Construction and validation of a multiparameter diagnostic model based on conventional tumor markers and cytokines for lung cancer

Figure 1 Receiver operating characteristic analysis. A: Receiver operating characteristic (ROC) analysis of carcinoembryonic antigen, cytokeratin 19 fragment, neuron-specific enolase, interleukin-8, monocyte chemoattractant protein-1, and tumor necrosis factor-alpha; B-E: ROC analysis of four multiparameter diagnostic models: Binary logistic regression model (B), bayes discriminant model (C), χ² automatic interaction detection classification tree model (D); and artificial neural network model (E); F: ROC analysis of binary logistic regression model for validation group. CEA: Carcinoembryonic antigen; CY211: Cytokeratin 19 fragment; NSE: Neuron-specific enolase; IL: Interleukin; MCP-1: Monocyte chemoattractant protein-1; TNF-α: Tumor necrosis factor-alpha.