Skip to main content

Table 6 ANN prediction based on 30 blinded samples in the melanoma data set

From: A simpler method of preprocessing MALDI-TOF MS data for differential biomarker analysis: stem cell and melanoma cancer studies

 

50 ANN sub-models

    

Sample label

S2

S3

ANN output

Std err in 95% CI

ANN classification

Target output

Blind 1

50

0

0

0

S2

S2

Blind 2

50

0

0

0

S2

S2

Blind 3

50

0

0

0

S2

S2

Blind 4

50

0

0

0

S2

S2

Blind 5

0

50

1

0

S3*

S2

Blind 6

40

10

0.200

0.115

S2

S2

Blind 7

50

0

0

0

S2

S2

Blind 8

50

0

0

0

S2

S2

Blind 9

46

4

0.080

0.078

S2

S2

Blind 10

50

0

0

0

S2

S2

Blind 11

42

8

0.160

0.106

S2

S2

Blind 12

47

3

0.060

0.069

S2

S2

Blind 13

50

0

0

0

S2

S2

Blind 14

49

1

0.020

0.040

S2

S2

Blind 15

0

50

1

0

S3*

S2

Blind 16

0

50

1

0

S3

S3

Blind 17

0

50

1

0

S3

S3

Blind 18

0

50

1

0

S3

S3

Blind 19

0

50

1

0

S3

S3

Blind 20

0

50

1

0

S3

S3

Blind 21

5

45

0.900

0.087

S3

S3

Blind 22

0

50

1

0

S3

S3

Blind 23

0

50

1

0

S3

S3

Blind 24

5

45

0.900

0.087

S3

S3

Blind 25

0

50

1

0

S3

S3

Blind 26

0

50

1

0

S3

S3

Blind 27

0

50

1

0

S3

S3

Blind 28

0

50

1

0

S3

S3

Blind 29

0

50

1

0

S3

S3

Blind 30

0

50

1

0

S3

S3

  1. S2 refers to the stage 2 of melanoma. S3 is the stage 3 of melanoma. ANN output is computed based on the average performance from 50 random samplings. Std err with 95% CI refers to the standard error for ANN output in 95% confident interval range. ANN classification indicates the final outcome of the model. Target output refers to the original group to which the sample belongs to.