Analytic tools such as multivariate pattern analysis (MVPA) enable inference at the individual-level, which may result in better discrimination3,11. MVPA techniques can be used to develop predictive models that extract common patterns from neuroimaging data to classify individuals based on their diagnosis. A major advantage of MVPA compared to traditional methods of analysis is its ability to use inter-regional correlations to detect subtle and spatially distributed effects4. Therefore, MVPA seems particularly well suited for neuroimaging analyses in OCD, as abnormalities are typically distributed across the brain12,13. Previous MVPA studies have been able to distinguish OCD patients from controls with accuracies ranging from 66–100%14. Although these results are promising, sample sizes have typically been small, limiting model performance optimization and leading to high variance in estimated accuracy, which may result in reporting optimistic or pessimistic classification rates15. In addition, most studies have been performed using data from one research center to minimize technical (e.g., scanner hardware, protocols, and diagnostic assessment) and clinical (e.g., age, medication status, disease chronicity, and severity) heterogeneity. It is therefore not clear whether the MVPA results obtained
