Figure 1

NB-MuSE-classifier construction. Workflow of the steps involved in the construction of the NB-MuSE classifier merging the information of 20 signatures matched to the optimal paradigm for outcome classification. The process can be subdivided into three main phases: 1) single signature classifiers generation, 2) classifiers filtering on performance features and, 3) Neuroblastoma Multi-Signature Ensemble classifier (NB-MuSE-classifier) training and validation. The dataset was subdivided into three different subsets: DS1(60 patients) to train the signatures, DS2 (60 patients) to externally validate single-signature classifiers and to train the NB-MuSE-classifier, and DS3(62 patients) to externally validate the NB-MuSE-classifier. The products of the procedure are indicated on the right side of the figure. 60 fold cross validation refers to leave one out cross-validation (LOOCV).