Klin Padiatr 2013; 225 - A3
DOI: 10.1055/s-0033-1343620

Prediction of minimal residual disease in pediatric ALL: Evaluation of the predictive potential of the variables from the ALL-BFM 2000 trial

A Torge 1, M Zimmermann 2, A Möricke 1, R Köhler 3, A Schrauder 1, CR Bartram 3, M Schrappe 1, M Stanulla 1
  • 1Department of Pediatrics, University Hospital Schleswig-Holstein, Kiel
  • 2Pediatric Hematology and Oncology, Hannover Medical School, Hannover
  • 3Department of Human Genetics, University of Heidelberg, Heidelberg, Germany

In pediatric acute lymphoblastic leukemia (ALL), the most important prognostic factor for the risk of relapse is the evaluation of minimal residual disease (MRD) at defined timepoints. The results of MRD analyses are not available at diagnosis to guide selection of the optimal treatment intensity already early on.

In trial ALL BFM 2000, multi-level patient data were collected and are now used to develop neural networks to predict MRD. For this task, the careful selection of as few as possible input data regarding computing time is indispensable.

Selected variables and resulting neural networks are tested regarding their capability to accurately predict MRD.