Predicting Heart Disease Using Machine Learning: A Comparative Analysis of Classification Models

Shreyas C.S.* and D N Sujatha
Department of Computer Applications, B.M.S. College of Engineering, Bangalore, India
*Corresponding Author: Shreyas C.S., Department of Computer Applications, B.M.S. College of Engineering, Bangalore, India.

Published: December 03, 2024

View Pdf

Abstract  

This research paper explores the application of machine learning techniques to predict heart disease, a leading cause of deaths worldwide. By utilizing various classification algorithms, including Logistic Regression, Decision Trees, Random Forest, K-Nearest Neighbours, and Support Vector Machines, we aim to identify the most effective model for accurate prediction. The study uses the dataset from Cleveland Heart Disease dataset, with data pre-processing steps such as handling missing values, scaling, and feature selection. Model performance is compared and used with metrics like accuracy, precision, recall, F1-score. The findings indicate that Random Forest algorithm outperforms other models, which provides insights for healthcare professionals in early diagnosis and preventive measures. The results also highlight the potential of machine learning to enhance clinical decision-making and improving patient outcomes.

Keywords: Classification Algorithms; Decision Trees; Healthcare Analytics; Heart Disease Prediction; K-Nearest Neighbour; Logistic Regression; Machine Learning; Random Forest; Support Vector Machines

.