Analysis of Common Indicators and Unidentified Factors of Heart Disease Based on Two Machine Learning Models

Jincheng Guo

2023

Abstract

In recent years, heart disease had caused great attention in the medical and health field. Many researchers continuously care about common key indicators that directly related to heart disease. However, some researchers have found that some unidentified non-direct indicators were also potential factors that affect early heart disease. Therefore, the research theme in this paper is the impact of multiple direct and indirect indicators on the prevalence of heart disease. And research method is downloading a large data set from Kaggle website, which includes 18 variables and 320 thousand samples, before using logistic regression model and random forest model to perform categorical prediction. It is found that the random forest model performs very excellent in the training set, but the comprehensive classification effect on the logistic regression model turns out to be better. Through analysis of these model results, it showed that in addition to well-known indicators such as age and physical health, whether a person have diabetes, stroke, asthma or some other indirect illnesses would also affect whether that person suffer from heart disease. Hence, the prevention and treatment of heart disease patients should start from the early stage of other minor diseases and potential latent factors, and patients should take their physical and psychological state seriously in a comprehensive assessment.

Paper Citation

in Harvard Style

Guo J. (2023). Analysis of Common Indicators and Unidentified Factors of Heart Disease Based on Two 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 315-320. DOI: 10.5220/0012805200003885

in Bibtex Style

@conference{daml23,
author={Jincheng Guo},
title={Analysis of Common Indicators and Unidentified Factors of Heart Disease Based on Two Machine Learning Models},
booktitle={Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML},
year={2023},
pages={315-320},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012805200003885},
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 - Analysis of Common Indicators and Unidentified Factors of Heart Disease Based on Two Machine Learning Models
SN - 978-989-758-705-4
AU - Guo J.
PY - 2023
SP - 315
EP - 320
DO - 10.5220/0012805200003885
PB - SciTePress