The effect of imbalance data mitigation techniques on cardiovascular disease prediction

The prevalence of class imbalance is a common challenge in medical datasets, which can adversely affect the performance of machine learning models. This paper explores how several data imbalance mitigation techniques affect the performance of cardiovascular disease prediction. This study applied va...

Full description

Saved in:
Bibliographic Details
Main Authors: Raphael Ozighor Enihe, Rajesh Prasad, Francisca Nonyelum Ogwueleka, Fatimah Binta Abdullahi
Format: Article
Language:English
Published: Nigerian Society of Physical Sciences 2025-05-01
Series:Journal of Nigerian Society of Physical Sciences
Subjects:
Online Access:https://journal.nsps.org.ng/index.php/jnsps/article/view/2385
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850199762691686400
author Raphael Ozighor Enihe
Rajesh Prasad
Francisca Nonyelum Ogwueleka
Fatimah Binta Abdullahi
author_facet Raphael Ozighor Enihe
Rajesh Prasad
Francisca Nonyelum Ogwueleka
Fatimah Binta Abdullahi
author_sort Raphael Ozighor Enihe
collection DOAJ
description The prevalence of class imbalance is a common challenge in medical datasets, which can adversely affect the performance of machine learning models. This paper explores how several data imbalance mitigation techniques affect the performance of cardiovascular disease prediction. This study applied various data balancing techniques on a real-life cardiovascular disease (CVD) dataset of 1000 patient records with 14 features obtained from the University of Abuja Teaching Hospital Nigeria to address this problem. The data balancing techniques used include random under-sampling, Synthetic Minority Over-sampling Technique (SMOTE), Synthetic Minority Oversampling-Edited Nearest Neighbour (SMOTE-ENN), and the combination of SMOTE and Tomek Links undersampling (SMOTE-TOMEK). After applying these techniques, their performance was evaluated on seven machine learning models, including Random Forest, XGBoost, LightGBM, Gradient Boosting, K-Nearest Neighbours, Decision Tree, and Support Vector Machine. The evaluation metrics used are precision, recall, F1-score, accuracy, and receiver operating characteristic-area under the curve (ROC-AUC). Learning curve plots were also used to showcase the impact of the different data balancing techniques on the challenges of overfitting and underfitting. The results showed that the application of data balancing techniques significantly enhances the performance of machine learning models in heart disease prediction and effectively addresses the challenges of overfitting and underfitting with SMOTE-TOMEK, yielding the best-balanced fit as well as the highest precision, recall, F1-score, accuracy of 92%, and ROC-AUC of 96% on the Lightweight Gradient Boosting Machine (LightGBM) model. These results underscore the critical role of data balancing in predictive modelling for heart disease and highlight the effectiveness of specific techniques and models in achieving accurate, more reliable, and generalised predictions.
format Article
id doaj-art-a721a9bd021e48d4b63702ef1e370cbf
institution OA Journals
issn 2714-2817
2714-4704
language English
publishDate 2025-05-01
publisher Nigerian Society of Physical Sciences
record_format Article
series Journal of Nigerian Society of Physical Sciences
spelling doaj-art-a721a9bd021e48d4b63702ef1e370cbf2025-08-20T02:12:33ZengNigerian Society of Physical SciencesJournal of Nigerian Society of Physical Sciences2714-28172714-47042025-05-017210.46481/jnsps.2025.2385The effect of imbalance data mitigation techniques on cardiovascular disease predictionRaphael Ozighor Enihe0https://orcid.org/0000-0001-8155-4205Rajesh Prasad1Francisca Nonyelum Ogwueleka2Fatimah Binta Abdullahi3Department of Computer Science, Baze University, Abuja, NigeriaDepartment of Computer Science & Engineering, Ajay Kumar Garg Engineering College, Ghaziabad, India; Department of Computer Science, University of Abuja, Abuja, NigeriaDepartment of Computer Science, University of AbujaDepartment of Computer Science, University of Abuja, Abuja, Nigeria The prevalence of class imbalance is a common challenge in medical datasets, which can adversely affect the performance of machine learning models. This paper explores how several data imbalance mitigation techniques affect the performance of cardiovascular disease prediction. This study applied various data balancing techniques on a real-life cardiovascular disease (CVD) dataset of 1000 patient records with 14 features obtained from the University of Abuja Teaching Hospital Nigeria to address this problem. The data balancing techniques used include random under-sampling, Synthetic Minority Over-sampling Technique (SMOTE), Synthetic Minority Oversampling-Edited Nearest Neighbour (SMOTE-ENN), and the combination of SMOTE and Tomek Links undersampling (SMOTE-TOMEK). After applying these techniques, their performance was evaluated on seven machine learning models, including Random Forest, XGBoost, LightGBM, Gradient Boosting, K-Nearest Neighbours, Decision Tree, and Support Vector Machine. The evaluation metrics used are precision, recall, F1-score, accuracy, and receiver operating characteristic-area under the curve (ROC-AUC). Learning curve plots were also used to showcase the impact of the different data balancing techniques on the challenges of overfitting and underfitting. The results showed that the application of data balancing techniques significantly enhances the performance of machine learning models in heart disease prediction and effectively addresses the challenges of overfitting and underfitting with SMOTE-TOMEK, yielding the best-balanced fit as well as the highest precision, recall, F1-score, accuracy of 92%, and ROC-AUC of 96% on the Lightweight Gradient Boosting Machine (LightGBM) model. These results underscore the critical role of data balancing in predictive modelling for heart disease and highlight the effectiveness of specific techniques and models in achieving accurate, more reliable, and generalised predictions. https://journal.nsps.org.ng/index.php/jnsps/article/view/2385Imbalance datasetCardiovascular disease predictionSMOTE-TOMEKMarchine learningOverfitting and Underfitting
spellingShingle Raphael Ozighor Enihe
Rajesh Prasad
Francisca Nonyelum Ogwueleka
Fatimah Binta Abdullahi
The effect of imbalance data mitigation techniques on cardiovascular disease prediction
Journal of Nigerian Society of Physical Sciences
Imbalance dataset
Cardiovascular disease prediction
SMOTE-TOMEK
Marchine learning
Overfitting and Underfitting
title The effect of imbalance data mitigation techniques on cardiovascular disease prediction
title_full The effect of imbalance data mitigation techniques on cardiovascular disease prediction
title_fullStr The effect of imbalance data mitigation techniques on cardiovascular disease prediction
title_full_unstemmed The effect of imbalance data mitigation techniques on cardiovascular disease prediction
title_short The effect of imbalance data mitigation techniques on cardiovascular disease prediction
title_sort effect of imbalance data mitigation techniques on cardiovascular disease prediction
topic Imbalance dataset
Cardiovascular disease prediction
SMOTE-TOMEK
Marchine learning
Overfitting and Underfitting
url https://journal.nsps.org.ng/index.php/jnsps/article/view/2385
work_keys_str_mv AT raphaelozighorenihe theeffectofimbalancedatamitigationtechniquesoncardiovasculardiseaseprediction
AT rajeshprasad theeffectofimbalancedatamitigationtechniquesoncardiovasculardiseaseprediction
AT franciscanonyelumogwueleka theeffectofimbalancedatamitigationtechniquesoncardiovasculardiseaseprediction
AT fatimahbintaabdullahi theeffectofimbalancedatamitigationtechniquesoncardiovasculardiseaseprediction
AT raphaelozighorenihe effectofimbalancedatamitigationtechniquesoncardiovasculardiseaseprediction
AT rajeshprasad effectofimbalancedatamitigationtechniquesoncardiovasculardiseaseprediction
AT franciscanonyelumogwueleka effectofimbalancedatamitigationtechniquesoncardiovasculardiseaseprediction
AT fatimahbintaabdullahi effectofimbalancedatamitigationtechniquesoncardiovasculardiseaseprediction