A prediction tool incorporating the biomarker S-100B for patient selection for completion lymph node dissection in stage III melanoma

Introduction: Completion lymph node dissection (CLND) in sentinel node (SN)-positive melanoma patients is accompanied with morbidity, while about 80% yield no additional metastases in non-sentinel nodes (NSNs). A prediction tool for NSN involvement could be of assistance in patient selection for CLND. This study investigated which parameters predict NSN-positivity, and whether the biomarker S-100B improves the accuracy of a prediction model. Methods: Recorded clinicopathologic factors were tested for their association with NSN-positivity in 110 SN-positive patients who underwent CLND. A prediction model was developed with multivariable logistic regression, incorporating all predictive factors. Five models were compared for their predictive power by calculating the Area Under the Curve (AUC). A weighted risk score, 'S-100B Non Sentinel Node Risk Score' (SN-SNORS), was derived for the model with the highest AUC. Besides, a nomogram was developed as visual representation. Results: NSN-positivity was present in 24 (21.8%) patients. Sex, ulceration, number of harvested SNs, number of positive SNs, and S-100B value were independently associated with NSN-positivity. The AUC for the model including all these factors was 0.78 (95%CI 0.69-0.88). SN-SNORS was the sum of scores for the five parameters. Scores of <= 9.5, 10-11.5, and >= 12 were associated with low (0%), intermediate (21.0%) and high (43.2%) risk of NSN involvement. Conclusions: A prediction tool based on five parameters, including the biomarker S-100B, showed accurate risk stratification for NSN-involvement in SN-positive melanoma patients. If validated in future studies, this tool could help to identify patients with low risk for NSN-involvement. (C) 2017 Elsevier Ltd, BASO similar to The Association for Cancer Surgery, and the European Society of Surgical Oncology. All rights reserved.