A multivariable model of ultrasound and clinicopathological features for predicting axillary nodal burden of breast cancer: potential to prevent unnecessary axillary lymph node dissection

Table 5 The ROC analysis of cortical thickness, hilum, T stage and the model in the training cohort

Variable	AUC	ACC(%)	SN (%)	SP (%)	PPV (%)	NPV (%)	P-value	95%CI
Variable	AUC	ACC(%)	SN (%)	SP (%)	PPV (%)	NPV (%)	P-value	Lower	Upper
Cortical_thickness	0.690	69.5	67.9	70.1	50.4	87.9	0.003	0.609	0.770
Hilum	0.639	75.3	42.9	85.0	56.1	83.2	< 0.001	0.551	0.728
T stage	0.621	58.0	69.6	54.5	41.5	85.7	< 0.001	0.539	0.703
Model	0.749	78.6	71.4	75.9	67.7	81.1		0.676	0.823

AUC Area under curve, ACC Accuracy, SN Sensitivity, SP Specificity, PPV Positive Predictive Value, NPV Negative Predictive Value, P-value: DeLong test of AUC, CI Confidence interval

ISSN: 1471-2407