classifications (OCD patients vs. HC) in either pediatric, adult or combined samples was statistically significant. This is likely due to the low classification performances obtained, suggesting that the features used are either too noisy or non-informative for main diagnosis predictions and unable to achieve statistical significance and consistency across folds. Similarly, no significant features were found for medicated OCD vs. HC and unmedicated OCD vs. HC classifications. On the other hand, significant features were found that enabled multivariate classifications for medicated vs. unmedicated OCD in adult and combined samples. These included widespread cortical thickness in frontal and temporal regions, including the left inferior temporal gyrus, medial orbital frontal and bilateral transverse temporal cortex, left insula, and bilateral anterior cingulate cortex, as well as surface area of the right entorhinal, left paracentral and bilateral temporal cortex, and left thalamus, pallidum, and ventricle volumes. A full overview of these significant features, as well as those found for early vs. late onset OCD classification, can be found in supplementary Tables S10-11.
