Skip to main content
. 2020 Jun;6(2):223–230. doi: 10.18383/j.tom.2020.00017

Table 3.

Performance of Multivariate Models from Each Feature Set in the Training and Validation Cohorts

IBEX PY CIFE
ClassificationAlgorithm T V T V T V
KNN 0.620 0.54 0.66 0.54 0.67 0.60
SVM 0.59 0.48 0.57 0.52 0.60 0.51
Random Forests 0.68 0.54a 0.67 0.56a 0.68 0.64a
Bagging 0.66 0.53 0.67 0.53 0.69 0.63

aOptimal model based on validation performance from each feature set, which was random forest for all extractors. T and V columns represent AUC scores for the indicated model from the training and validation cohorts, respectively. Performance values are presented as AUC values.