Cover Image

Identification Of Asthma Severity Levels Through Wheeze Sound Characterization And Classification Using Integrated Power Features

This study aimed to investigate and classify wheeze sound characteristics according to asthma severity levels (mild, moderate and severe) using integrated power (IP) features. Method: Validated and segmented wheeze sounds were obtained from the lower lung base (LLB) and trachea recordings of 55 asth...

Full description

Saved in:
Bibliographic Details
Main Authors: Nabi, Fizza Ghulam, Sundaraj, Kenneth, Chee, Kiang Lam
Format: Article
Language:English
Published: Elsevier Ltd. 2019
Online Access:http://eprints.utem.edu.my/id/eprint/24363/2/2019%20FIZZA%20BSPC.PDF
http://eprints.utem.edu.my/id/eprint/24363/
https://www.sciencedirect.com/science/article/pii/S1746809419301156
https://doi.org/10.1016/j.bspc.2019.04.018
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utem.eprints.24363
record_format eprints
spelling my.utem.eprints.243632020-12-22T12:33:44Z http://eprints.utem.edu.my/id/eprint/24363/ Identification Of Asthma Severity Levels Through Wheeze Sound Characterization And Classification Using Integrated Power Features Nabi, Fizza Ghulam Sundaraj, Kenneth Chee, Kiang Lam This study aimed to investigate and classify wheeze sound characteristics according to asthma severity levels (mild, moderate and severe) using integrated power (IP) features. Method: Validated and segmented wheeze sounds were obtained from the lower lung base (LLB) and trachea recordings of 55 asthmatic patients with different severity levels during tidal breathing manoeuvres. From the segments, nine datasets were obtained based on the auscultation location, breath phases and their combination. In this study, IP features were extracted for assessing asthma severity. Subsequently, univariate and multivariate (MANOVA) statistical analyses were separately implemented to analyse behaviour of wheeze sounds according to severity levels. Furthermore, the ensemble (ENS), knearest- neighbour (KNN) and support vector machine (SVM) classifiers were applied to classify the asthma severity levels. Results and conclusion: The univariate results of this study indicated that the majority of features significantly discriminated (p < 0.05) the severity levels in all the datasets. The MANOVA results yielded significantly (p < 0.05) large effect size in all datasets (including LLB-related) and almost all post hoc results were significant(p < 0.05). A comparison ofthe performance of classifiers revealed that eight ofthe nine datasets showed improved performance with the ENS classifier. The Trachea inspiratory (T-Inspir) dataset produced the highest performance. The overall best positive predictive rate (PPR) for the mild, moderate and severe severity levels were 100% (KNN), 92% (SVM) and 94% (ENS) respectively. Analysis related to auscultation locations revealed that tracheal wheeze sounds are more specific and sensitive predictors of asthma severity. Additionally, phase related investigations indicated that expiratory and inspiratory wheeze sounds are equally informative for the classification of asthma severity Elsevier Ltd. 2019-07 Article PeerReviewed text en http://eprints.utem.edu.my/id/eprint/24363/2/2019%20FIZZA%20BSPC.PDF Nabi, Fizza Ghulam and Sundaraj, Kenneth and Chee, Kiang Lam (2019) Identification Of Asthma Severity Levels Through Wheeze Sound Characterization And Classification Using Integrated Power Features. Biomedical Signal Processing and Control, 52. 302 - 311. ISSN 1746-8094 https://www.sciencedirect.com/science/article/pii/S1746809419301156 https://doi.org/10.1016/j.bspc.2019.04.018
institution Universiti Teknikal Malaysia Melaka
building UTEM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknikal Malaysia Melaka
content_source UTEM Institutional Repository
url_provider http://eprints.utem.edu.my/
language English
description This study aimed to investigate and classify wheeze sound characteristics according to asthma severity levels (mild, moderate and severe) using integrated power (IP) features. Method: Validated and segmented wheeze sounds were obtained from the lower lung base (LLB) and trachea recordings of 55 asthmatic patients with different severity levels during tidal breathing manoeuvres. From the segments, nine datasets were obtained based on the auscultation location, breath phases and their combination. In this study, IP features were extracted for assessing asthma severity. Subsequently, univariate and multivariate (MANOVA) statistical analyses were separately implemented to analyse behaviour of wheeze sounds according to severity levels. Furthermore, the ensemble (ENS), knearest- neighbour (KNN) and support vector machine (SVM) classifiers were applied to classify the asthma severity levels. Results and conclusion: The univariate results of this study indicated that the majority of features significantly discriminated (p < 0.05) the severity levels in all the datasets. The MANOVA results yielded significantly (p < 0.05) large effect size in all datasets (including LLB-related) and almost all post hoc results were significant(p < 0.05). A comparison ofthe performance of classifiers revealed that eight ofthe nine datasets showed improved performance with the ENS classifier. The Trachea inspiratory (T-Inspir) dataset produced the highest performance. The overall best positive predictive rate (PPR) for the mild, moderate and severe severity levels were 100% (KNN), 92% (SVM) and 94% (ENS) respectively. Analysis related to auscultation locations revealed that tracheal wheeze sounds are more specific and sensitive predictors of asthma severity. Additionally, phase related investigations indicated that expiratory and inspiratory wheeze sounds are equally informative for the classification of asthma severity
format Article
author Nabi, Fizza Ghulam
Sundaraj, Kenneth
Chee, Kiang Lam
spellingShingle Nabi, Fizza Ghulam
Sundaraj, Kenneth
Chee, Kiang Lam
Identification Of Asthma Severity Levels Through Wheeze Sound Characterization And Classification Using Integrated Power Features
author_facet Nabi, Fizza Ghulam
Sundaraj, Kenneth
Chee, Kiang Lam
author_sort Nabi, Fizza Ghulam
title Identification Of Asthma Severity Levels Through Wheeze Sound Characterization And Classification Using Integrated Power Features
title_short Identification Of Asthma Severity Levels Through Wheeze Sound Characterization And Classification Using Integrated Power Features
title_full Identification Of Asthma Severity Levels Through Wheeze Sound Characterization And Classification Using Integrated Power Features
title_fullStr Identification Of Asthma Severity Levels Through Wheeze Sound Characterization And Classification Using Integrated Power Features
title_full_unstemmed Identification Of Asthma Severity Levels Through Wheeze Sound Characterization And Classification Using Integrated Power Features
title_sort identification of asthma severity levels through wheeze sound characterization and classification using integrated power features
publisher Elsevier Ltd.
publishDate 2019
url http://eprints.utem.edu.my/id/eprint/24363/2/2019%20FIZZA%20BSPC.PDF
http://eprints.utem.edu.my/id/eprint/24363/
https://www.sciencedirect.com/science/article/pii/S1746809419301156
https://doi.org/10.1016/j.bspc.2019.04.018
_version_ 1687397266646630400
score 13.211869

Similar Items