Predicting heart disease risk in patients using various kinds of analytical models

Document Type

Conference Proceeding

Source of Publication

2023 7th IEEE Congress on Information Science and Technology (CiSt)

Publication Date

12-22-2023

Abstract

In 2021, 18 million people were estimated to die every year because of various heart diseases. This excess mortality rate became a pain in the neck for scientists and medical professionals. With new developments in the technological field, artificial intelligence has provided good support for decision-makers on how to deal with many challenges, like heart disease issues. Consequently, many algorithms were proposed to build various models depending on their application. Using different analytical models in predicting heart disease, including logistic regression, decision tree, random forest, neural network, and deep learning models; the logistic regression model gives the highest and best metric scores with an 83% accuracy rate, an 88% precision rate, and an 86% recall rate. From there, this study will significantly contribute to the advancement of healthcare practices by using both big data and advanced analytical models, which will offer valuable insights into addressing critical health issues in society in the future.

ISBN

978-1-6654-6133-7

Publisher

IEEE

Volume

00

First Page

649

Last Page

656

Disciplines

Medicine and Health Sciences

Keywords

Heart disease risk, Analytical models, Artificial intelligence, Logistic regression, Deep learning

Indexed in Scopus

no

Open Access

no

Link to Full Text

Share

COinS