Fig. 3
From: Artificial neural network classifier predicts neuroblastoma patients’ outcome
The plot shows the concordance between NB-hypo prediction and the clinical characteristics of the 82 patients in the external test dataset. Patients are grouped according to INSS staging. Rows represent individual patients. For each stage, the column “Prediction” indicates the prediction results of NB-hypo classifier (Poor or Good). The column “Correct” represents the correctness of NB-hypo classifier prediction (true or false). The column “Age” shows the age at diagnosis (>1 year vs. < 1 year). The column “MYCN” shows the MYCN amplification status (A = amplified; NA = not amplified). Patients marked with a clearer color are the ones predicted as “Poor” by NB-hypo classifier