Skip to main content

Table 4 Performance of multivariable models for the prediction of death, ICU or complication in CAP patients (n = 925)

From: Prohormones for prediction of adverse medical outcome in community-acquired pneumonia and lower respiratory tract infections

Endpoint

Model

Bootstrap-corrected accuracy measure

Leave-one-hospital-out cross-validation

Accuracy calculated on left out hospital

   

Mean

Range

Serious complication*

CURB covariates

   
 

-AUC

0.75

0.75

0.67 to 0.83

 

-Brier score

0.11

0.11

0.09 to 0.15

 

CURB covariates + proADM

   
 

-AUC

0.76

0.76

0.72 to 0.81

 

-Brier score

0.10

0.11

0.09 to 0.14

 

CURB covariates + all biomarkers

   
 

-AUC

0.76

0.76

0.71 to 0.81

 

-Brier score

0.11

0.11

0.09 to 0.14

Death

CURB covariates

   
 

-AUC

0.80

0.81

0.72 to 0.87

 

-Brier score

0.05

0.05

0.03 to 0.07

 

CURB covariates + proADM

   
 

-AUC

0.81

0.82

0.71 to 0.87

 

-Brier score

0.05

0.05

0.03 to 0.07

 

CURB covariates + all biomarkers

   
 

-AUC

0.80

0.81

0.72 to 0.88

 

-Brier score

0.05

0.05

0.03 to 0.07