Aim
The purpose of this study is to develop and validate a prediction model of overall survival (OS) in choroidal melanoma patients.
Methods
A total of 3415 patients with choroidal melanoma from 2004 to 2015 were collected from the Surveillance, Epidemiology, and End Results database. A novel nomogram was built based on independent risk factors evaluated by Cox proportional hazards regression model. And internal validations were performed to assess the performance of our nomogram by concordance index (C-index), calibration plot and decision curve analysis (DCA).
Results
Seven factors (age at diagnosis, race, sex, American Joint Committee for Cancer (AJCC) primary tumor (T) category, histological type, marital status and total number of primary tumors) were prognostic factors of OS. These factors were used to conduct a prediction model. The predictive accuracy of the nomogram for the OS has been stable at about 0.72 from 36 to 60 months evaluated by C-index. The calibration plots showed that the OS was also consistent between prediction and actual observation. Moreover, the DCA indicated our nomogram had better net benefit than the T-category.
Conclusion
The nomogram predicting the OS of choroidal melanoma may assist clinicians to decide treatment options individually.