Fig. 7
From: A neural network model to screen feature genes for pancreatic cancer
Construction of the neural network model. A Neural network model were built to predict genetic properties and consist of an input layer, hidden layer, and output layer; B Plotting ROC curve to detect the accuracy of the train group neural network model, the AUC was 0.990 (95% CI: 0.976–1.000); C ROC curve detection test group neural network model accuracy, the AUC was 0.869 (95% CI: 0.720–0.983)