Research Article
A Comparative Examination of Methodical Approaches for Machine Learning-based Heart Disease Prediction
|
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
| Volume 187 - Issue 115 |
| Published: June 2026 |
| Authors: Asha Dilipkumar Jariwala, Hemangini Patel |
10.5120/ijcad77258553170
|
Asha Dilipkumar Jariwala, Hemangini Patel . A Comparative Examination of Methodical Approaches for Machine Learning-based Heart Disease Prediction. International Journal of Computer Applications. 187, 115 (June 2026), 44-49. DOI=10.5120/ijcad77258553170
@article{ 10.5120/ijcad77258553170,
author = { Asha Dilipkumar Jariwala,Hemangini Patel },
title = { A Comparative Examination of Methodical Approaches for Machine Learning-based Heart Disease Prediction },
journal = { International Journal of Computer Applications },
year = { 2026 },
volume = { 187 },
number = { 115 },
pages = { 44-49 },
doi = { 10.5120/ijcad77258553170 },
publisher = { Foundation of Computer Science (FCS), NY, USA }
}
%0 Journal Article
%D 2026
%A Asha Dilipkumar Jariwala
%A Hemangini Patel
%T A Comparative Examination of Methodical Approaches for Machine Learning-based Heart Disease Prediction%T
%J International Journal of Computer Applications
%V 187
%N 115
%P 44-49
%R 10.5120/ijcad77258553170
%I Foundation of Computer Science (FCS), NY, USA
Abstract
Heart disease is seen as a contemporary epidemic. People frequently disregard their health as a result of modern lives and work-related stress, which leads to an increase in a number of health problems. Among these, cardiovascular disease has become one of the most common and dangerous illnesses. Numerous risk factors, including diabetes, high blood pressure, high cholesterol, irregular pulse rate, and other associated medical disorders, make heart disease prediction difficult. The primary objective is to identify and process heart-related data in order to identify cardiac problems and save lives. To predict cardiac disease, In this paper, machine learning methods such as KNN, SVM, NB, RF, LR, DT, RF + SVM, RF + DT, RF + KNN, and HRLFM. The UCI repository and Kaggle are the sources of the dataset used to train and evaluate the prediction model. Compare to all other model HRLFM (Hybrid random forest and logistic regression) is outperformed
References
No references available
Index Terms
Keywords