Cardiovascular Disease Prediction Using Machine Learning

Saravanan N P, Manimaran A, Kanisha A, Karthickrajan S, Keerthana Devi S

2025

Abstract

Cardiovascular disease is a major cause of death worldwide, and developing predictive models for early detection and treatment initiation is crucial. A suite of machine learning algorithms, including KNN, LR, and NB, has been developed to improve predictions for CVD. The Cardiovascular Disease Dataset, the largest dataset with over 70,000 records, was pre-processed to recover from missing values, normalize continuous attributes, and remove outliers. Ensemble approaches were found to be more useful than individual classifiers. Bagging trained multiple copies of the same model on different data subsets, improving basic classifier accuracies by an average of 1.96%. Boosting had the highest AUC score of any model, with an average accuracy of 73.4%. The stacking model, which stacked Cat boost, AdaBoost, and other tree classifiers, showed the best results, with a train accuracy of 84.33% and a test accuracy of 95.05%. This suggests the potential of machine learning methods in developing more accurate classifiers for CVD prediction. The stacking model is significantly better than the rest, indicating the potential for the development of sophisticated diagnostic tools that improve patient outcomes through correct and timely diagnosis

Paper Citation

in Harvard Style

N P S., A M., A K., S K. and S K. (2025). Cardiovascular Disease Prediction Using Machine Learning. In Proceedings of the 3rd International Conference on Futuristic Technology - Volume 3: INCOFT; ISBN 978-989-758-763-4, SciTePress, pages 877-886. DOI: 10.5220/0013734300004664

in Bibtex Style

@conference{incoft25,
author={Saravanan N P and Manimaran A and Kanisha A and Karthickrajan S and Keerthana Devi S},
title={Cardiovascular Disease Prediction Using Machine Learning},
booktitle={Proceedings of the 3rd International Conference on Futuristic Technology - Volume 3: INCOFT},
year={2025},
pages={877-886},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013734300004664},
isbn={978-989-758-763-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Futuristic Technology - Volume 3: INCOFT
TI - Cardiovascular Disease Prediction Using Machine Learning
SN - 978-989-758-763-4
AU - N P S.
AU - A M.
AU - A K.
AU - S K.
AU - S K.
PY - 2025
SP - 877
EP - 886
DO - 10.5220/0013734300004664
PB - SciTePress