Breast Cancer Survival Prediction using Artificial Neural Network
P. Venkatesan · 2009
Breast cancer survival prediction is an important step in the complex decision process. The present study investigates the effects of prognostic variables on the risk of breast cancer failure/survival using feed forward neural network. The neural network was trained and tested using six hundred and fifty breast cancer patients. 15 prognostic variables were used in this study as features for the input vectors. Multivariate analysis on survival was performed using a recursive partitioning namely classification and regression trees (CART). The results show that the accuracy of artificial neural network (ANN) for the survival prediction was better than regression based approaches. Key words: ANN, Breast cancer, MLP, CART, logistic regression