S9 Table -

Classifier type robustness analysis. For each disorder, we compared the cross-validated classification performance of each model (e.g., left entorhinal cortex in Aregion) using the (1) standard linear SVM (as in our main analyses) along with (2) an additional L1-regularized SVM, (3) a radial basis function (RBF) SVM, (4) a random forest ensemble, and (5) a gradient-boosted ensemble classifier. The mean balanced accuracy is indicated for each of the five compared classifier types. (CSV)