Skip to main content

Table 3 Model comparisons for predicting NSLN metastasis among SLN+ patients (Bay Area SLN Database).

From: New models and online calculator for predicting non-sentinel lymph node status in sentinel lymph node positive breast cancer patients

  For all SLN+ Pts (n = 285) For pts with known angiolymphatic invasion status (n = 213) For pts with known angiolymphatic invasion and ER status (n = 171)
RP-ROC with 10-fold cross validation    
Sensitivity (%)   78.8 83.2
Specificity (%)   75.5 78.1
Diagnostic Accuracy by AUC (%)   76.7 80.2
Boosted CART with 10-fold cross validation    
Sensitivity (%) 78.2 87.9 89.0
Specificity (%) 62.0 71.4 74.7
Diagnostic Accuracy by AUC (%) 67.7 77.5 80.3
Multivariable logistic regression with 10-fold cross validation    
Sensitivity (%)   78.0 78.9
Specificity (%)   86.2 88.3
Diagnostic Accuracy by AUC (%)   83.3 84.9
MSKCC Breast Cancer Nomogram a    
Diagnsotic Accuracy by AUC (%)    76.7
  1. a Memorial Sloan-Kettering Cancer Center Breast Cancer Nomogram for Prediction of Axillary Lymph Node Metastasis applied to SLN+ pts in Stanford dataset who have complete data for all Nomogram variables