Predicting Heart Disease with Machine Learning: A Comparative Analysis of Models

Abstract

Heart disease remains a leading cause of mortality worldwide, highlighting the urgent need for accurate and early prediction systems. This study aims to develop and compare the performance of various machine learning (ML) models for predicting the presence of heart disease based on clinical attributes. Using a dataset comprising patient information such as age, sex, blood pressure, and cholesterol levels, the study applies and evaluates four widely used ML algorithms: Decision Tree, Random Forest, Support Vector Machine (SVM), and Logistic Regression. The dataset was pre-processed through techniques such as missing value imputation and feature scaling to ensure model reliability. Model performance was assessed using precision, recall, accuracy, and F1-score. Among the models tested, Decision Tree and Random Forest demonstrated superior performance, achieving accuracy rates of approximately 98.5%. The findings underscore the potential of tree-based models in developing robust heart disease prediction tools. This study contributes to the growing field of health informatics by offering a comparative approach to model evaluation and showcasing the importance of data pre-processing. The novelty lies in its systematic performance comparison under a unified framework and its emphasis on high-accuracy, interpretable ML models suitable for clinical application.

Keywords

• machine learning
• heart disease prediction
• decision tree
• random forest
• SVM
• logistic regression

How to cite

Jahangir Hussen, Madhabi Rani Kar, Taspia Momotaz (2025). Predicting Heart Disease with Machine Learning: A Comparative Analysis of Models. Sonargaon University Journal, 5(II), 81–94.

@article{hussen20257,
  title   = {Predicting Heart Disease with Machine Learning: A Comparative Analysis of Models},
  author  = {Jahangir Hussen and Madhabi Rani Kar and Taspia Momotaz},
  journal = {Sonargaon University Journal},
  volume  = {5},
  number  = {II},
  pages   = {81--94},
  year    = {2025},
  issn    = {2518-3125},
  url     = {https://su.edu.bd/journal/volume-5-issue-2/predicting-heart-disease-with-machine-learning-a-comparative-analysis-of-models}
}