Skip to main content

Advertisement

Table 3 Analysis of gene expression profiles in eight selected data sets of for cancer diagnosis. Comparison between five methods of supervised data mining in cross-validation

From: Analyzing gene expression data for pediatric and adult cancer diagnosis using logic learning machine and standard supervised methods

MethodSens. %Spec. %Youden Index %Empirical Accuracy %Cohen’s Kappa %p
GDS4968
 LLM98.190.288.494.791.7<  0.001
 DT96.295.193.195.793.3<  0.001
 ANN94.395.189.493.690.0<  0.001
 SVM98.197.595.797.996.7<  0.001
 kNN98.197.695.796.895.1<  0.001
GDS4887
 LLM10095.095.097.595.0<  0.001
 DT10095.095.097.595.0<  0.001
 ANN100100100100100<  0.001
 SVM100100100100100<  0.001
 kNN100100100100100<  0.001
GDS4794
 LLM100100100100100<  0.001
 DT100100100100100<  0.001
 ANN100100100100100<  0.001
 SVM100100100100100<  0.001
 kNN100100100100100<  0.001
GDS4762
 LLM100100100100100<  0.001
 DT100100100100100<  0.001
 ANN97.310097.398.897.5<  0.001
 SVM100100100100100<  0.001
 kNN100100100100100<  0.001
GDS4471
 LLM99.096.095.097.494.0<  0.001
 DT88.276.064.284.264.2<  0.001
 ANN82.488.070.484.266.3<  0.001
 SVM98.096.094.097.497.4<  0.001
 kNN94.296.090.194.788.3<  0.001
GDS4296
 LLM97.896.294.096.695.7<  0.001
 DT75.810075.863.353.1<  0.001
 ANN98.996.295.193.291.4<  0.001
 SVM100100100100100<  0.001
 kNN100100100100100<  0.001
GDS3952
 LLM96.490.387.692.289.4<  0.001
 DT94.510094.570.257.7<  0.001
 ANN97.390.387.676.667.2<  0.001
 SVM10010010095.794.2<  0.001
 kNN10010010097.296.1<  0.001
GDS3945
 LLM100100100100100<  0.001
 DT90.510090.595.290.5<  0.001
 ANN14.381.0−4.846.6−4.80.661
 SVM95.210010097.695.2<  0.001
 kNN85.795.281.090.581.0<  0.001