External validation of a model to predict recurrence-free and melanoma-specific survival for patients with melanoma after sentinel node biopsy

Abstract

Background: Recently, a model to predict 5-year recurrence-free survival (RFS) and melanoma-specific survival (MSS) after sentinel lymph node biopsy (SLNB) was published. The aim of this study was to validate that model in a large independent international cohort.

Methods: The database of the Sentinel Lymph Node Working Group (SLNWG) was analysed for patients with malignant melanoma who underwent SLNB. Patients with clinical stage III melanoma, a history of other malignancies, or receiving concomitant systemic therapies during follow-up were excluded. The model's predictive performance was evaluated using discrimination and calibration metrics in the eligible cohort. Decision curve analysis was performed to assess the clinical value of the model.

Results: The external validation cohort consisted of 6174 patients of the SLNWG from the USA, Europe, and Israel. A positive sentinel node was found in 788 patients (12.8%). The area under the time-dependent receiver operating characteristic (ROC) curve of the external validation was 0.76 (95% c.i. 0.74 to 0.77) for RFS and 0.79 (95% c.i. 0.76 to 0.81) for MSS. The model was well calibrated, as the observed 5-year survival rates aligned closely with the predicted survival rates (calibration slope of 0.98 for RFS and calibration slope of 0.99 for MSS). The model provided a net benefit versus the 'treat all' and 'treat none' strategies at the predetermined probability threshold for recurrence of 45%.

Conclusion: The model demonstrated good performance in a large heterogeneous independent cohort, emphasizing its robustness. Decision curve analysis revealed a clear net benefit of the model over a treat all strategy, highlighting its potential for clinical use.

Fig. 1

Flow chart for study SLNWG, Sentinel Lymph Node Working Group.

Fig. 2

Calibration and discrimination of the model predicting RFS for all patients, only patients with a positive SLN, and only patients with a negative SLN RFS, recurrence-free survival; SLN, sentinel lymph node. Values in parentheses are 95% confidence intervals.

Fig. 3

Calibration and discrimination of the model predicting MSS for all patients, only patients with a positive SLN, and only patients with a negative SLN MSS, melanoma-specific survival; SLN, sentinel lymph node. Values in parentheses are 95% confidence intervals.

Fig. 4

Decision curve analysis for the composite outcome of recurrence or death for the full validation cohort of patients who underwent SLNB in the USA, Sweden, Israel, Italy, and the Netherlands a The y-axis represents the net benefit at each probability threshold, reflecting the proportion of patients with the composite outcome correctly identified by the treatment strategy, adjusted for the penalty of incorrectly identifying patients without the composite outcome. The x-axis represents the continuum of threshold probabilities for experiencing the composite outcome within 5 years. The green line represents the net benefit of treating no individuals with adjuvant therapy (treat none approach). The red line represents the net benefit of treating all individuals with adjuvant therapy (treat all approach). The blue line represents the net benefit of treating patients according to the individualized predictions of experiencing the composite outcome resulting from the PREFERS model across the continuum of threshold probabilities (model approach). b Displays the distribution of predicted probabilities for the composite outcome of recurrence or death. SLNB, sentinel lymph node biopsy; PREFERS, Predicting REcurrence-Free mElanoma-specific suRvival for patients who underwent a Sentinel node procedure.