Prediction of Heart Attack on Random Forest and Logistic Regression

Xinyi Huang

2023

Abstract

The heart is one of the most important organs. There are various kinds of heart diseases, with coronary artery disease (CAD) being the most prevalent ones. CAD refers to a group of diseases caused by the damage to the coronary arteries that supply oxygen and blood, resulting in ischemia, hypoxia or necrosis. About 2% of the world’s population suffers from CAD, which causes 17.5 million deaths worldwide every year. Therefore, monitoring and prevention of heart disease is essential. The study uses two different algorithms, Random Forest Classifier and Logistic Regression to establish models, with respective accuracies of 0.9798 and 0.8965. RF is found to be more effective than LR in this small classification problem. Future research should focus on integrating larger, more diverse datasets and introducing other advanced machine learning algorithms in conjunction with the RF algorithm to explore hidden patterns in the data. These models can help predict the risk of heart disease.

Paper Citation

in Harvard Style

Huang X. (2023). Prediction of Heart Attack on Random Forest and Logistic Regression. In Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML; ISBN 978-989-758-705-4, SciTePress, pages 466-470. DOI: 10.5220/0012816000003885

in Bibtex Style

@conference{daml23,
author={Xinyi Huang},
title={Prediction of Heart Attack on Random Forest and Logistic Regression},
booktitle={Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML},
year={2023},
pages={466-470},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012816000003885},
isbn={978-989-758-705-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML
TI - Prediction of Heart Attack on Random Forest and Logistic Regression
SN - 978-989-758-705-4
AU - Huang X.
PY - 2023
SP - 466
EP - 470
DO - 10.5220/0012816000003885
PB - SciTePress