A Comparative Study of Machine Learning Models for Cardiovascular Disease Prediction

Beining Qian

2024

Abstract

The efficacy of diverse machine learning approaches in predicting cardiovascular diseases is compared in this analysis by utilizing a range of hyperparameter tuning and data preprocessing techniques to improve model performance. The methods applied include encoding categorical data, generating additional features, selecting the most relevant features, and standardizing data, along with extensive hyperparameter optimization. The models evaluated include Decision Tree, Logistic Regression, Random Forest, and Extreme Gradient Boosting (XGBoost). The results show that compared with other models, the Random Forest Model has a unique ensemble learning method, and achieves excellent performance and robustness by virtue of this method. As demonstrated by results, the Random Forest effectively balances bias and variance and addresses the complexity of medical data. The results of the experiment proved to be the best performer in this survey was the Random Forest Model, although XGBoost also showed strong performance with its sophisticated boosting and regularization strategies. This emphasizes how crucial model tuning and selection are to improving forecast accuracy. To further improve prediction reliability and generality, future research should investigate more sophisticated models and methodologies, optimize preprocessing and tuning strategies, and incorporate larger datasets.

Paper Citation

in Harvard Style

Qian B. (2024). A Comparative Study of Machine Learning Models for Cardiovascular Disease Prediction. In Proceedings of the 1st International Conference on Modern Logistics and Supply Chain Management - Volume 1: MLSCM; ISBN 978-989-758-738-2, SciTePress, pages 377-381. DOI: 10.5220/0013332300004558

in Bibtex Style

@conference{mlscm24,
author={Beining Qian},
title={A Comparative Study of Machine Learning Models for Cardiovascular Disease Prediction},
booktitle={Proceedings of the 1st International Conference on Modern Logistics and Supply Chain Management - Volume 1: MLSCM},
year={2024},
pages={377-381},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013332300004558},
isbn={978-989-758-738-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Modern Logistics and Supply Chain Management - Volume 1: MLSCM
TI - A Comparative Study of Machine Learning Models for Cardiovascular Disease Prediction
SN - 978-989-758-738-2
AU - Qian B.
PY - 2024
SP - 377
EP - 381
DO - 10.5220/0013332300004558
PB - SciTePress