Abstract: The major cause of death worldwide in recent years has been heart disease. This issue is being raised globally as a result of changes in dietary habits, working cultures, and other aspects of daily living. The creation of a technique that can identify early indications and so save many lives is one method for treating and diagnosing this disease. Researchers can estimate the prevalence of heart disease in high-risk groups using machine learning (ML) techniques. For efficient prevention, management and treatment of diseases, it is crucial to create precise and trustworthy approaches for early illness prediction through automation. In previous publications, multiple experts have discussed efforts to create the optimum techniques for predicting heart disease. This study compares three commonly used heart disease prediction methods. These results can be utilised to assist in creating precise and effective models that aid physicians in lowering the count of heart disease fatalities. The cardiovascular systems of three ML algorithms—Logistic Regression (LR), Support Vector Machine (SVM), and Random Forest (RF)—are compared in this study.

Keywords: Logistic Regression, Support Vector Machine, Random Forest, Heart disease prediction.

| DOI: 10.17148/IARJSET.2023.10762