Skip to main content
. 2019 Jul;7(3):223–231. doi: 10.29252/beat-070303

Table 4.

Comparison of areas under ROCb curves

Youden’s J Sensitivitya Specificitya AUCc SEd of AUCc 95% CIe of AUCc
Model 1 0.62 0.80 0.82 0.84 0.03 0.79, 0.91  2=77.00 P <0.001
Model 2 0.56 0.80 0.76 0.83 0.03 0.78, 0.90
Model 3 0.57 0.75 0.81 0.83 0.03 0.77, 0.89
Model 4 0.07 0.11 0.96 0.49 0.05 0.40, 0.58
Model 5 0.07 0.28 0.79 0.47 0.05 0.38, 0.56
Model 6 0.18 0.60 0.58 0.59 0.04 0.52, 0.66

Model 1 covariates: ASA, age, logMorbidity POSSUM, logMortality POSSUM, surgery indication, PRB transfusion, cancer, systolic blood pressure, surgical procedure

Model 2 covariates: ASA, age, logMortality POSSUM, surgery indication, PRB transfusion, cancer, systolic blood pressure, surgical procedure

Model 3 covariates: ASA, age, logMorbidity POSSUM, surgery indication, PRB transfusion, cancer, systolic blood pressure, surgical procedure

Model 4 covariate: logMortality POSSUM

Model 5 covariate: logMorbidity POSSUM

Model 6 covariate: Osteopenia

a

At optimum cut-off point based on Youden’s J statistic;

b

ROC: Receiver operating characteristic,

c

AUC: Area under ROC curve,

d

SE: Standard error, CI: Confidence interval