Validation Approaches for Cough Monitoring Tools: A Scoping Review.

Authors

Laylaa Ramos Arriaza, Laurie Slovarp, Brandon D Abell, Mindaugas Galvosas, Simon Grandjean Lapierre, Marie E Jetté

Published in

Lung. Volume 204. Issue 1. Jun 27, 2026. Epub Jun 27, 2026.

Abstract

To characterize validation approaches used in ambulatory cough monitoring systems and identify methodological variability that may limit clinical and research applications.
Scoping review.
A comprehensive search was performed in Embase (last updated May 8, 2026), and was limited to English-language, peer-reviewed human studies.
This review followed PRISMA-ScR guidelines. Studies were included if they reported validation of cough monitoring systems in human participants or human-derived datasets. Two reviewers independently screened and selected studies, with discrepancies resolved by a senior author. Data were extracted using a standardized form and synthesized descriptively.
Fifty studies met inclusion criteria. Most studies evaluated adult populations (72%) and were conducted in laboratory (29%) or home (25%) settings. Validation approaches were heterogeneous, with manual human annotation used as the reference standard in 66% of studies, neural network-based approaches in 12%, and alternative methods in 22%. Definitions of cough events and outcome metrics varied widely, including counts of cough events, epochs, and time-based measures. Technologies ranged from audio-based systems to wearable sensors and machine learning-enabled platforms. While many systems demonstrated high accuracy in controlled environments, performance in real-world settings was more variable, particularly in the presence of background noise and multiple speakers.
Validation of cough monitoring systems remains highly heterogeneous, with no standardized framework for reference measures or outcome metrics. Manual annotation is the most commonly used reference standard, although annotation methods and cough event definitions vary across studies. Standardization of validation protocols, development of shared datasets, and incorporation of real-world testing are needed to support clinical translation of cough monitoring technologies.

PMID:
42365132
Bibliographic data and abstract were imported from PubMed on 28 Jun 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.