Predicting Heart Disease Risk Using Machine Learning Models and Feature Selection Techniques

Abstract

Heart disease is one of the leading causes of death worldwide, making early detection essential for improving patient outcomes. With advancements in machine learning (ML), predictive models now offer a powerful way to assist doctors in diagnosing heart disease more accurately and efficiently. This study explores various ML algorithms, including Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), Naïve Bayes (NB), and K-Nearest Neighbors (KNN), to identify the most effective approach for heart disease prediction. Using the Cleveland Heart Disease Dataset, which contains 1,025 patient records with 14 medical attributes, we preprocessed the data, selected key features, and optimized model parameters. After evaluating the models with 10-fold cross-validation, the Random Forest model achieved the highest accuracy (98%), followed by Decision Tree (97%). These results highlight the potential of ML-based tools in clinical decision-making, helping doctors detect heart disease at an earlier stage and make informed treatment plans.