Comparative Study on Coronary Heart Disease Prediction Using Five Machine Learning Models

Haikun Guo

2023

Abstract

In recent times, Coronary Heart Disease (CHD) has emerged as a significant global public health concern, not only due to its mortality rate but also because of the substantial financial burden it places on healthcare systems. Traditional statistical methods for predicting the onset of CHD have limitations in handling multidimensional data and often fail to capture complex interactions among different risk factors. This has created a pressing need for a cost-effective cardiac health monitoring system capable of leveraging large-scale, multidimensional data for accurate CHD predictions. In this research, the author employs machine learning (ML) techniques to address this discrepancy. The author designs and perform a comparative analysis of five ML classifiers: Logistic Regression (LR), K-Nearest Neighbor (KNN), Random Forest (RF), Decision Tree (DT), and Gradient Boosting (GB) for robust CHD forecast. These classifiers were rigorously tested on a dataset that includes various risk factors contributing to CHD. Performance metrics were employed to evaluate the effectiveness of each model, including accuracy, specificity, and sensitivity. The results demonstrate that ML classifiers, particularly Random Forest and Gradient Boosting, show high efficacy in predicting CHD, thereby confirming the potential of ML in augmenting cardiac health monitoring systems. This study has far-reaching implications in preventive healthcare, as it offers a pathway to early diagnosis and effective management of CHD.

Paper Citation

in Harvard Style

Guo H. (2023). Comparative Study on Coronary Heart Disease Prediction Using Five Machine Learning Models. In Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML; ISBN 978-989-758-705-4, SciTePress, pages 256-261. DOI: 10.5220/0012800700003885

in Bibtex Style

@conference{daml23,
author={Haikun Guo},
title={Comparative Study on Coronary Heart Disease Prediction Using Five Machine Learning Models},
booktitle={Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML},
year={2023},
pages={256-261},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012800700003885},
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 - Comparative Study on Coronary Heart Disease Prediction Using Five Machine Learning Models
SN - 978-989-758-705-4
AU - Guo H.
PY - 2023
SP - 256
EP - 261
DO - 10.5220/0012800700003885
PB - SciTePress