Table 2

Classification results of the LDA-based classifiers included in the different versions of the INTERPRET DSS.

Version

Classifier

TE

Accuracy with training set

Classifier tested with a test set

Number of cases in the test set

Accuracy with test set


1.1

MCTT

Short

94.00%

yes

87

85.05%


2.0

MCTT

Short

88.94%

no

-

-


2.0

MCTT

Long

82.56%

no

-

-


3.0

MCTT

Short

89.00%

yes

63

82.54%


3.0

MCTT

Long

84.20%

yes

63

69.84%


3.0

MCTT

Short+Long

89.20%

yes

63

82.54%


3.0

T vs.PS

Short

85.50%

yes

19

78.95%


3.0

T vs.PS

Long

81.10%

yes

19

84.21%


3.0

T vs.PS

Short+Long

92.10%

yes

19

78.95%


MCTT: Most common tumour types; T vs.PS: Tumour vs. pseudotumoural disease. Summary of classifiers released.

PĂ©rez-Ruiz et al. BMC Bioinformatics 2010 11:581   doi:10.1186/1471-2105-11-581

Open Data