An Artificial Neural Network Model for Prediction of Survival Time of Breast Cancer Dataset

This paper attempts survival analysis problem on censored dataset. Artificial Neural Networks (ANNs) is a well known, flexible non-linear prediction model for survival analysis over a period of time than other traditional methods. In this work, ANN is used to handle two tasks: first is predicting the status of a patient at a particular endpoint and the second one is predicting the time of disease recurrence. Wisconsin Prognostic Breast Cancer (WPBC) dataset is used for evaluating both the tasks. The results show that ANNs can predict the status and recurrence probability more effectively.