FIGURE 6.
Construction and validation of the diagnostic model. (A) Construction of the artificial neural network (ANN) model, which contains the input layer, hidden layer and output layer. (B) Training set receiver operating characteristic curve (ROC), the size of the area under the curve (AUC) demonstrates the feasibility of the model. (C) Validation set ROC, the size of AUC can indicate the applicability of the model. (D) Diagnostic line graph of HBV-LC feature genes, each gene corresponds to a score, and the scores of all genes are summed to obtain the total score. (E) Calibration curve to assess the predictive performance of the diagnostic line graph. (F) Decision curve analysis (DCA), which compares the clinical benefit of the diagnostic line graph model with other diagnostic indicators.