Skip to main content
. 2020 Sep 30;15(9):e0239536. doi: 10.1371/journal.pone.0239536

Fig 4. Discrimination and calibration of prediction models in external validation.

Fig 4

a) 7-day mortality: Receiver operator characteristic (ROC) curve for discrimination. Area under the curve (AUC) = 0.851 (95%CI 0.781–0.921). b) 7-day mortality: Calibration plot of observed versus predicted risk of mortality (Hosmer-Lemeshow chi-squared = 9.03, p = 0.340; DF = 8). c) 14-day mortality: Receiver operator characteristic (ROC) curve for discrimination. Area under the curve (AUC) = 0.825 (95%CI 0.764–0.887). d) 14-day mortality: Calibration plot of observed versus predicted risk of mortality (Hosmer-Lemeshow chi-squared = 7.63, p = 0.471; DF = 8).