CLINICAL RESEARCH
Application of artificial neural networks for predicting presence of non-sentinel lymph node metastases in breast cancer patients with positive sentinel lymph node biopsies
 
More details
Hide details
 
Submission date: 2015-08-26
 
 
Final revision date: 2015-10-02
 
 
Acceptance date: 2015-11-09
 
 
Online publication date: 2016-05-05
 
 
Publication date: 2017-10-30
 
 
Arch Med Sci 2017;13(6):1399-1407
 
KEYWORDS
TOPICS
ABSTRACT
Introduction: The aim of this article is to present a new predictive tool for non-sentinel lymph node (nSLN) metastases.
Material and methods: One thousand five hundred and eighty-three patients with early-stage breast cancer were subjected to sentinel lymph node biopsy (SLNB) between 2004 and 2012. Metastatic SLNs were found in 348 patients. Selective axillary lymph node dissection (ALND) was performed in 94% of cases. Involvement of the nSLNs was identified in 32.1% of patients following ALND. The correlation between nSLN involvement and selected epidemiological data, primary tumor features and details of the diagnostic and therapeutic management was examined. Multivariate analysis was performed using an artificial neural network to create a new nomogram.
Results: Accuracy of the new test was calculated using the area under the receiver operating characteristics curve (AUC). We obtained an AUC coefficient equal to 0.87 (95% confidence interval (CI): 0.81–0.92). Sensitivity was 69%, specificity 86%, accuracy 80% (retrospective group) and 77%, 46%, 66% (validation group), respectively. For the Memorial Sloan-Kettering Cancer Center (MSKCC) nomogram the calculated AUC value was 0.71, for Stanford 0.68, for Tenon 0.67.
Conclusions: In the analyzed group only the MSKCC nomogram and the new model for prediction of nSLN involvement showed AUC values exceeding the expected level of 0.70. Our nomogram performs well in prospective validation on patient series. The overall assessment of clinical usefulness of this test will be possible after testing it on different patient populations.
eISSN:1896-9151
ISSN:1734-1922
Journals System - logo
Scroll to top