I have a dataset with 1500 patients for which I want to predict the outcome of death. I wanted to utilize multivariate cox-regression in a model containing biomarkers and other covariates. I was told to use the C-statistic, NRI and IDI to evaluate the model performance on classification. I am not quite sure how to approach these classification methods in the framework of glmnnet and regularized Cox-regression.
There have been serious criticisms of IDI and NRI. And the $c$-index is not sensitive enough for comparing two models. I like to use measures that apply to any model and are very efficient. See here for several efficient and simple measures to choose from.