Construction of a predictive model for gastric cancer neuroaggression and clinical validation analysis: A single-center retrospective study

Table 4 Diagnostic efficacy of PNI prediction model for gastric cancer

Model name	AUC (95%CI)	Optimal threshold	Yoden index	Sensitivity	Specificity
Clinical model	0.858 (0.692-1.000)	0.486	0.772	0.926	0.845
Spectral CT model	0.832 (0.680-0.983)	0.531	0.695	0.925	0.769
Imaging omics model	0.897 (0.778-1.000)	0.718	0.809	0.963	0.845
Clinical + spectral model	0.772 (0.608-0.936)	0.643	0.735	0.889	0.845
Clinical and imaging omics models	0.842 (0.717-0.967)	0.67	0.584	0.815	0.769
Energy spectrum + imaging omics model	0.846 (0.720-0.972)	0.809	0.553	0.63	0.923
Clinical + energy spectrum + imaging omics model	0.927 (0.850-1.000)	0.879	0.778	0.778	1.00

CT: Computed tomography; AUC: Area under the curve.