Page 68 - GTM-3-1

Global Translational Medicine

ORIGINAL RESEARCH ARTICLE
Evaluating machine learning models for

prediction of coronary artery disease

Rejath Jose, Anvin Thomas, Jennifer Guo, Robert Steinberg, and Milan Toma*
Department of Osteopathic Manipulative Medicine, College of Osteopathic Medicine, New York
Institute of Technology, Old Westbury, New York, United States of America

Abstract
Coronary artery disease (CAD) is a prevailing global health issue and a leading
cause of death worldwide. Its accurate and timely diagnosis is crucial for effectively
managing the disease and improving patient outcomes. In this study, we conducted
a comparative analysis of machine learning (ML)-based approaches to detect and
diagnose CAD. A dataset of 918 instances from the UCI ML repository, comprising
11 typical risk factors and CAD predictors, was used for this investigation. The study
deployed ML models in Google Colaboratory and PyCaret, testing their efficacy in
diagnosing CAD. Our study provides a detailed overview of these ML methodologies,
their strengths, and limitations, underscoring the potential of these algorithms to
revolutionize CAD diagnosis and treatment. The overall goal of the study is to
create a model that can predict the presence or chance of presence of CAD based
on different parameters of the patient’s history. Findings include the showcased
logistic regression model, which was proven to be particularly effective, with an area
under curve of 0.88, indicating a high ability to differentiate between patients with
and without CAD, and a successful ability to identify clinically key features of CAD
*Corresponding author: such as the presence of exertional angina and chest pain. This study emphasizes
Milan Toma the importance of further research in this field to establish ML as a cornerstone of
(tomamil@tomamil.com) modern healthcare diagnostics.
Citation: Jose R, Thomas A,
Guo J, Steinberg R, Toma M.
Evaluating machine learning Keywords: Machine learning; Coronary artery disease; Diagnosis; Predictive modeling;
models for prediction of coronary Health informatics; Medical data analysis
artery disease. Global Transl Med.
2024;3(1):2669.
https://doi.org/10.36922/gtm.2669
Received: January 8, 2024 1. Introduction
Accepted: March 12, 2024
Published Online: March 22, 2024 Cardiovascular disease (CVD) is the leading cause of morbidity and mortality worldwide
1
Copyright: © 2024 Author(s). and in the United States. In 2019, coronary artery disease (CAD), a complex medical
This is an Open Access article subtype of CVD characterized by plaque buildup in the arteries that supply blood to
distributed under the terms of the
1
Creative Commons Attribution the heart, accounted for 8.9 million deaths, or 16% of the world’s total deaths. In 2021,
License, permitting distribution, CAD was responsible for almost 400,000 deaths in the United States and exacted a
and reproduction in any medium, financial burden of over $200 billion in health-care costs. Such statistics maintain the
2,3
provided the original work is
properly cited. importance of early detection and accurate diagnosis in improving patient prognoses
and outcomes.
Publisher’s Note: AccScience
Publishing remains neutral with Coronary angiography is currently the gold standard for the definitive diagnosis of
regard to jurisdictional claims in
published maps and institutional CAD, which uses computed tomography (CT) to visualize the extent of blockage in the
affiliations. coronary arteries. For this procedure, patients are asked to avoid oral intake of food
Volume 3 Issue 1 (2024) 1 https://doi.org/10.36922/gtm.2669