Design & Analysis of Computational Features Prediction Model for Heart Disease Diagnosis

Heart disease prediction is designed to support clinicians in their diagnosis. 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. We also propose a new feature selection method algorithm which is the hybrid method combining CFS and RandomTree followed by part rule. The proposed algorithm provides better accuracy compared to the traditional algorithm and the hybrid Algorithm CFS. This research paper proposed a frequent feature selection method for Heart Disease Prediction. Good performance of this method comes from the use of the RandomTree and the PART rule. The nonadditivity of the RandomTree against different target attributes measure reflects the importance of the feature attributes as well as their interactions. Using medical profiles such as age, sex, blood pressure and blood sugar it can predict the likelihood of patients getting a heart disease. Clustering the objects which have similar meaning, the proposed approach improves the accuracy and reduces the computational time.