Fig. 2From: Creating sparser prediction models of treatment outcome in depression: a proof-of-concept study using simultaneous feature selection and hyperparameter tuningModel performances for the three classifiers and the two data sets on the validation data. Matthews correlation coefficients are shown for the 100 permutations (annotations correspond to the respective means) as well as for the models with and without RFE. LR, logistic regression; RF, random forest classifier; RFE, recursive feature elimination; SVC, support vector classifierBack to article page