Data Science Framework - Heart Disease Predictions, Variant Models and Visualizations

Heart disease refers to a condition where the blood vessels are blocked and the heart stops functioning. Many of the researches are concluded that this disease has become number one cause of death cases. It is alarmed that abnormalities can only be detected and recognized in its last stages. However it is curable if the person detects the disease earlier. The goal of this paper is to develop a data science framework which addresses the how to discover the chances of existence of heart disease by applying different classification algorithms, influence and distribution of various parameters are playing major role in disease prediction along with visualizations on Cleveland cardiovascular medical records. To minimize the diagnostic error caused by the complexity of visual and subjective interpretation. This work majorly aims to find the optimal classification algorithm on the heart disease affected health records and majorly influencing parameters. This can be used for predicting the heart disease on the classification reports. This experimental work focuses on the performance of the system was tested and classified by various algorithms such as Random Forest, Vector support, Logistic regression and XG-Boost for building the heart disease prediction model and evaluates the performance of the model.