A novel Prognostic Model for Overall Survival in Patients with melanoma

Abstract Objective The objective of this research was to develop and validate a novel prognostic model for predicting overall survival (OS) in patients diagnosed with melanoma. Methods Based on data (n = 752) from patients diagnosed with melanoma between January 2017 and December 2020 in Chongqing University Cancer Hospital in China, we randomly divided them into two cohorts: a training cohort (n = 527) and a validation cohort (n = 225) in a 7:3 ratio. We conducted logistic univariable and multivariable analysis to identify independent risk factors for OS in melanoma patients, which were then integrated into a nomogram. The nomogram was internally validated to ensure its reliabitly. The predictive effectiveness of the nomogram was assessed using receiver operating characteristic (ROC) and calibration curve. Decision curve analysis (DCA) curves were also utilized to evaluate the model’ prediction ability. Results A total of 752 melanoma patients were included in the analysis. The nomogram incorporated seven independent risk factors for melanoma patients, including age, basic-disease, surgery, tumor node metastasis (TNM), chemotherapy, interleukin2, lactate-dehydrogenase (LDH). The C-indices for OS to predict the 1-, 3-, and 5- years survival retes were 0.704 (0.643–0.766),0.742 (0.685–0.799),0.740 (0.663–0.817) in the training cohort, and 0.733 (0.647–0.818),0.714 (0.624–0.803),0.710 (0.591–0.830) in the validation cohort, respectively. The calibration curve showed a strong agreement between nomogram and actual observations for the probability of survival in both the training and validation cohorts. The calibration plots and DCA of the nomogram demonstrated excellent concordance between the predicted and actual probabilities. Conclusions We developed and validated a predictive nomogram for OS in melanoma patients. This nomogram provided a reliable and user-friendly approach to forecast the survival outcomes of individuals with melanoma. The application of this innovative model has the potential to facilitate personalized early detection and treatment strategies, thereby benefiting patients with melanoma.