Electroconvulsive therapy (ECT) is the most effective intervention for patients with treatment resistant depression. A clinical decision support tool could guide patient selection to improve the overall response rate and avoid ineffective treatments with adverse effects. Initial small-scale, monocenter studies indicate that both structural magnetic resonance imaging (sMRI) and functional MRI (fMRI) biomarkers may predict ECT outcome, but it is not known whether those results can generalize to data from other centers. The objective of this study was to develop and validate neuroimaging biomarkers for ECT outcome in a multicenter setting.

Multimodal data (i.e. clinical, sMRI and resting-state fMRI) were collected from seven centers of the Global ECT-MRI Research Collaboration (GEMRIC). We used data from 189 depressed patients to evaluate which data modalities or combinations thereof could provide the best predictions for treatment remission (HAM-D score ⩽7) using a support vector machine classifier.

Remission classification using a combination of gray matter volume and functional connectivity led to good performing models with average 0.82–0.83 area under the curve (AUC) when trained and tested on samples coming from the three largest centers (N = 109), and remained acceptable when validated using leave-one-site-out cross-validation (0.70–0.73 AUC).

These results show that multimodal neuroimaging data can be used to predict remission with ECT for individual patients across different treatment centers, despite significant variability in clinical characteristics across centers. Future development of a clinical decision support tool applying these biomarkers may be feasible.

Major depressive disorder (MDD) has been related to structural brain characteristics that are correlated with the severity of disease. However, the correlation of these structural changes is less well clarified in treatment-resistant depression (TRD).

To summarise the existing literature on structural brain characteristics in TRD to create an overview of known abnormalities of the brain in patients with MDD, to form hypotheses about the absence or existence of a common pathophysiology of MDD and TRD.

A systematic search of PubMed and the Cochrane Library for studies published between 1998 and August of 2016 investigating structural brain changes in patients with TRD compared with healthy controls or patients with MDD.

Fourteen articles are included in this review. Lower grey matter volume (GMV) in the anterior cingulate cortex, right cerebellum, caudate nucleus, superior/medial frontal gyrus and hippocampus does not seem to differentiate TRD from milder forms of MDD. However, lower GMV in the putamen, inferior frontal gyrus, precentral gyrus, angular- and post-central gyri together with specific mainly parietal white matter tract changes seem to be more specific structural characteristics of TRD.

The currently available data on structural brain changes in patients with TRD compared with milder forms of MDD and healthy controls cannot sufficiently distinguish between a ‘shared continuum hypothesis’ and a ‘different entity hypothesis’. Our review clearly suggests that although there is some overlap in affected brain regions between milder forms of MDD and TRD, TRD also comes with specific alterations in mainly the putamen and parietal white matter tracts.

None.