Publications

Abstract : One of the major causes of world's high death rate is heart disease. Massive volumes of data related to clinical trials and analysis are stored on biomedical equipment and other systems in the hospital. As a result, understanding the data associated with heart disease is crucial for enhancing prediction accuracy. In this study, the performance of models created with machine learning classification algorithms and standardized characteristics derived with various feature selection approaches was tested experimentally. This study investigated the possibilities of classification approaches, notably decision trees, K-Nearest Neighbour (KNN), Support Vector Machine (SVM) and Random Forest (RF), for the prediction of heart disease. Medical features of individualslike age, gender, blood pressure, fasting blood sugar, and the type of chest discomfort can be used to predict an individual's risk of getting heart disease. Consequently, medical community is flourishing. when compared to previous methods, classification-based approaches have shown to be highly effective and accurate. This research compares many ways for predicting heart issues. The results of this study will help researchers better grasp the present approaches for developing heart disease prediction models. This research presents the findings of a study of key machine learning algorithms that could be utilized to develop a highly accurate and efficient prediction model to help physicians reduce the number of heart disease-related deaths.