its use in clinical practice16,17. Thus, whereas small monocenter studies focus on answering a specific question about their patient population, large multicenter studies assume that a fundamental pattern of the disorder of interest can be detected despite the presence of heterogeneity, and both are geared toward answering complementary questions about a particular disorder18,39. Our LOSO-CV results demonstrated that structural MRI features do not provide a biomarker that enables generalization to new sites.
