Research Article

Nonlinear Survival Regression Using Artificial Neural Network

Table 1

Describing of models* and its censoring status.

Model Censoring status

Model (I): Average censoring for training and testing sets equal to 20%, 30%, 40%, 50%, 60%, 70%, and 80%
Model (II): Average censoring for training and testing sets equal to 20%, 30%, 40%, 50%, 60%, 70%, and 80%
Model (III): Average censoring for training and testing sets equal to 20%, 30%, 40%, 50%, 60%, 70%, and 80%
Model (IV): Average censoring for training and testing sets equal to 20%, 30%, 40%, 50%, 60%, 70%, and 80%

The hazard at any time was considered as exponential form, and then the survival time was generated.