Skip to main content

Table 3 Classification rules of neuroblastoma patients including NB-hypo

From: Logic Learning Machine creates explicit and stable rules stratifying neuroblastoma patients

Rule IDa

 

NB-hypo

INSS Stage

MYCN Status

Age at diagnosis (Years)

 

Predicted Outcome

Covering b (%)

ErroreC (%)

Fisher pvalued

Stabilitye

3.1

IF (

High

{3,4}

_

≥1

) THEN

Poor

64

3

<0.001

0.94

3.2

IF (

High

{2,3,4}

Normal

≥1

) THEN

Poor

25

2.2

<0.001

0.8

3.3

IF (

_

{1, 3, 4, 4s}

Amplified

≥1

) THEN

Poor

50

1.5

<0.001

0.5

3.4

IF (

_

_

_

<1

) THEN

Good

65

0

<0.001

0.94

3.5

IF (

Low

_

Normal

_

) THEN

Good

89

23

<0.001

0.64

3.6

IF (

_

{1, 4s}

_

_

) THEN

Good

50

0

<0.001

0.9

3.7

IF (

_

{1, 2, 4s}

Amplified

_

) THEN

Good

1.5

0

>0.5

0.8

  1. a The Rule ID is composed by the table number followed by a dot and the rule number.
  2. b The covering is the fraction of examples in the training set that verify the rule and belong to the target class.
  3. C The error is the fraction of examples in the training set that satisfy the rule and do not belong to the target class.
  4. d Fisher p-value quantifies the statistical significance of the rule.
  5. e Stability measures the fraction of the occurrences of a given rule in a 5 rounds of 10 fold cross validations.