Validation of an automated cough detection algorithm for tracking recovery of pulmonary tuberculosis patients.

<h4>Background</h4>A laboratory-free test for assessing recovery from pulmonary tuberculosis (TB) would be extremely beneficial in regions of the world where laboratory facilities are lacking. Our hypothesis is that analysis of cough sound recordings may provide such a test. In the curre...

Full description

Saved in:
Bibliographic Details
Main Authors: Sandra Larson, Germán Comina, Robert H Gilman, Brian H Tracey, Marjory Bravard, José W López
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2012-01-01
Series:PLoS ONE
Online Access:https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0046229&type=printable
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850137645026377728
author Sandra Larson
Germán Comina
Robert H Gilman
Brian H Tracey
Marjory Bravard
José W López
author_facet Sandra Larson
Germán Comina
Robert H Gilman
Brian H Tracey
Marjory Bravard
José W López
author_sort Sandra Larson
collection DOAJ
description <h4>Background</h4>A laboratory-free test for assessing recovery from pulmonary tuberculosis (TB) would be extremely beneficial in regions of the world where laboratory facilities are lacking. Our hypothesis is that analysis of cough sound recordings may provide such a test. In the current paper, we present validation of a cough analysis tool.<h4>Methodology/principal findings</h4>Cough data was collected from a cohort of TB patients in Lima, Peru and 25.5 hours of recordings were manually annotated by clinical staff. Analysis software was developed and validated by comparison to manual scoring. Because many patients cough in bursts, coughing was characterized in terms of cough epochs. Our software correctly detects 75.5% of cough episodes with a specificity of 99.6% (comparable to past results using the same definition) and a median false positive rate of 4 false positives/hour, due to the noisy, real-world nature of our dataset. We then manually review detected coughs to eliminate false positives, in effect using the algorithm as a pre-screening tool that reduces reviewing time to roughly 5% of the recording length. This cough analysis approach provides a foundation to support larger-scale studies of coughing rates over time for TB patients undergoing treatment.
format Article
id doaj-art-ce18fee40f8b414592bad01608ab05c2
institution OA Journals
issn 1932-6203
language English
publishDate 2012-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-ce18fee40f8b414592bad01608ab05c22025-08-20T02:30:46ZengPublic Library of Science (PLoS)PLoS ONE1932-62032012-01-01710e4622910.1371/journal.pone.0046229Validation of an automated cough detection algorithm for tracking recovery of pulmonary tuberculosis patients.Sandra LarsonGermán CominaRobert H GilmanBrian H TraceyMarjory BravardJosé W López<h4>Background</h4>A laboratory-free test for assessing recovery from pulmonary tuberculosis (TB) would be extremely beneficial in regions of the world where laboratory facilities are lacking. Our hypothesis is that analysis of cough sound recordings may provide such a test. In the current paper, we present validation of a cough analysis tool.<h4>Methodology/principal findings</h4>Cough data was collected from a cohort of TB patients in Lima, Peru and 25.5 hours of recordings were manually annotated by clinical staff. Analysis software was developed and validated by comparison to manual scoring. Because many patients cough in bursts, coughing was characterized in terms of cough epochs. Our software correctly detects 75.5% of cough episodes with a specificity of 99.6% (comparable to past results using the same definition) and a median false positive rate of 4 false positives/hour, due to the noisy, real-world nature of our dataset. We then manually review detected coughs to eliminate false positives, in effect using the algorithm as a pre-screening tool that reduces reviewing time to roughly 5% of the recording length. This cough analysis approach provides a foundation to support larger-scale studies of coughing rates over time for TB patients undergoing treatment.https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0046229&type=printable
spellingShingle Sandra Larson
Germán Comina
Robert H Gilman
Brian H Tracey
Marjory Bravard
José W López
Validation of an automated cough detection algorithm for tracking recovery of pulmonary tuberculosis patients.
PLoS ONE
title Validation of an automated cough detection algorithm for tracking recovery of pulmonary tuberculosis patients.
title_full Validation of an automated cough detection algorithm for tracking recovery of pulmonary tuberculosis patients.
title_fullStr Validation of an automated cough detection algorithm for tracking recovery of pulmonary tuberculosis patients.
title_full_unstemmed Validation of an automated cough detection algorithm for tracking recovery of pulmonary tuberculosis patients.
title_short Validation of an automated cough detection algorithm for tracking recovery of pulmonary tuberculosis patients.
title_sort validation of an automated cough detection algorithm for tracking recovery of pulmonary tuberculosis patients
url https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0046229&type=printable
work_keys_str_mv AT sandralarson validationofanautomatedcoughdetectionalgorithmfortrackingrecoveryofpulmonarytuberculosispatients
AT germancomina validationofanautomatedcoughdetectionalgorithmfortrackingrecoveryofpulmonarytuberculosispatients
AT roberthgilman validationofanautomatedcoughdetectionalgorithmfortrackingrecoveryofpulmonarytuberculosispatients
AT brianhtracey validationofanautomatedcoughdetectionalgorithmfortrackingrecoveryofpulmonarytuberculosispatients
AT marjorybravard validationofanautomatedcoughdetectionalgorithmfortrackingrecoveryofpulmonarytuberculosispatients
AT josewlopez validationofanautomatedcoughdetectionalgorithmfortrackingrecoveryofpulmonarytuberculosispatients