Skip to main content

Table 2 An outline of the variables included in each model and the performance of each one as measured by AUC and AIC. CI; confidence interval, OR; odds ratio, AIC; Akaike Information Criterion, AUC; Area under the receiver operator curve

From: Development of a simple prediction model for tracheostomy requirement after surgical resection of medulloblastoma in children

Model

Variable Selection

Variable

Coefficient

Wald

OR

95% CI for OR

p-value

-2 log likelihood

AIC

AUC

(95% CI)

Validation AUC

Lower

Upper

Model 1

Wald backward elimination

Brainstem infiltration

-2.313

22.252

0.099

0.038

0.259

0.000

128.574

122.574

0.869 (0.804–0.934)

0.7824

Calcification

1.217

3.297

3.375

0.908

12.549

0.069

Post-operative brainstem contusion

-3.505

32.567

0.030

0.009

0.100

0.000

Model 2

Likelihood ratio backward elimination

Brainstem infiltration

-1.788

11.104

0.167

0.058

0.479

0.001

120.498

112.498

0.892 (0.838–0.946)

0.7674

Brainstem compression

− 0.911

2.784

0.402

0.138

1.173

0.095

Calcification

1.255

3.475

3.507

0.937

13.121

0.062

Post-operative brainstem contusion

-3.334

29.310

0.036

0.011

0.119

0.000

Model 3

Wald and likelihood ratio forward selection

Brainstem infiltration

-2.144

20.188

0.117

0.046

0.299

0.000

132.247

128.247

0.862 (0.794–0.930)

0.7922

Post-operative brainstem contusion

-3.067

33.114

0.047

0.016

0.132

0.000