Wüthrich F, Lefebvre S, Mittal VA, Shankman SA, Alexander N, Brosch K, Flinkenflügel K, Goltermann J, Grotegerd D, Hahn T, Jamalabadi H, Jansen A, Leehr EJ, Meinert S, Nenadić I, Nitsch R, Stein F, Straube B, Teutenberg L, Thiel K, Thomas-Odenthal F, Usemann P, Winter A, Dannlowski U, Kircher T, Walther S (in press). The neural signature of psychomotor disturbance in depression. Mol Psychiatry. (full article)
Abstract:
Up to 70% of patients with major depressive disorder present with psychomotor disturbance (PmD), but at the present time understanding of its pathophysiology is limited. In this study, we capitalized on a large sample of patients to examine the neural correlates of PmD in depression. This study included 820 healthy participants and 699 patients with remitted (n = 402) or current (n = 297) depression. Patients were further categorized as having psychomotor retardation, agitation, or no PmD. We compared resting-state functional connectivity (ROI-to-ROI) between nodes of the cerebral motor network between the groups, including primary motor cortex, supplementary motor area, sensory cortex, superior parietal lobe, caudate, putamen, pallidum, thalamus, and cerebellum. Additionally, we examined network topology of the motor network using graph theory. Among the currently depressed 55% had PmD (15% agitation, 29% retardation, and 11% concurrent agitation and retardation), while 16% of the remitted patients had PmD (8% retardation and 8% agitation). When compared with controls, currently depressed patients with PmD showed higher thalamo-cortical and pallido-cortical connectivity, but no network topology alterations. Currently depressed patients with retardation only had higher thalamo-cortical connectivity, while those with agitation had predominant higher pallido-cortical connectivity. Currently depressed patients without PmD showed higher thalamo-cortical, pallido-cortical, and cortico-cortical connectivity, as well as altered network topology compared to healthy controls. Remitted patients with PmD showed no differences in single connections but altered network topology, while remitted patients without PmD did not differ from healthy controls in any measure. We found evidence for compensatory increased cortico-cortical resting-state functional connectivity that may prevent psychomotor disturbance in current depression, but may perturb network topology. Agitation and retardation show specific connectivity signatures. Motor network topology is slightly altered in remitted patients arguing for persistent changes in depression. These alterations in functional connectivity may be addressed with non-invasive brain stimulation.
Winter N, Blanke J, Leenings R, Ernsting J, Fisch L, Sarink K, Barkhau C, Thiel K, Flinkenflügel K, Winter A, Goltermann J, Meinert S, Dohm K, Repple J, Gruber M, Leehr EJ, Opel N, Grotegerd D, Redlich R, Nitsch R, Bauer J, Heindel W, Groß J, Andlauer TFM, Forstner AJ, Nöthen MM, Rietschel M, Hofmann SG, Pfarr JK, Teutenberg L, Usemann P, Thomas-Odenthal F, Wroblewski A, Brosch K, Stein F, Jansen A, Jamalabadi H, Alexander N, Straube B, Nenadić I, Kircher T, Dannlowski U*, Hahn T* (*equal contribution) (in press). A Systematic Evaluation of Machine Learning-based Biomarkers for Major Depressive Disorder. JAMA Psychiatry.
Abstract:
Importance: 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), no informative biomarkers have been identified.
Objective: To evaluate whether machine learning (ML) can identify a multivariate biomarker for MDD.
Design, setting, and participants: This study used data from the Marburg-Münster Affective Disorders Cohort Study, a case-control clinical neuroimaging study. Patients with acute or lifetime MDD and healthy controls aged 18 to 65 years were recruited from primary care and the general population in Münster and Marburg, Germany, from September 11, 2014, to September 26, 2018. The Münster Neuroimaging Cohort (MNC) was used as an independent partial replication sample. Data were analyzed from April 2022 to June 2023.
Exposure: Patients with MDD and healthy controls.
Main outcome and measure: Diagnostic classification accuracy was quantified on an individual level using an extensive ML-based multivariate approach across a comprehensive range of neuroimaging modalities, including structural and functional magnetic resonance imaging and diffusion tensor imaging as well as a polygenic risk score for depression.
Results: Of 1801 included participants, 1162 (64.5%) were female, and the mean (SD) age was 36.1 (13.1) years. There were a total of 856 patients with MDD (47.5%) and 945 healthy controls (52.5%). The MNC replication sample included 1198 individuals (362 with MDD [30.1%] and 836 healthy controls [69.9%]). Training and testing a total of 4 million ML models, mean (SD) accuracies for diagnostic classification ranged between 48.1% (3.6%) and 62.0% (4.8%). Integrating neuroimaging modalities and stratifying individuals based on age, sex, treatment, or remission status does not enhance model performance. Findings were replicated within study sites and also observed in structural magnetic resonance imaging within MNC. Under simulated conditions of perfect reliability, performance did not significantly improve. Analyzing model errors suggests that symptom severity could be a potential focus for identifying MDD subgroups.
Conclusion and relevance: Despite the improved predictive capability of multivariate compared with univariate neuroimaging markers, no informative individual-level MDD biomarker-even under extensive ML optimization in a large sample of diagnosed patients-could be identified.
