Please use this identifier to cite or link to this item:
Title: Automatic classification of adventitious respiratory sounds: a (un)solved problem?
Author: Rocha, Bruno Machado
Pessoa, Diogo
Marques, Alda
Carvalho, Paulo
Paiva, Rui Pedro
Keywords: Adventitious respiratory sounds
Experimental design
Machine learning
Issue Date: 1-Jan-2021
Publisher: MDPI
Abstract: (1) Background: Patients with respiratory conditions typically exhibit adventitious respiratory sounds (ARS), such as wheezes and crackles. ARS events have variable duration. In this work we studied the influence of event duration on automatic ARS classification, namely, how the creation of the Other class (negative class) affected the classifiers’ performance. (2) Methods: We conducted a set of experiments where we varied the durations of the other events on three tasks: crackle vs. wheeze vs. other (3 Class); crackle vs. other (2 Class Crackles); and wheeze vs. other (2 Class Wheezes). Four classifiers (linear discriminant analysis, support vector machines, boosted trees, and convolutional neural networks) were evaluated on those tasks using an open access respiratory sound database. (3) Results: While on the 3 Class task with fixed durations, the best classifier achieved an accuracy of 96.9%, the same classifier reached an accuracy of 81.8% on the more realistic 3 Class task with variable durations. (4) Conclusion: These results demonstrate the importance of experimental design on the assessment of the performance of automatic ARS classification algorithms. Furthermore, they also indicate, unlike what is stated in the literature, that the automatic classification of ARS is not a solved problem, as the algorithms’ performance decreases substantially under complex evaluation scenarios.
Peer review: yes
DOI: 10.3390/s21010057
ISSN: 1424-8220
Appears in Collections:IBIMED - Artigos
ESSUA - Artigos
Lab3R - Artigos

Files in This Item:
File Description SizeFormat 
2021_Rocha_Automatic classification of ARS.pdf611.86 kBAdobe PDFView/Open

Formato BibTex MendeleyEndnote Degois 

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.