Predictive Analysis of Rapid Spread of Heart Disease with Data Mining

cardiovascular disease is the leading cause of mortality for both sexes in worldwide. Heart disease is increasing at a rapid rate in both older and younger generation of males and females now days. So in need demand of right strategies, development and implementation of effective health monitoring policies should be emphasized to combat the epidemic of heart related diseases. So early detection and treatment with the use of both conventional and innovative technique must be preferred In this paper we have used the UCI machine learning repository Cleveland heart disease database having 303 instance and 76 attributes. For the proposed method we have used the Information gain concept for selection of best attribute and processes the selected features using weka and python. This paper identifies the gap of research on prediction of heart disease based on python Anaconda navigator, spyder and weka platform on which we have much emphasized. The various techniques, processes which have used to train the model of heart datasets such as feature selection, numpy, pandas library, decision tree classifier, KNN classifier, entropy, gini-index, confusion matrix.The result shows that decision tree classifier is most effective and appropriate for prediction of UCI repository Cleveland heart dataset.