Table 2

Performance of classification algorithms for the van 't Veer et al. breast cancer genomic data based on 20 repetitions of 10-fold CV

Algorithm

Accuracy

Sensitivity*

Specificity^†

PPV^‡

NPV^§

CERP

62.3 (.023)

50.9 (.037)

71.1 (.026)

57.7 (.029)

65.2 (.020)

RF

62.5 (.019)

46.8 (.032)

74.7 (.032)

58.9 (.029)

64.5 (.014)

AdaBoost

58.8 (.041)

32.1 (.089)

79.4 (.069)

55.0 (.094)

60.3 (.028)

SVM

56.5 (.029)

39.6 (.053)

69.7 (.027)

50.1 (.042)

59.9 (.025)

DLDA

62.5 (.019)

52.4 (.023)

70.3 (.026)

57.8 (.026)

65.6 (.015)

SC

60.9 (.019)

50.6 (.026)

68.9 (.023)

55.7 (.024)

64.3 (.016)

CART

54.6 (.028)

17.5 (.058)

83.2 (.047)

44.6 (.084)

56.6 (.018)

CRUISE

55.1 (.048)

21.5 (.100)

81.0 (.059)

45.6 (.112)

57.3 (.034)

QUEST

56.5 (.044)

22.8 (.080)

82.6 (.077)

51.0 (.117)

58.1 (.027)

SD is given in parentheses. *Poor prognosis considered positive. ^†Good prognosis considered negative. ^‡Positive predictive value. ^§Negative predictive value.

Moon et al. Genome Biology 2006 7:R121   doi:10.1186/gb-2006-7-12-r121