Survival analysis and neural nets

Abstract

We consider feed-forward neural nets and their relation to regression models for survival data. We show how the back-propagation algorithm may be used to obtain maximum likelihood estimates in certain standard regression models for survival data, as well as in various generalizations of these. Examples concerning malignant melanoma and post-partum amenorrhoea during lactation are used as illustration. We conclude that although problems with the substantial number of parameters and their interpretation remain, the feed-forward neural network models are flexible extensions to the standard regression models and thereby candidates for use in prediction and exploratory analyses in larger data sets.