Gene array prediction of AML transformation in MDS

Microarray-based classifiers and prognosis models identify subgroups with distinct clinical outcomes and high risk of AML transformation of myelodysplastic syndrome (MDS) An array-based Diagnostic Classifier (DC) model, developed for and evaluated during the MILE study, correctly identified ~50% of the unfractionated MDS specimens submitted to the study; predictions for the other samples were split between “none-of-the-targets” classes and AML signatures, but this distinction also reflected clinical outcome in terms of time to AML transformation. Furthermore, an improved Prognostic Classifier (PC) model was developed that correlated with both time to AML transformation and overall survival. Keywords: Microarray-based gene expression profiling aimed at prediction of AML transformation in MDS 164 MDS, 202 AML and 69 non-leukemia bone marrow samples were hybridized to Affymetrix HG-U133 Plus 2.0 GeneChips. This dataset is a subset of the MILE Study (Microarray Innovations In LEukemia) program, headed by the European Leukemia Network (ELN) and sponsored by Roche Molecular Systems, Inc.