Skip to main content

Table 2 Accuracya of elastic net-regularized models for the prediction of extra-prostatic extension (EPE).

From: Computational purification of individual tumor gene expression profiles leads to significant improvements in prognostic prediction

Classifier input Average accuracy, %
Unpurified expression profiles 61.76 ± 1.64
ISOpure cancer expression profiles 69.12 ± 0.90
Matrix factorization estimates 62.94 ± 0.57
Clarke cancer expression profiles 62.50 ± 1.06
  1. aThe average accuracy and standard error of the mean over ten 10-fold cross-validation runs are reported for logistic regression classifiers trained using either the original unpurified profiles, ISOpure cancer profiles, matrix factorization mixing proportions, or Clarke cancer profiles.