Figure 1
From: Interrogating differences in expression of targeted gene sets to predict breast cancer outcome
Kaplan-Meier plots illustrating separation among the 1000 test data sets. Predictions were based on L 1 penalized (LASSO) Cox regression models fitted to each training set. Plots A (OS = overall survival) and B (DFS = disease free survival) represent predictions of low or high risk based on actual data, while plots C (OS) and D (DFS) represent predictions based on permuted data sets.