Skip to main content

Table 3 Model error for the prediction of the 1–7-year GH growth response expressed in Dheight SD scores for the model group and the validation group separately: for the total group and subdivided into children born AGA or SGA.

From: The first-year growth response to growth hormone treatment predicts the long-term prepubertal growth response in children

Model group

Validation group

Total group:

n

SDres

SDstudRes

Total group:

n

SDres

SDstudRes

   1–2 year

162

0.17

1.00

   1–2 year

205

0.19

1.11

   1–3 years

97

0.29

1.00

   1–3 years

111

0.28

0.97

   1–4 years

53

0.38

1.00

   1–4 years

58

0.35

0.90

   1–5 years

34

0.43

1.00

   1–5 years

40

0.45

1.04

   1–6 years

17

0.48

1.00

   1–6 years

29

0.40

0.84

   1–7 years

7

0.57

1.00

   1–7 years

9

0.43

0.75

AGA:

   

AGA:

   

   1–2 year

125

0.17

0.99

   1–2 year

117

0.19

1.12

   1–3 years

69

0.28

0.96

   1–3 years

63

0.26

0.90

   1–4 years

39

0.39

1.02

   1–4 years

31

0.31

0.82

   1–5 years

21

0.44

1.03

   1–5 years

18

0.39

0.92

   1–6 years

8

0.45

0.95

   1–6 years

15

0.42

0.88

   1–7 years

7

0.57

1.00

   1–7 years

3

0.26

0.45

SGA:

   

SGA:

   

   1–2 year

37

0.18

1.05

   1–2 year

88

0.19

1.09

   1–3 years

28

0.31

1.08

   1–3 years

48

0.30

1.05

   1–4 years

14

0.36

0.93

   1–4 years

27

0.37

0.98

   1–5 years

13

0.41

0.96

   1–5 years

22

0.49

1.13

   1–6 years

9

0.50

1.04

   1–6 years

14

0.37

0.79

   1–7 years

0

-

-

   1–7 years

6

0.49

0.87

  1. SDres = root mean square error of the residuals.
  2. SD stud Res = SDres/SDresModelgroup
  3. For a reliable model, the SDres should be similar, or lower, for the validation group compared with the SDres from the model group.
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us