Fig. 4From: Integrating multiple molecular sources into a clinical risk prediction signature by extracting complementary informationVariability of the.632+ prediction error estimates in the first AML application based on varying overlap sizes of 26, 15 and 10 biological samples, respectively. Integrated prediction error curve estimates for the Cox model, the reference approach and the sequential complementary strategy. The performance of the Kaplan-Meier benchmark is indicated by a horizontal lineBack to article page