Development and validation of prognostic nomogram in patients with nonmetastatic malignant melanoma: a SEER population-based study.

BACKGROUND The condition of tumor recurrence and overall death can be worried in the progress of nonmetastatic malignant melanoma (NMMM). Our goal was to construct and validate a prognostic nomogram from a large population database, which is vital for physicians to predict the 3- and 5-year overall survival (OS) rates of patients with NMMM. METHODS According to the Surveillance, Epidemiology, and End Results (SEER) program, patients were collected and randomly assigned into the training and validation cohorts. Several independent risk factors were identified based on the methods of univariable and multivariable cox hazards regression and were incorporated to develop a nomogram. The concordance index (C-index), the area under the receiver operating characteristics (AUC) curve and calibration plot were confirmed to assess predictive power of the nomogram. Decision curve analysis (DCA) was performed to measure nomogram for the clinical practice. RESULTS A total of 66192 eligible patients, randomly assigned into 70% of training (n = 46 336) and 30% of validation cohorts (n = 19 856), were selected in this study. The selected independent factors were applied to develop a nomogram, and validated indexes indicated nomogram had a good discrimination ability. The C-index for OS rates was 0.817 (95% CI: 0.811-0.823) in training cohort and 0.817 (95% CI: 0.809-0.825) in validation cohort, respectively. The AUCs of 3- and 5-year OS rates were more than 0.79, and the calibration plots also showed a good power for the nomogram. DCA demonstrated that constructed nomogram can provide clinical net benefit. CONCLUSION We constructed a novel nomogram that more accurately and comprehensively predict OS with nonmetastatic malignant melanoma patients, which is vital for clinician to improve individual treatment, make reasonable clinical decisions, and set appropriate follow-up strategies.