Comparison of artificial neural network with logistic regression as classification models for variable selection for prediction of breast cancer patient outcomes

摘要: The aim of this study was to compare multilayer perceptron neural networks (NNs) with standard logistic regression (LR) identify key covariates impacting on mortality from cancer causes, disease-free survival (DFS), and disease recurrence using Area Under Receiver-Operating Characteristics (AUROC) in breast patients. From 1996 2004, 2,535 patients diagnosed primary entered into the at a single French centre, where they received treatment. For specific as well DFS analysis, ROC curves were greater NN models compared LR model better sensitivity specificity. Four predictive factors retained by both approaches for mortality: clinical size stage, Scarff Bloom Richardson grade, number invaded nodes, progesterone receptor. results enhanced relevance use analysis oncology, which appeared be more accurate prediction cohort.