For a study, researchers downloaded the clinical data of 597 patients from the Therapeutically Applicable Research to Generate Effective Treatments (TARGET) database as a training set and included 189 patients from the center as a validation set to develop a personal prognostic model and change the risk stratification of pediatric acute myeloid leukemia.

Age at diagnosis, -7/del(7q) or -5/del(5q), core binding factor fusion genes, FMS-like tyrosine kinase 3-internal tandem duplication (FLT3-ITD)/nucleophosmin 1 (NPM1) status, Wilms tumor 1 (WT1) mutation, and biallelic CCAAT enhancer binding protein alpha (CEBPA) mutation were strongly correlated with overall survival in the With a Harrell’s concordance value of 0.68, a 3-year and 5-year area under the receiver operating characteristic curve of 0.71 and 0.72; respectively, the prognostic model showed strong discriminative performance.

The model performed better than other prognostic systems in the validation set when it was validated. The approach successfully identified candidates for hematopoietic stem cell transplantation, and patients were divided into 3 risk categories (low, moderate, and high risk) with considerably different prognoses. The recently created prognostic model showed strong capability and value in risk classification and survival prediction, which might be useful in changing therapy choices in ordinary clinical practice.