Multivariable prognostic model: external validation and model recalibration with application to non-metastatic renal cell carcinoma

To define a useful prognostic model is not sufficient to show that it accurately predicts outcome in the initial development data, but evidence is necessary that the model performs well also in other groups of individuals. External validation tests the accuracy of the system in a different setting to assess the transportability and generalizability of the model. Different measures are available to test model accuracy in term of discrimination...