Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: Integrating multiple molecular sources into a clinical risk prediction signature by extracting complementary information

Fig. 1

Flowchart describing the sequential complementary strategy based on a stepwise procedure (notation focuses on the first AML application combining GEP and SNP data). Established clinical predictors (clin) that need to be adjusted for are considered as mandatory in the stepwise procedure based on componentwise likelihood-based boosting. Important clinical predictors are available for all AML cases. The SNP signature (\(\hat {\eta }_{i}^{SNP}\)) including the known SNP signature (overlap samples) from model (1) and the predicted SNP signature (non-overlap samples) considering continuous response linear regression (3) as prediction technique is incorporated as fixed offset in model (2) for the microarray-based GEP data

Back to article page