Figure 1

Classification tree from the derivation cohort (n = 220). The classification tree consists of five biomarker-based decision rules and ten daughter nodes. The classification tree includes five of the twelve candidate stratification biomarkers: C-C chemokine ligand 3 (CCL3), heat shock protein 70 kDa 1B (HSPA1B), interleukin-8 (IL8), elastase 2 (ELA2), and lipocalin 2 (LCN2). Each node provides the total number of subjects in the node, the biomarker serum concentration-based decision rule, and the number of survivors and non-survivors with the respective rates. For consistency, the serum concentrations of all stratification biomarkers are provided in pg/ml. Terminal nodes 5, 8, and 9 are considered low-risk nodes, whereas terminal nodes 2, 4, 10 are considered high-risk terminal nodes. To calculate the diagnostic test characteristics, all subjects in the low-risk terminal nodes (n = 171) were classified as predicted survivors, whereas all subjects in the high-risk terminal nodes (n = 49) were classified as predicted non-survivors. The area under the curve (AUC) for the derivation cohort tree was 0.885.