Heart Disease Prediction using Machine Learning

Abstract

Early detection and timely medical intervention significantly improve patient outcomes. However, traditional diagnostic methods can be time-consuming and rely heavily on expert interpretation. With advancements in Artificial Intelligence and the increasing availability of medical datasets, machine learning offers a reliable and efficient approach to heart-disease prediction. This project, Heart Disease Prediction Using Machine Learning, presents an end-to-end predictive system developed using machine learning algorithms. The objective is to analyse clinical parameters such as age, sex, chest pain type, cholesterol, resting blood pressure, maximum heart rate, exercise-induced angina, ST depression (oldpeak), and thalassemia to predict the likelihood of heart disease. The methodology includes data preprocessing, Exploratory Data Analysis (EDA), baseline model comparison, correlation study, hyperparameter tuning, and evaluation using metrics such as accuracy, precision, recall, F1-score, and ROC-AUC. Among the models evaluated—Logistic Regression, K-Nearest Neighbours, and Random Forest—the optimized Logistic Regression model exhibited the best-balanced performance, achieving strong accuracy and interpretability. The system demonstrates the potential of machine learning in enhancing early detection, supporting clinical decision-making, and improving healthcare delivery.