Abstract:
Over the years, heart diseases have become one of the most common causes related to
death. Most of the time heart diseases are detected at the very last stage; therefore, an
accurate prediction may reduce the catastrophe related to heart diseases. Heart-related
diseases have a significant relationship with various health features including age, sex,
heartbeat rate, blood pressure, cholesterol etc. In this context, four machine learning
algorithms (e.g. Multiple Linear Regression, Decision Tree, Random Forest and Support
Vector Machine) are applied on Cleveland heart disease dataset to analyze the
comparative performance for achieving accurate prediction. The dataset contains thirteen
health features, which have significant relations to heart disease. The best prediction has
been achieved by the Random Forest algorithm, which is an ensemble version of the
Decision Tree algorithm. To recapitulate the Random Forest algorithm outperformed
other three algorithms followed by Support Vector Machine algorithm by providing a
satisfactory prediction on 303 patient’s data.
