Survival Data Analysis Using Recurrent Neural Networks

Abstract

Recently, recurrent neural networks have been widely used in many fields. Bone marrow transplants are a standard treatment for leukemia disease data. Recovery following bone marrow transplantation is a multistate process. The bootstrapping for the recurrent neural network is introduced when selecting the optimum number of hidden units and testing the goodness-of-test. We can predict the probability of surviving during the course of the disease with better accuracy than feed-forward neural networks, partial logistic models.