Development and validation of a nomogram for predicting overall survival in patients with lower extremity melanoma: based on the Surveillance, Epidemiology, and End Results (SEER) database

Abstract

Lower extremity melanoma (LEM) is a relatively common malignant tumor with a poor prognosis. This study aims to identify prognostic factors and develop a nomogram model to predict overall survival (OS) in patients with LEM. A total of 4257 LEM patients were selected from the Surveillance, Epidemiology, and End Results (SEER) database and randomly divided into a training set (2979 cases) and a validation set (1278 cases). In the training set, univariate and multivariate Cox regression analyses were conducted to identify independent prognostic factors associated with patient outcomes, and a nomogram model was constructed. The model’s validity was then assessed by generating ROC curves, C-index, clinical decision curve analysis (DCA), and calibration curves, and validated using the validation set. Multivariate Cox regression analysis in the training set revealed that age, gender, AJCC stage, AJCC.M, Breslow thickness, radiotherapy, mitotic rate, ulceration, first malignant primary indicator, and marital status were independent variables associated with OS. In both the training and validation sets, the area under the curve (AUC) for predicting 1-year, 3-year, and 5-year OS was 0.887, 0.868, and 0.859, and 0.859, 0.872, and 0.848, respectively. The C-index, calibration curves, and DCA demonstrated good agreement in both the training and validation sets. In this study, we developed and validated a nomogram to predict OS in patients with LEM, demonstrating good reliability and clinical applicability.