Predictive Analysis of Heart Disease using Stochas-tic Gradient Boosting along with Recursive Feature Elimination

Coronary heart disease (CHD) is an illness in which plaque constructs up inside the coronary arteries. CHD descriptions for over 15.9 % of all deaths creates it the most regular origin of death globally. Health professionals are facing tough to anticipate the heart alignment as it is capable of medical practitioners that require experience and knowledge. Over the past few years machine learning has proved to be a very successful tool in clinical diagnosis which take up the huge amount of data. This contains hidden information that can be used effectively in making informed decisions. The investigation such type of data utilizes maximum time in terms of execution and utilization of resources. Data features do not support for the outcomes. Therefore, it is especially significant to recognize the features that add further in recognizing diseases. The aim of this work is to predicting the heart disease stage level of a patient by employ machine learning algorithms. In this regard we used the stochastic gradient boosting algorithm along with Recursive Feature Elimination (RFE) for selecting the best features in the data.