Heart Disease Prediction Based on the Random Forest Algorithm

Jiaxuan Huang

2023

Abstract

Annually, many lives are claimed by heart disease worldwide, which is influenced by many complicated factors. In order to detect the disease as early as possible instead of missing the optimal treatment period, high-accuracy prediction of heart disease is crucial. This paper aims to explore the viability of applying a specific machine learning algorithm called random forest to heart disease prediction. In this research work, a prediction system including data preprocessing, dimensionality reduction, model building based on the random forest algorithm, and parameter tuning using grid search is developed. Evaluation experiments are conducted using percentage split and cross validation to test the method, with a dataset obtained from Kaggle involved. It is concluded that the method based on the random forest algorithm has good application prospects in the task of predicting heart disease since the values of the metrics selected in the study are all above 0.9 in the experiments.

Paper Citation

in Harvard Style

Huang J. (2023). Heart Disease Prediction Based on the Random Forest Algorithm. In Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML; ISBN 978-989-758-705-4, SciTePress, pages 503-508. DOI: 10.5220/0012798700003885

in Bibtex Style

@conference{daml23,
author={Jiaxuan Huang},
title={Heart Disease Prediction Based on the Random Forest Algorithm},
booktitle={Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML},
year={2023},
pages={503-508},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012798700003885},
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 - Heart Disease Prediction Based on the Random Forest Algorithm
SN - 978-989-758-705-4
AU - Huang J.
PY - 2023
SP - 503
EP - 508
DO - 10.5220/0012798700003885
PB - SciTePress