Optimal and Novel Hybrid Feature Selector for Accurate Prediction of Heart Disease

Heart disease prediction is designed to support clinicians in their diagnosis. We proposed a method for classifying the heart disease data. The patient's record is predicted to find if they have symptoms of heart disease through data mining. It is essential to find the best fit classification algorithm that has greater accuracy on classification in the case of heart disease prediction. Since the data is huge attribute selection method used for reducing the dataset. Then the reduced data is given to the classification. In the investigation, the hybrid attribute selection method combining CFS and Filter Subset Evaluation gives better accuracy for classification. We also propose a new feature selection method algorithm which is the hybrid method combining CFS and Bayes Theorem. The proposed algorithm provides better accuracy compared to the traditional algorithm and the hybrid algorithm CFS and Filter Subset Evaluation.