Fig. 4From: Prognosis of lasso-like penalized Cox models with tumor profiling improves prediction over clinical data alone and benefits from bi-dimensional pre-screeningC-index obtained after pre-screening for the 16 cancers and the convex penalization methods studied (i.e. ridge, lasso, elastic net, adaptive elastic net). In each case, we computed the C-index by 10 repetitions of a nested 5-fold cross validation (section Suggested screening algorithm)Back to article page