An Early Detection of Asthma Using BOMLA Detector

Asthma is a chronic and airway-induced disease, causing the incidence of bronchus inflammation, breathlessness, wheezing, is drastically becoming life-threatening. Even in the worst cases, it may destroy the quality to lead. Therefore, early detection of asthma is urgently needed, and machine learni...

Full description

Saved in:
Bibliographic Details
Main Authors: Md. Abdul Awal, Md. Shahadat Hossain, Kumar Debjit, Nafiz Ahmed, Rajan Dev Nath, G. M. Monsur Habib, Md. Salauddin Khan, Md. Akhtarul Islam, M. A. Parvez Mahmud
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9402730/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849223119719366656
author Md. Abdul Awal
Md. Shahadat Hossain
Kumar Debjit
Nafiz Ahmed
Rajan Dev Nath
G. M. Monsur Habib
Md. Salauddin Khan
Md. Akhtarul Islam
M. A. Parvez Mahmud
author_facet Md. Abdul Awal
Md. Shahadat Hossain
Kumar Debjit
Nafiz Ahmed
Rajan Dev Nath
G. M. Monsur Habib
Md. Salauddin Khan
Md. Akhtarul Islam
M. A. Parvez Mahmud
author_sort Md. Abdul Awal
collection DOAJ
description Asthma is a chronic and airway-induced disease, causing the incidence of bronchus inflammation, breathlessness, wheezing, is drastically becoming life-threatening. Even in the worst cases, it may destroy the quality to lead. Therefore, early detection of asthma is urgently needed, and machine learning can help identify asthma accurately. In this paper, a novel machine learning framework, namely BOMLA (<bold>B</bold>ayesian <bold>O</bold>ptimisation-based <bold>M</bold>achine <bold>L</bold>earning framework for <bold>A</bold>sthma) detector has been proposed to detect asthma. Ten classifiers have been utilized in the BOMLA detector, where Support Vector Classifier (SVC), Random Forest (RF), Gradient Boosting Classifier (GBC), eXtreme Gradient Boosting (XGB), and Artificial Neural Network (ANN) are state-of-the-art classifiers. In contrast, Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QLDA), Naive Bayes (NB), Decision Tree (DT), and K-Nearest Neighbor (KNN) are conventional popular classifiers. ADASYN algorithm has also been employed in the BOMLA detector to eradicate the issues created due to the imbalanced dataset. It has even been attempted to delineate how the ADASYN algorithm affects the classification performance. The highest accuracy (ACC) and Matthews&#x2019;s correlation coefficient (MCC) for an Asthma dataset provide 94.35&#x0025; and 88.97&#x0025;, respectively, using BOMLA detector when SVC is adapted, and it has been increased to 96.52&#x0025; and 93.04&#x0025;, respectively, when ensemble technique is adapted. The one-way analysis of variance (ANOVA) has also been performed in the 10-fold cross-validation to measure the statistical significance. A decision support system has been built as a potential application of the proposed system to visualize the probable outcome of the patient. Finally, it is expected that the BOMLA detector will help patients in their early diagnosis of asthma.
format Article
id doaj-art-3e92e6d0a22845dcb6f8b6a2162018a5
institution Kabale University
issn 2169-3536
language English
publishDate 2021-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-3e92e6d0a22845dcb6f8b6a2162018a52025-08-25T23:00:46ZengIEEEIEEE Access2169-35362021-01-019584035842010.1109/ACCESS.2021.30730869402730An Early Detection of Asthma Using BOMLA DetectorMd. Abdul Awal0https://orcid.org/0000-0003-3028-4932Md. Shahadat Hossain1https://orcid.org/0000-0002-1368-7230Kumar Debjit2https://orcid.org/0000-0002-1779-0788Nafiz Ahmed3https://orcid.org/0000-0002-9445-2846Rajan Dev Nath4G. M. Monsur Habib5Md. Salauddin Khan6https://orcid.org/0000-0002-5001-7877Md. Akhtarul Islam7https://orcid.org/0000-0003-2396-2168M. A. Parvez Mahmud8https://orcid.org/0000-0002-1905-6800Electronics and Communication Engineering Discipline, Khulna University, Khulna, BangladeshDepartment of Quantitative Sciences, International University of Business Agriculture and Technology, Dhaka, BangladeshFaculty of Health, Engineering, and Sciences, University of Southern Queensland, Toowoomba, QLD, AustraliaFaculty of Law and Business, Peter Faber Business School, Australian Catholic University, North Sydney, NSW, AustraliaFaculty of Business, Education, Law and Arts, School of Commerce, University of Southern Queensland, Toowoomba, QLD, AustraliaGlobal Health Academy, The University of Edinburgh, Edinburgh, U.K.Statistics Discipline, Khulna University, Khulna, BangladeshStatistics Discipline, Khulna University, Khulna, BangladeshSchool of Engineering, Deakin University, Geelong, VIC, AustraliaAsthma is a chronic and airway-induced disease, causing the incidence of bronchus inflammation, breathlessness, wheezing, is drastically becoming life-threatening. Even in the worst cases, it may destroy the quality to lead. Therefore, early detection of asthma is urgently needed, and machine learning can help identify asthma accurately. In this paper, a novel machine learning framework, namely BOMLA (<bold>B</bold>ayesian <bold>O</bold>ptimisation-based <bold>M</bold>achine <bold>L</bold>earning framework for <bold>A</bold>sthma) detector has been proposed to detect asthma. Ten classifiers have been utilized in the BOMLA detector, where Support Vector Classifier (SVC), Random Forest (RF), Gradient Boosting Classifier (GBC), eXtreme Gradient Boosting (XGB), and Artificial Neural Network (ANN) are state-of-the-art classifiers. In contrast, Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QLDA), Naive Bayes (NB), Decision Tree (DT), and K-Nearest Neighbor (KNN) are conventional popular classifiers. ADASYN algorithm has also been employed in the BOMLA detector to eradicate the issues created due to the imbalanced dataset. It has even been attempted to delineate how the ADASYN algorithm affects the classification performance. The highest accuracy (ACC) and Matthews&#x2019;s correlation coefficient (MCC) for an Asthma dataset provide 94.35&#x0025; and 88.97&#x0025;, respectively, using BOMLA detector when SVC is adapted, and it has been increased to 96.52&#x0025; and 93.04&#x0025;, respectively, when ensemble technique is adapted. The one-way analysis of variance (ANOVA) has also been performed in the 10-fold cross-validation to measure the statistical significance. A decision support system has been built as a potential application of the proposed system to visualize the probable outcome of the patient. Finally, it is expected that the BOMLA detector will help patients in their early diagnosis of asthma.https://ieeexplore.ieee.org/document/9402730/Classificationclinical and non-clinical dataasthmaADASYNANOVA
spellingShingle Md. Abdul Awal
Md. Shahadat Hossain
Kumar Debjit
Nafiz Ahmed
Rajan Dev Nath
G. M. Monsur Habib
Md. Salauddin Khan
Md. Akhtarul Islam
M. A. Parvez Mahmud
An Early Detection of Asthma Using BOMLA Detector
IEEE Access
Classification
clinical and non-clinical data
asthma
ADASYN
ANOVA
title An Early Detection of Asthma Using BOMLA Detector
title_full An Early Detection of Asthma Using BOMLA Detector
title_fullStr An Early Detection of Asthma Using BOMLA Detector
title_full_unstemmed An Early Detection of Asthma Using BOMLA Detector
title_short An Early Detection of Asthma Using BOMLA Detector
title_sort early detection of asthma using bomla detector
topic Classification
clinical and non-clinical data
asthma
ADASYN
ANOVA
url https://ieeexplore.ieee.org/document/9402730/
work_keys_str_mv AT mdabdulawal anearlydetectionofasthmausingbomladetector
AT mdshahadathossain anearlydetectionofasthmausingbomladetector
AT kumardebjit anearlydetectionofasthmausingbomladetector
AT nafizahmed anearlydetectionofasthmausingbomladetector
AT rajandevnath anearlydetectionofasthmausingbomladetector
AT gmmonsurhabib anearlydetectionofasthmausingbomladetector
AT mdsalauddinkhan anearlydetectionofasthmausingbomladetector
AT mdakhtarulislam anearlydetectionofasthmausingbomladetector
AT maparvezmahmud anearlydetectionofasthmausingbomladetector
AT mdabdulawal earlydetectionofasthmausingbomladetector
AT mdshahadathossain earlydetectionofasthmausingbomladetector
AT kumardebjit earlydetectionofasthmausingbomladetector
AT nafizahmed earlydetectionofasthmausingbomladetector
AT rajandevnath earlydetectionofasthmausingbomladetector
AT gmmonsurhabib earlydetectionofasthmausingbomladetector
AT mdsalauddinkhan earlydetectionofasthmausingbomladetector
AT mdakhtarulislam earlydetectionofasthmausingbomladetector
AT maparvezmahmud earlydetectionofasthmausingbomladetector