Fig. 2
From: Predictive model for 5-year mortality after breast cancer surgery in Taiwan residents
Schematic representation of the artificial neural network (ANN) model. This model consists of 7 input neurons [age, Charlson comorbidity index (CCI), chemotherapy, radiotherapy, hormone therapy, surgery volumes of hospital and surgeon], 1 bias neuron in the input layer, 4 neurons in a single hidden layer (H1-4), 1 bias neuron in the hidden layer (HB), and 2 output neurons (death and survival) representing the 5-year outcome of breast cancer patients after surgery. Surgery volume of hospital/surgeon was defined as the percentage of breast cancer surgeries among the total surgeries performed by the respective hospital or surgeon during the study period