Major depressive disorder (MDD) is a complex psychiatric disorder that affects the lives of hundreds of millions of individuals around the globe. Even today, researchers debate if morphological alterations in the brain are linked to MDD, likely due to the heterogeneity of this disorder. The application of deep learning tools to neuroimaging data, capable of capturing complex non-linear patterns, has the potential to provide diagnostic and predictive biomarkers for MDD. However, previous attempts to demarcate MDD patients and healthy controls (HC) based on segmented cortical features via linear machine learning approaches have reported low accuracies. In this study, we used globally representative data from the ENIGMA-MDD working group containing 7012 participants from 31 sites (N = 2772 MDD and N = 4240 HC), which allows a comprehensive analysis with generalizable results. Based on the hypothesis that integration of vertex-wise cortical features can improve classification performance, we evaluated the classification of a DenseNet and a Support Vector Machine (SVM), with the expectation that the former would outperform the latter. As we analyzed a multi-site sample, we additionally applied the ComBat harmonization tool to remove potential nuisance effects of site. We found that both classifiers exhibited close to chance performance (balanced accuracy DenseNet: 51%; SVM: 53%), when estimated on unseen sites. Slightly higher classification performance (balanced accuracy DenseNet: 58%; SVM: 55%) was found when the cross-validation folds contained subjects from all sites, indicating site effect. In conclusion, the integration of vertex-wise morphometric features and the use of the non-linear classifier did not lead to the differentiability between MDD and HC. Our results support the notion that MDD classification on this combination of features and classifiers is unfeasible. Future studies are needed to determine whether more sophisticated integration of information from other MRI modalities such as fMRI and DWI will lead to a higher performance in this diagnostic task.
Social anxiety disorder (SAD) is among the most prevalent anxiety disorders, and it has been associated with signs of advanced biological ageing. Despite this, brain age research on anxiety disorders remains limited. This mega-analysis investigated brain ageing in adults with SAD within the ENIGMA-Anxiety Working Group. Structural MRI scans from 576 participants with SAD and 1 355 non-affected healthy controls (HCs) across 26 international samples were included. Brain age was estimated from 77 cortical and subcortical regions using a publicly available ENIGMA brain age model. The brain-predicted age difference (brain-PAD) was calculated as the difference between brain age and chronological age. Group and subgroup differences (comorbidity, medication) were assessed using linear mixed-effect models. In the full sample, there was no group difference in brain-PAD ( β diagnosis (SE)=0.70 (0.37) years, p =0.061). In a subgroup of participants with SAD with comorbid anxiety disorders (n=184 SAD, n=1 355 HCs), a brain-PAD of +2.39 (0.93) years (Cohen’s d =0.23, p FDR=0.003) was observed. This brain-PAD became smaller after exclusion of participants with comorbid agoraphobia and specific phobia, suggesting that these disorders may partly drive the advanced brain-PAD. In conclusion, this ENIGMA-Anxiety mega-analysis did not find evidence of advanced brain ageing in the full sample of adult participants with SAD relative to HCs. However, a sub-analysis suggested that SAD with co-occurring phobic disorders, or the phobic disorders themselves, are associated with neurostructural patterns typical of older brains. Future research could utilise transdiagnostic samples with information on age of onset and disorder duration to further clarify this relation.