Skip to main content

Table 2 Performance of the models for predicting hospital mortality; N = 36,632 patients

From: Mortality prediction by SOFA score in ICU-patients after cardiac surgery; comparison with traditional prognostic–models

Models

AUC (CI 95%)*

Brier score (CI 95%)

Ĉ-statistic (CI)*

Ĉ-statistic p-value

APACHE IV – model

0.851 (0.851–0.851)

0.019 (0.019–0.019)

27.0 (24.1–36.4)

<  0.0001

APACHE II – model

0.830 (0.830–0.830)

0.020 (0.19–0.20)

16.3 (12.6–24.8)

0.0308

SOFA - model

0.809 (0.808–0.810)

0.020 (0.019–0.20)

43.7 (31.5–61.1)

<  0.0001

SAPS-II - model

0.850 (0.850–0.850)

0.019 (0.019–0.019)

19.4 (11.0–33.5)

0.009

MPM24-II - model

0.801 (0.801–0.801)

0.020 (0.20–0.020)

30.3 (28.7–37.6)

<  0.0001

  1. *AUC: area under the receiver operating characteristic curve; Ĉ-statistic: Hosmer and Lemeshow goodness-of-fit Ĉ-statistic; CI: 95% confidence interval
Back to article page

BMC Anesthesiology

ISSN: 1471-2253

Contact us