Machine learning models for chronic kidney disease diagnosis and prediction

Mustafizur Rahman, M; Al-Amin, M; Hossain, J

Machine learning models for chronic kidney disease diagnosis and prediction

Mustafizur Rahman, M Al-Amin, M Hossain, J

Permalink

Publisher:: Elsevier
Publication Type:: Journal Article
Citation:: Biomedical Signal Processing and Control, 2024, 87, pp. 105368
Issue Date:: 2024-01-01

Closed Access

	Filename	Description	Size
	1-s2.0-S1746809423008017-main.pdf	Published version	8.45 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Mustafizur Rahman, M
dc.contributor.author	Al-Amin, M
dc.contributor.author	Hossain, J https://orcid.org/0000-0001-7602-3581
dc.date.accessioned	2024-02-02T00:18:48Z
dc.date.available	2024-02-02T00:18:48Z
dc.date.issued	2024-01-01
dc.identifier.citation	Biomedical Signal Processing and Control, 2024, 87, pp. 105368
dc.identifier.issn	1746-8094
dc.identifier.issn	1746-8108
dc.identifier.uri	http://hdl.handle.net/10453/175260
dc.description.abstract	Background and objective: Chronic kidney disease is a severe health problem that affects people all over the world, particularly in South Asia. Therefore, proper diagnosis and treatment are required as early as possible. The main goal of this study is to detect the presence or absence of CKD in the human body utilizing a variety of features grasped from a few medical tests. Methods: This paper has focused on eight ensemble learning methods for diagnosing CKD on the UCI machine learning datasets. The datasets have been fixed by imputing the missing values using the MICE imputation method and handling the imbalance properties using the borderline SVMSMOTE method to improve the performance of classifiers. Moreover, recursive feature elimination and the boruta method have been used to find the most significant features and reduce the compilation time, while the hyperparameter tuning technique was used to raise the performance of classifiers and get optimal solutions. Results: Taking the most significant feature into consideration, RFE outperformed boruta and selected only 50% of the total features. Moreover, various performance matrices are used to find the best competent classifiers for detecting CKD. LightGBM outperformed state-of-the-art and other ensemble methods with the lowest compilation time and highest accuracy. Based on experimental findings, the proposed method achieved the highest average of 99.75% accuracy, 99.40% precision, 99.41% recall, 99.61% F-measure and 99.57% AUC-ROC. Moreover, our proposed method rises the average detection rate by 5.64%, 1%, 2.04%, 8.63%,1.99%, 2.84%, 2.42% and 4.76%, respectively, in comparison with different approaches performing on the same dataset. Conclusion: Experiments show that our suggested method can identify CKD more precisely than the most recent methods.
dc.language	en
dc.publisher	Elsevier
dc.relation.ispartof	Biomedical Signal Processing and Control
dc.relation.isbasedon	10.1016/j.bspc.2023.105368
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0903 Biomedical Engineering, 0906 Electrical and Electronic Engineering, 1004 Medical Biotechnology
dc.subject.classification	Biomedical Engineering
dc.subject.classification	3006 Food sciences
dc.subject.classification	4003 Biomedical engineering
dc.title	Machine learning models for chronic kidney disease diagnosis and prediction
dc.type	Journal Article
utslib.citation.volume	87
utslib.for	0903 Biomedical Engineering
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	1004 Medical Biotechnology
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	closed_access	*
dc.date.updated	2024-02-02T00:18:43Z
pubs.publication-status	Published
pubs.volume	87

Abstract:

Background and objective: Chronic kidney disease is a severe health problem that affects people all over the world, particularly in South Asia. Therefore, proper diagnosis and treatment are required as early as possible. The main goal of this study is to detect the presence or absence of CKD in the human body utilizing a variety of features grasped from a few medical tests. Methods: This paper has focused on eight ensemble learning methods for diagnosing CKD on the UCI machine learning datasets. The datasets have been fixed by imputing the missing values using the MICE imputation method and handling the imbalance properties using the borderline SVMSMOTE method to improve the performance of classifiers. Moreover, recursive feature elimination and the boruta method have been used to find the most significant features and reduce the compilation time, while the hyperparameter tuning technique was used to raise the performance of classifiers and get optimal solutions. Results: Taking the most significant feature into consideration, RFE outperformed boruta and selected only 50% of the total features. Moreover, various performance matrices are used to find the best competent classifiers for detecting CKD. LightGBM outperformed state-of-the-art and other ensemble methods with the lowest compilation time and highest accuracy. Based on experimental findings, the proposed method achieved the highest average of 99.75% accuracy, 99.40% precision, 99.41% recall, 99.61% F-measure and 99.57% AUC-ROC. Moreover, our proposed method rises the average detection rate by 5.64%, 1%, 2.04%, 8.63%,1.99%, 2.84%, 2.42% and 4.76%, respectively, in comparison with different approaches performing on the same dataset. Conclusion: Experiments show that our suggested method can identify CKD more precisely than the most recent methods.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/175260