Neural network models for breast cancer prognosis

Estimating the risk of relapse for breast cancer patients is necessary, sin ce it affects the choice of treatment This problem involves analysing data of times to relapse of patients and relating them to prognostic variables. Some of the times to relapse will usually be censored. We investigate vario us ways of using neural network models to extend traditional statistical mo dels in this situation. Such models are better able to model both non-linea r effects of prognostic factors and interactions between them, than linear logistic or Cox regression models. With the dataset used in our study, howe ver, the prediction of the risk of relapse is not significantly improved wh en using a neural network model. Predicting the risk that a patient will re lapse within three years, say, is possible from this data, but not when any relapse will happen.