Can Passive Cough Monitoring Predict COPD Exacerbations?

Purpose Validation of an alert mechanism for COPD exacerbations based on coughing detected by a stationary unobtrusive nighttime monitor.Methods This prospective double-blind longitudinal study of cough monitoring included 40 chronic obstructive pulmonary disease (COPD) patients. Participants underw...

Full description

Saved in:
Bibliographic Details
Main Authors: A. H. Morice, A. C. den Brinker, M. Crooks, S. Thackray-Nocera, O. Ouweltjes, R. Rietman
Format: Article
Language:English
Published: Taylor & Francis Group 2025-04-01
Series:COPD
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/15412555.2025.2487909
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849737978568507392
author A. H. Morice
A. C. den Brinker
M. Crooks
S. Thackray-Nocera
O. Ouweltjes
R. Rietman
author_facet A. H. Morice
A. C. den Brinker
M. Crooks
S. Thackray-Nocera
O. Ouweltjes
R. Rietman
author_sort A. H. Morice
collection DOAJ
description Purpose Validation of an alert mechanism for COPD exacerbations based on coughing detected by a stationary unobtrusive nighttime monitor.Methods This prospective double-blind longitudinal study of cough monitoring included 40 chronic obstructive pulmonary disease (COPD) patients. Participants underwent cough monitoring and completed a daily questionnaire for 12 weeks. If no exacerbation occurred within that period patients were asked to continue being monitored for a further 12 weeks. The automated system identified deteriorating trends in cough based on a personalized cough classifier and the alerts were compared with patient reported exacerbation onsets.Results Thirty-eight patients [median age 72 (range 57–84)], median FEV-1% predicted 43% (range 20–106%) completed the study and had 41 exacerbations over a total of 3981 days. For 32 patients, the cough monitor data allowed classifier personalization, trend analysis, and alert generation. Based on the trend data, it is estimated that ∼30% of exacerbations are not associated with an increase in cough. The alert mechanism flagged 59% of the exacerbations. For the cases with alerts preceding the onset, the associated lead time was 4 days or more.Conclusion Though based on a single variable only, the cough-based alert system captured more than half of the exacerbations in a passive, free-living scenario. No adherence issues were reported, and patients confirmed the unobtrusive and hassle-free nature of the approach.
format Article
id doaj-art-d30da4032a724b1e9a43ee663742a8b3
institution DOAJ
issn 1541-2555
1541-2563
language English
publishDate 2025-04-01
publisher Taylor & Francis Group
record_format Article
series COPD
spelling doaj-art-d30da4032a724b1e9a43ee663742a8b32025-08-20T03:06:44ZengTaylor & Francis GroupCOPD1541-25551541-25632025-04-0122110.1080/15412555.2025.2487909Can Passive Cough Monitoring Predict COPD Exacerbations?A. H. Morice0A. C. den Brinker1M. Crooks2S. Thackray-Nocera3O. Ouweltjes4R. Rietman5Department of Academic Respiratory Medicine, Centre for Cardiovascular and Metabolic Research, Hull York Medical School, Castle Hill Hospital, Hull, UKIndependent Researcher, Formerly with Philips Research, High Tech Campus, Eindhoven, NetherlandsDepartment of Academic Respiratory Medicine, Centre for Cardiovascular and Metabolic Research, Hull York Medical School, Castle Hill Hospital, Hull, UKDepartment of Academic Respiratory Medicine, Centre for Cardiovascular and Metabolic Research, Hull York Medical School, Castle Hill Hospital, Hull, UKDigital Standardization & Licensing Research, Philips, High Tech Campus, Eindhoven, NetherlandsInnovation Engineering, Data Science and AI, Philips, High Tech Campus, Eindhoven, NetherlandsPurpose Validation of an alert mechanism for COPD exacerbations based on coughing detected by a stationary unobtrusive nighttime monitor.Methods This prospective double-blind longitudinal study of cough monitoring included 40 chronic obstructive pulmonary disease (COPD) patients. Participants underwent cough monitoring and completed a daily questionnaire for 12 weeks. If no exacerbation occurred within that period patients were asked to continue being monitored for a further 12 weeks. The automated system identified deteriorating trends in cough based on a personalized cough classifier and the alerts were compared with patient reported exacerbation onsets.Results Thirty-eight patients [median age 72 (range 57–84)], median FEV-1% predicted 43% (range 20–106%) completed the study and had 41 exacerbations over a total of 3981 days. For 32 patients, the cough monitor data allowed classifier personalization, trend analysis, and alert generation. Based on the trend data, it is estimated that ∼30% of exacerbations are not associated with an increase in cough. The alert mechanism flagged 59% of the exacerbations. For the cases with alerts preceding the onset, the associated lead time was 4 days or more.Conclusion Though based on a single variable only, the cough-based alert system captured more than half of the exacerbations in a passive, free-living scenario. No adherence issues were reported, and patients confirmed the unobtrusive and hassle-free nature of the approach.https://www.tandfonline.com/doi/10.1080/15412555.2025.2487909COPDexacerbationalert systemautomated cough counttelehealth
spellingShingle A. H. Morice
A. C. den Brinker
M. Crooks
S. Thackray-Nocera
O. Ouweltjes
R. Rietman
Can Passive Cough Monitoring Predict COPD Exacerbations?
COPD
COPD
exacerbation
alert system
automated cough count
telehealth
title Can Passive Cough Monitoring Predict COPD Exacerbations?
title_full Can Passive Cough Monitoring Predict COPD Exacerbations?
title_fullStr Can Passive Cough Monitoring Predict COPD Exacerbations?
title_full_unstemmed Can Passive Cough Monitoring Predict COPD Exacerbations?
title_short Can Passive Cough Monitoring Predict COPD Exacerbations?
title_sort can passive cough monitoring predict copd exacerbations
topic COPD
exacerbation
alert system
automated cough count
telehealth
url https://www.tandfonline.com/doi/10.1080/15412555.2025.2487909
work_keys_str_mv AT ahmorice canpassivecoughmonitoringpredictcopdexacerbations
AT acdenbrinker canpassivecoughmonitoringpredictcopdexacerbations
AT mcrooks canpassivecoughmonitoringpredictcopdexacerbations
AT sthackraynocera canpassivecoughmonitoringpredictcopdexacerbations
AT oouweltjes canpassivecoughmonitoringpredictcopdexacerbations
AT rrietman canpassivecoughmonitoringpredictcopdexacerbations