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 6 The ROC analysis of cortical thickness, hilum, T stage and the model in the validation 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	0.718	74.0	66.7	77.0	54.1	85.1	0.009	0.605	0.832
Hilum	0.639	74.0	40.0	87.8	57.1	78.3	0.001	0.514	0.764
T stage	0.614	57.6	70.0	70.0	37.5	81.3	0.007	0.496	0.731
Model	0.783	77.9	70.0	71.6	61.2	84.9		0.685	0.881

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