Skip to main content

Table 7 Variables entered and removed (in square brackets) at each step of the stepwise selection procedure

From: A comparative analysis of predictive models of morbidity in intensive care unit after cardiac surgery – Part II: an illustrative example

Step no.

BL

BQ

k NN

LR

HS

DS

ANN1

ANN2

1

O2ER

O2ER

Post-CI

O2ER

O2ER

SvO2

O2ER

O2ER

2

VCO2

DO2I

O2ER

VCO2

VCO2

Card-ID

Card-ID

VO2

3

Card-ID

Card-ID

Card-ID

Card-ID

Card-ID

DO2I

VO2

Card-ID

4

PVD

PVD

PVD

PVD

PVD

O2ER

PVD

PVD

5

TBU

W

TBU

TBU

TBU

PVD

TBU

Gly

6

EM

VD

MAP

EM

EM

O2ER

Pre-CI

Gender

7

Pre-CI

DAP

 

SAP

SAP

EM

EM

MVR

8

WBC

SAP

 

Pre-CI

Pre-CI

BSA

WBC

Cr

9

SAP

Diur

 

WBC

WBC

AD

Age

AVO2

10

Age

Xclamp

 

SaO2

SaO2

CHF

SaO2

Arrhy

11

PvO2

H

 

PvO2

PvO2

MVR

AD

 

12

SaO2

Gender

 

AD

AD

O2ER

P/F

 

13

AD

  

PaO2

PaO2

MR

PVS

 

14

SvO2

  

Cr

Cr

EM

Temp

 

15

Xclamp

  

CvO2

CvO2

Card-ID

  

16

PaO2

  

Xclamp

Xclamp

O2ER

  

17

[PvO2]

  

DO2I

DO2I

PVD

  

18

Cr

  

W

W

Diab

  

19

Intra-CI

  

SVRI

SVRI

VCO2

  

20

Post-CI

  

[VCO2]

[VCO2]

O2ER

  

21

[Age]

  

Pre-IABP

Pre-IABP

AD

  

22

W

  

CHF

CHF

O2ER

  

23

[Pre-CI]

  

[Xclamp]

[Xclamp]

CHF

  

24

DO2I

    

CABG-C

  

25

[VCO2]

    

MR

  

26

Bil

    

PAH

  

27

Hb

    

O2ER

  

28

[WBC]

    

IABP

  

29

SVRI

    

O2ER

  

30

[Post-CI]

    

IABP

  

31

BSA

    

O2ER

  

32

CABG-A

    

PVS

  

33

     

IABP

  

34

     

O2ER

  

35

     

IABP

  
  1. BL, Bayes linear model; BQ, Bayes quadratic model; k NN, k-nearest neighbour model; LR, logistic regression model; HS, Higgins score system; DS, direct score system; ANN1, one-layer artificial neural network; ANN2, two-layer artificial neural network. Predictor variable abbreviations are indicated in Tables 1-6.