Heart Disease Prediction System Using Model Of Machine Learning and Sequential Backward Selection Algorithm for Features Selection

Detection of Heart Disease (HD) by using models of machine learning (ML) is very effective in early stages. The HD treatment and recovery is effective if detected the disease at initial stages. HD identification by machine learning (ML) techniques has been developed to assist the physicians. In this study we proposed an Identification system by using ML models to classify the HD and healthy subjects. Sequential backward selection of feature algorithm was used to select more appropriate features to increase the classification accuracy and reduced the computational time of predictive system. Cleveland heart disease dataset was for evaluation of the system. The dataset 70% used for training and remaining for validation. The proposed system performances have been measured by using evaluation metrics. The experimental results shows that Sequential Backward Selection (SBS) algorithms choose appropriate features and these features increase the accuracy using K-Nearest Neighbor supervised machine learning classifier. The good accuracy of this study suggests that the proposed model will effectively identify the HD and healthy subjects.