A Comparative Analysis of Machine Learning Models for Prediction of Coronary Artery Disease (CAD) and Congestive Heart Failure (CHF)

Author(s)	Ms. Meenakshi J R, Ms. Mrudula G, Mr. Pavan Pranav B, Mr. Sai Praveen K, Mr. Akshith A, Mr. Suresh Gopi Y
Country	India
Abstract	This study conducts an experimental comparison of four machine learning classifiers—Logistic Regression, Decision Tree, Random Forest, and Gradient Boosting—to simultaneously predict Coronary Artery Disease (CAD) and Congestive Heart Failure (CHF). Two benchmark datasets are employed: the Extended UCI Cleveland Heart Disease Dataset (299 records, 14 attributes) and the Heart Failure Clinical Records Dataset (299 records, 13 attributes). An 80:20 train-test split is adopted alongside oversampling techniques to address class imbalance. Among the evaluated models, Logistic Regression demonstrates superior predictive performance for both conditions, attaining an accuracy of 88.33% with a recall of 85.71% for CAD, and an accuracy of 75.00% with a recall of 73.68% for CHF. Feature importance analysis derived from the Random Forest model reveals that Thalassemia type, Chest Pain, and ST Depression are the most influential predictors for CAD, whereas Follow-up Time, Serum Creatinine, and Ejection Fraction emerge as the dominant contributors for CHF prediction.
Keywords	Machine Learning, Coronary Artery Disease, Congestive Heart Failure, Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, Feature Importance, Clinical Prediction
Field	Engineering
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-04-06

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research