Fig. 3: Performance of the models in internal and external test cohorts. | npj Digital Medicine

Fig. 3: Performance of the models in internal and external test cohorts.

From: Unlocking the potential of real-time ICU mortality prediction: redefining risk assessment with continuous data recovery

Fig. 3

a–c Display the area under the receiver operating characteristic curve (AUC) for the internal test cohort (eICU-CRD), and for the external test cohorts (MIMIC and SICdb), respectively. d–f Present the calibration curves for the same cohorts. Panels (g–i) show the decision curve analysis (DCA) results for the internal and two external cohorts, respectively. eICU-CRD eICU Collaborative Research Database, MIMIC Medical Information Mart for Intensive Care, SICdb Salzburg Intensive Care Database, AUC area under the receiver operating characteristic curve, DCA decision curve analysis, NEWS National Early Warning Score, MEWS Modified Early Warning Score, SOFA sequential organ failure assessment, APACHE acute physiology and chronic health evaluation.

Back to article page