A practical nomogram and risk stratification system predicting the cancer-specific survival for patients aged >50 with advanced melanoma.

Objective: To investigate risk factors for advanced melanoma over 50 years of age and to develop and validate a new line chart and classification system.

Methods: The SEER database was screened for patients diagnosed with advanced melanoma from 2010 to 2019 and Cox regression analysis was applied to select variables affecting patient prognosis. The area under curve (AUC), relative operating characteristic curve (ROC), Consistency index (C-index), decision curve analysis (DCA), and survival calibration curves were used to verify the accuracy and utility of the model and to compare it with traditional AJCC tumor staging.