Institutes
Refine
Year of publication
- 2023 (2)
Language
- English (2) (remove)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- Connectomics (1)
- Electroconvulsive Therapy (1)
- Major Depressive Disorder (1)
- Plasticity (1)
Institute
- Medizin (2)
Background: This study investigates (1) whether alterations in magnetic resonance imaging (MRI)-based structural global network organization is impaired in patients with major depressive disorder (MDD), (2) whether in-patient treatment including pharmacological, psychological and neurostimulation interventions is linked to changes in structural brain connectivity and (3) whether brain structural changes relate to changes in depression symptomatology.
Methods: One hundred seventy-eight subjects – 109 subjects diagnosed with current MDD and 55 healthy controls (HC) - participated in the present study (baseline + 6-weeks follow up). Fifty-six depressed patients were treated with electroconvulsive therapy (ECT) and 67 received in-patient treatment without ECT. Here, grey matter T1-weighted MRI was used to define nodes and DWI-based tractography to define the connections – or edges – between the nodes creating a structural connectome. Changes over time in depressions symptom severity was measured with the Hamilton Depression Ratings Scale.
Results: MDD patients showed reduced connectivity strength at baseline compared to healthy controls. MDD patients showed a significant increase of connectivity strength over time, an effect that was not detected in HC. An increase of connectivity strength was associated with a decrease in depression symptom severity. These effects were independent of treatment choice, suggesting a nonspecific effect that cannot be traced back to ECT.
Conclusion: We demonstrate an alleviation of structural brain dysconnectivity in MDD patients after successful antidepressive treatment, which is most prominent in those patients that show the greatest reduction in depressive symptomatology. This pattern of results suggests neuroplastic mechanisms involved in the successful treatment of depression and should be investigated as a potential treatment target in future studies.
Research Category and Technology and Methods: Clinical Research: 2. Electroconvulsive Therapy (ECT)
Background: Biological psychiatry aims to understand mental disorders in terms of altered neurobiological pathways. However, for one of the most prevalent and disabling mental disorders, Major Depressive Disorder (MDD), patients only marginally differ from healthy individuals on the group-level. Whether Precision Psychiatry can solve this discrepancy and provide specific, reliable biomarkers remains unclear as current Machine Learning (ML) studies suffer from shortcomings pertaining to methods and data, which lead to substantial over-as well as underestimation of true model accuracy.
Methods: Addressing these issues, we quantify classification accuracy on a single-subject level in N=1,801 patients with MDD and healthy controls employing an extensive multivariate approach across a comprehensive range of neuroimaging modalities in a well-curated cohort, including structural and functional Magnetic Resonance Imaging, Diffusion Tensor Imaging as well as a polygenic risk score for depression.
Findings Training and testing a total of 2.4 million ML models, we find accuracies for diagnostic classification between 48.1% and 62.0%. Multimodal data integration of all neuroimaging modalities does not improve model performance. Similarly, training ML models on individuals stratified based on age, sex, or remission status does not lead to better classification. Even under simulated conditions of perfect reliability, performance does not substantially improve. Importantly, model error analysis identifies symptom severity as one potential target for MDD subgroup identification.
Interpretation: Although multivariate neuroimaging markers increase predictive power compared to univariate analyses, single-subject classification – even under conditions of extensive, best-practice Machine Learning optimization in a large, harmonized sample of patients diagnosed using state-of-the-art clinical assessments – does not reach clinically relevant performance. Based on this evidence, we sketch a course of action for Precision Psychiatry and future MDD biomarker research.