Machine Learing-Based Heart Disease Prediction: Insights and Comparative Analysis

Yawen Chang, Xiaoyi Chen, Lingzhi He

2023

Abstract

The incidence of heart attacks has increased rapidly all over the world. This research offers an in-depth discussion of the performance and implications of various machine learning methods for heart disease prediction, despite the existing comparative analyses in the literature. In this research, three machine learning algorithms, K-Nearest Neighbor (KNN), Support vector machine (SVM) and Adaptive Boosting, were evaluated. They were used to deal with the data about heart disease. The dataset comprised 303 patient records with 14 distinct attributes, including age, sex, chest pain type etc. Key findings included the influence of age and sex on heart disease risk, with females showing a higher susceptibility. Various chest pain types and exercise-induced angina were linked to different heart attack probabilities. Moreover, the study highlighted the significance of maximum heart rate, ST segment slope, and ST depression values in risk assessment. Among three machine learning algorithms, SVM achieved the highest accuracy while KNN exhibited better sensitivity for detecting patients with heart disease. The research underscored the importance of selecting appropriate algorithms based on specific goals, offering insights for early heart disease diagnosis and treatment.

Paper Citation

in Harvard Style

Chang Y., Chen X. and He L. (2023). Machine Learing-Based Heart Disease Prediction: Insights and Comparative Analysis. In Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML; ISBN 978-989-758-705-4, SciTePress, pages 305-314. DOI: 10.5220/0012805000003885

in Bibtex Style

@conference{daml23,
author={Yawen Chang and Xiaoyi Chen and Lingzhi He},
title={Machine Learing-Based Heart Disease Prediction: Insights and Comparative Analysis},
booktitle={Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML},
year={2023},
pages={305-314},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012805000003885},
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 - Machine Learing-Based Heart Disease Prediction: Insights and Comparative Analysis
SN - 978-989-758-705-4
AU - Chang Y.
AU - Chen X.
AU - He L.
PY - 2023
SP - 305
EP - 314
DO - 10.5220/0012805000003885
PB - SciTePress