Machine Learning Methods for Heart Disease Prediction

Hongyu Zhou

2024

Abstract

Heart disease prediction and treatment play a crucial role in enhancing human health. Numerous studies have highlighted the effectiveness of machine learning models in predicting heart diseases. However, there still have problems with widely use and the accuracy of the prediction. This paper aims to apply different machine learning models, including Naïve Bayes, Decision Tree, Random Forest, XGBoost, and Neural Network System, to a specific dataset and provide a comprehensive evaluation. After thorough analysis using various metrics, the Random Forest model demonstrated the highest recall and F1-score among all models. Additionally, the shallow neural networks model outperformed traditional neural network structures with fewer parameters in this task. In conclusion, this study emphasizes the significance of machine learning models in improving heart disease prediction and treatment. Further research and development in this area are essential to enhance healthcare outcomes and promote overall well-being.

Paper Citation

in Harvard Style

Zhou H. (2024). Machine Learning Methods for Heart Disease Prediction. In Proceedings of the 1st International Conference on Innovations in Applied Mathematics, Physics and Astronomy - Volume 1: IAMPA; ISBN 978-989-758-722-1, SciTePress, pages 46-52. DOI: 10.5220/0012990900004601

in Bibtex Style

@conference{iampa24,
author={Hongyu Zhou},
title={Machine Learning Methods for Heart Disease Prediction},
booktitle={Proceedings of the 1st International Conference on Innovations in Applied Mathematics, Physics and Astronomy - Volume 1: IAMPA},
year={2024},
pages={46-52},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012990900004601},
isbn={978-989-758-722-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Innovations in Applied Mathematics, Physics and Astronomy - Volume 1: IAMPA
TI - Machine Learning Methods for Heart Disease Prediction
SN - 978-989-758-722-1
AU - Zhou H.
PY - 2024
SP - 46
EP - 52
DO - 10.5220/0012990900004601
PB - SciTePress