A Novel Nomogram and Risk Classification System Predicting the Cancer-Specific Mortality of Patients with Initially Diagnosed Metastatic Cutaneous Melanoma.

BACKGROUND Cutaneous melanoma and distant organ metastasis has varying outcomes. Considering all prognostic indicators in a prediction model might assist in selecting cases who could benefit from a personalized therapy strategy. OBJECTIVE This study aimed to develop and validate a prognostic model for patients with metastatic melanoma. METHODS A total of 1535 cases diagnosed with metastatic cutaneous melanoma (stage IV) were identified from the Surveillance, Epidemiology, and End Results database. Patients were randomly divided into the training (n = 1023) and validation (n = 512) cohorts. A prognostic nomogram was established based predominantly on results from the competing-risk regression model for predicting cancer-specific death (CSD). The area under the time-dependent receiver operating characteristic curve (AUC), calibration curves, and decision curve analyses (DCAs) were used to evaluate the nomogram. RESULTS No significant differences were observed in the clinical characteristics between the training and validation cohorts. In the training cohort, patient-, tumor-, and treatment-related predictors of CSD for metastatic melanoma included age, sex, race, marital status, insurance, American Joint Committee on Cancer T and N stage, number of metastatic organs, surgical treatment, and chemotherapy. All these factors were used for nomogram construction. The time-dependent AUC values of the training and validation cohorts suggested a favorable performance and discrimination of the nomogram. The 6-, 12-, and 18-month AUC values were 0.706, 0.700, and 0.706 in the training cohort, and 0.702, 0.670, and 0.656 in the validation cohort, respectively. The calibration curves for the probability of death at 6, 12, and 18 months showed acceptable agreement between the values predicted by the nomogram and the observed outcomes in both cohorts. DCA curves showed good positive net benefits in the prognostic model among most of the threshold probabilities at different time points (death at 6, 12, and 18 months). Based on the total nomogram scores of each case, all patients were divided into the low-risk (n = 511), intermediate-risk (n = 512), and high-risk (n = 512) groups, and the risk classification could identify cases with a high risk of death in both cohorts. CONCLUSIONS A predictive nomogram and a corresponding risk classification system for CSD in patients with metastatic melanoma were developed in this study, which may assist in patient counseling and in guiding clinical decision making for cases with metastatic melanoma.