Skip to main content

Table 2 RNA Expression Classifier Performance

From: Machine learning with the TCGA-HNSC dataset: improving usability by addressing inconsistency, sparsity, and high-dimensionality

Datasets

Classifiers:

RF

WSRF

CIRF

AUCs

 Full RNA

0.632 ± 0.106

0.596 ± 0.038

0.629 ± 0.105

 SPCA

0.640 ± 0.128

0.626 ± 0.114

0.658 ± 0.044

Nested CV Runtimes

–

–

–

 Full RNA

52 h

185 h

85 h

 SPCA

12 min

1.9 h

30 min

  1. AUC and approximate runtime values for the RNA expression feature sets. The best value in each row is bolded. Here, runtimes are evaluation times for a given classifier on a given feature set via 10-fold nested cross validation with the internal cross validation procedures as described in Methods. Computations performed on the University of Iowa’s Argon High-Performance Computing cluster