Skip to main content
Fig. 2 | BMC Pediatrics

Fig. 2

From: Development and validation of a diagnostic model for early differentiation of sepsis and non-infectious SIRS in critically ill children - a data-driven approach using machine-learning algorithms

Fig. 2

Graphical illustration of the backward variable selection process based on the out-of-bag area under the curve (OOB-AUC). Left panel: Area under the curve (AUC) based permutation variable importance measure (VIM) ordered by importance of included variable; the VIM is a proxy for the importance of the variable for correct outcome prediction, but has not the same meaning as classic influence measures based on distributional statistics (like effect sizes (e.g. Odds Ratios) or p values). Right panel: Areas under the curve by number of included predictor variables (as determined by out-of-bag area under the curve (OOB-AUC) procedure). Corresponding variables can be found in Additional file 1: Table S3

Back to article page

BMC Pediatrics

ISSN: 1471-2431

Contact us