Related Experiment Video
Updated: Jun 25, 2026
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
Predictive probability of four different breast cancer nomograms for nonsentinel axillary lymph node metastasis in
Akif S Gur1, Bulent Unal, Ronald Johnson
1Department of Surgery, Magee-Women's Hospital of the University of Pittsburgh Medical Center (UPMC), Pittsburgh, PA 15213, USA.
Background:
Although completion axillary lymph node dissection (CALND) is the gold standard for evaluating axillary status after identification of a positive sentinel lymph node (SLN) in breast cancer, almost 40% to 70% of SLN-positive patients will have negative non-SLNs. To predict non-SLN metastases (NSLNM) in patients with a positive SLN biopsy, four different nomograms have been created. The aim of this study was to evaluate the accuracy of four different nomograms in our SLN-positive breast cancer patients.
Study Design:
We identified 319 patients who had a positive SLN biopsy and CALND at our hospital during an 8-year period. Breast cancer nomograms developed by Memorial Sloan-Kettering Cancer Center, Tenon Hospital, Cambridge University, and Stanford University were used to calculate the probability of NSLNM. The area under the receiver operating characteristics curve was calculated for each nomogram, and values greater than 0.70 were accepted as demonstrating considerable discrimination.
Results:
One hundred seven of 319 patients (33.5%) had positive axillary NSLNM. The mean number of SLNs was 2.01 (range, 1 to 11 nodes), and the mean number of positive SLNs was 1.44 (range, 1 to 9 nodes). The area under the curve values were 0.70, 0.69, 0.69, and 0.64 for the Memorial Sloan-Kettering Cancer Center, Tenon, Cambridge, and Stanford models, respectively.
Conclusions:
We found that the Memorial Sloan-Kettering Cancer Center nomogram was more predictive than the other nomograms, but the Cambridge model and the Tenon model reached borderline values for accurate prediction. Nomograms developed at other institutions should be used with caution when counseling patients about the risk of additional nodal disease.
