Skip to main content

Table 4 assessment of the predictive power of the composite models using the 100-gene profile

From: Gene expression profiling of breast cancer survivability by pooled cDNA microarray analysis using logistic regression, artificial neural networks and decision trees

Prediction model

ACC

AUC

 

Training sample

Test sample

Δ(Difference)

Training sample

Test sample

Δ(Difference)

DL

75.60

68.90

6.69

77.59

61.66

15.93

DA80

72.69

69.30

3.39

71.92

64.20

7.72

DA100

89.91

65.91

22.56

87.74

61.65

26.10

  1. Abbreviations: ACC, ACCuracy; AUC, Area Under the Curve; DL, Decision Tree combined with Logistic regression; DA80, Decision tree combined with Artificial neural network using 80% resampling set (over-training prevention); DA100, Decision tree combined with Artificial neural network using 100% resampling set (without over-training prevention).
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us