiers: logistic regression (LR), k-nearest neighbour (KNN), support vector machine (SVM), multilayer perceptron (MLP), convolutional neural network (CNN), long short-term memory (LSTM) and a residual-based neural network architecture (Resnet50). Our results show that although all classifiers were able to identify COVID-19 coughs, the best performance was exhibited by the Resnet50 classifier, which was best able to discriminate between the COVID-19 positive and the healthy coughs with an area under the ROC curve (AUC) of 0.98. An LSTM classifier was best able to discriminate between the COVID-19 positive and COVID-19 negative coughs, with an AUC of 0.94 after selecting the best 13 features from a sequential forward selection (SFS). Since this type of cough audio classification is cost-effective and easy to deploy, it is potentially a useful and viable means of non-contact COVID-19 screening. |
format | Online Article Text |
id | pubmed-8213969 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Elsevier Ltd. |
record_format | MEDLINE/PubMed |
spelling | pubmed-82139692021-06-21 COVID-19 cough classification using machine learning and global smartphone recordings Pahar, Madhurananda Klopper, Marisa Warren, Robin Niesler, Thomas Comput Biol Med Article We present a machine learning based COVID-19 cough classifier which can discriminate COVID-19 positive coughs from both COVID-19 negative and healthy coughs recorded on a smartphone. This type of screening is non-contact, easy to apply, and can reduce the workload in testing centres as well as limit transmission by recommending early self-isolation to those who have a cough suggestive of COVID-19. The datasets used in this study include subjects from all six continents and contain both forced and natural coughs, indicating that the approach is widely applicable. The publicly available Coswara dataset contains 92 COVID-19 positive and 1079 healthy subjects, while the second smaller dataset was collected mostly in South Africa and contains 18 COVID-19 positive and 26 COVID-19 negative subjects who have undergone a SARS-CoV laboratory test. Both datasets indicate that COVID-19 positive coughs are 15%–20% shorter than non-COVID coughs. Dataset skew was addressed by applying the synthetic minority oversampling technique (SMOTE). A leave-p-out cross-validation scheme was used to train and evaluate seven machine learning classifiers: logistic regression (LR), k-nearest neighbour (KNN), support vector machine (SVM), multilayer perceptron (MLP), convolutional neural network (CNN), long short-term memory (LSTM) and a residual-based neural network architecture (Resnet50). Our results show that although all classifiers were able to identify COVID-19 coughs, the best performance was exhibited by the Resnet50 classifier, which was best able to discriminate between the COVID-19 positive and the healthy coughs with an area under the ROC curve (AUC) of 0.98. An LSTM classifier was best able to discriminate between the COVID-19 positive and COVID-19 negative coughs, with an AUC of 0.94 after selecting the best 13 features from a sequential forward selection (SFS). Since this type of cough audio classification is cost-effective and easy to deploy, it is potentially a useful and viable means of non-contact COVID-19 screening. Elsevier Ltd. 2021-08 2021-06-17 /pmc/articles/PMC8213969/ /pubmed/34182331 http://dx.doi.org/10.1016/j.compbiomed.2021.104572 Text en © 2021 Elsevier Ltd. All rights reserved. Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID-19. The COVID-19 resource centre is hosted on Elsevier Connect, the company's public news and information website. Elsevier hereby grants permission to make all its COVID-19-related research that is available on the COVID-19 resource centre - including this research content - immediately available in PubMed Central and other publicly funded repositories, such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source. These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active. |
spellingShingle | Article Pahar, Madhurananda Klopper, Marisa Warren, Robin Niesler, Thomas COVID-19 cough classification using machine learning and global smartphone recordings |
title | COVID-19 cough classification using machine learning and global smartphone recordings |
title_full | COVID-19 cough classification using machine learning and global smartphone recordings |
title_fullStr | COVID-19 cough classification using machine learning and global smartphone recordings |
title_full_unstemmed | COVID-19 cough classification using machine learning and global smartphone recordings |
title_short | COVID-19 cough classification using machine learning and global smartphone recordings |
title_sort | covid-19 cough classification using machine learning and global smartphone recordings |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8213969/ https://www.ncbi.nlm.nih.gov/pubmed/34182331 http://dx.doi.org/10.1016/j.compbiomed.2021.104572 |
work_keys_str_mv | AT paharmadhurananda covid19coughclassificationusingmachinelearningandglobalsmartphonerecordings AT kloppermarisa covid19coughclassificationusingmachinelearningandglobalsmartphonerecordings AT warrenrobin covid19coughclassificationusingmachinelearningandglobalsmartphonerecordings AT nieslerthomas covid19coughclassificationusingmachinelearningandglobalsmartphonerecordings |