Fig. 3From: Creating sparser prediction models of treatment outcome in depression: a proof-of-concept study using simultaneous feature selection and hyperparameter tuningNumber of selected features for the non-permuted models. Across both data sets and all three classifiers, the nested cross-validation pipeline with RFE (lower rows) resulted in sparser models requiring less features than the reference method without RFE (upper rows). LR, logistic regression; RF, random forest classifier; RFE, recursive feature elimination; SVC, support vector classifierBack to article page