Enhancing survival prognostication in patients with choroidal melanoma by integrating pathologic, clinical and genetic predictors of metastasis

Survival in choroidal melanoma was modelled using accelerated failure time models. We combined pathological, clinical and genetic data, using imputation techniques. Performance was assessed using n-fold cross-validation. Using data from 3653 patients, we generated two models; the first using clinical data only and the second using clinical and laboratory data. The c-index of discrimination was 0.75 for the clinical model and 0.79 for the laboratory model. Calibration showed good correlation between predicted and observed mortality (p-value: 0.699 for clinical model and 0.801 for laboratory model). We conclude that our model provides reasonably reliable prognosis relevant to individual patients.