Design of Classifier Using Artificial Neural Network for Patients Survival Analysis

The aim of this paper is to develop the design of classifier using Artificial Neural Network for patients survival analysis based on echocardiography dataset. Survival analysis can be considered a classification problem in which the application of machine learning methods is appropriate. Survival analysis plays an important role not only for health care policy markers, but also for the clinician. Echocardiography is used for diagnosis of cardiac diseases and to arrive at precise diagnosis experienced cardiologists need complementary assistance from intelligent decision system. Artificial Neural Networks have emerged as an important tool for classification. The advantage of Artificial Neural Network helps for efficient classification of given data. In this research paper, design the classifiers Back Propagation Neural Network (BPNN) and Radial Basis Function Neural Network (RBFNN) for patient’s survival analysis. The performance of classifiers is measured in terms of classification accuracy. Experimental result showed that the good design of classifier for patients survival analysis based on Echocardiogram database is Back propagation neural network (BPNN) with training set classification accuracy 93% and testing set classification accuracy 84% and design of Radial Basis function neural network (RBFNN) classifier training set classification accuracy 88% and testing set classification accuracy 69%.