Functional connectivity signatures of major depressive disorder: machine learning analysis of two multicenter neuroimaging studies.

The promise of machine learning has fueled the hope for developing diagnostic tools for psychiatry. Initial studies showed high accuracy for the identification of major depressive disorder (MDD) with resting-state connectivity, but progress has been hampered by the absence of large datasets. Here we used regular machine learning and advanced deep learning algorithms to differentiate patients with MDD from healthy controls and identify neurophysiological signatures of depression in two of the largest resting-state datasets for MDD. We obtained resting-state functional magnetic resonance imaging data from the REST-meta-MDD (N = 2338) and PsyMRI (N = 1039) consortia. Classification of functional connectivity matrices was done using support vector machines (SVM) and graph convolutional neural networks (GCN), and performance was evaluated using 5-fold cross-validation. Features were visualized using GCN-Explainer, an ablation study and univariate t-testing. The results showed a mean classification accuracy of 61% for MDD versus controls. Mean accuracy for classifying (non-)medicated subgroups was 62%. Sex classification accuracy was substantially better across datasets (73-81%). Visualization of the results showed that classifications were driven by stronger thalamic connections in both datasets, while nearly all other connections were weaker with small univariate effect sizes. These results suggest that whole brain resting-state connectivity is a reliable though poor biomarker for MDD, presumably due to disease heterogeneity as further supported by the higher accuracy for sex classification using the same methods. Deep learning revealed thalamic hyperconnectivity as a prominent neurophysiological signature of depression in both multicenter studies, which may guide the development of biomarkers in future studies.

Brain morphometry and connectivity differs between adolescent- and adult-onset major depressive disorder.

BACKGROUND: Early-onset (EO) major depressive disorder (MDD) patients experience more depressive episodes and an increased risk of relapse. Thus, on a neurobiological level, adult EO patients might display brain structure and function different from adult-onset (AO) patients. METHODS: A total of 103 patients (66 females) underwent magnetic resonance imaging. Structural measures of gray matter volume (GMV) and functional connectivity networks during resting state were compared between EO (≤19 years) and AO groups. Four residual major depression symptoms, mood, anxiety, insomnia, and somatic symptoms, were correlated with GMV between groups. RESULTS: We found comparatively increased GMV in the EO group, namely the medial prefrontal and insular cortex, as well as the anterior hippocampus. Functional networks in EO patients showed a comparatively weaker synchronization of the left hippocampus with the adjacent amygdala, and a stronger integration with nodes in the contralateral prefrontal cortex and supramarginal gyrus. Volumetric analysis of depression symptoms associated the caudate nuclei with symptoms of insomnia, and persisting mood symptoms with the right amygdala, while finding no significant clusters for somatic and anxiety symptoms. CONCLUSIONS: The study highlights the important role of the hippocampus and the prefrontal cortex in EO patients as part of emotion-regulation networks. Results in EO patients demonstrated subcortical volume changes irrespective of sleep and mood symptom recovery, which substantiates adolescence as a pivotal developmental phase for MDD. Longitudinal studies are needed to differentiate neural recovery trajectories while accounting for age of onset.

Altered resting-state functional connectome in major depressive disorder: a mega-analysis from the PsyMRI consortium.

Major depressive disorder (MDD) is associated with abnormal neural circuitry. It can be measured by assessing functional connectivity (FC) at resting-state functional MRI, that may help identifying neural markers of MDD and provide further efficient diagnosis and monitor treatment outcomes. The main aim of the present study is to investigate, in an unbiased way, functional alterations in patients with MDD using a large multi-center dataset from the PsyMRI consortium including 1546 participants from 19 centers ( www.psymri.com ). After applying strict exclusion criteria, the final sample consisted of 606 MDD patients (age: 35.8 ± 11.9 y.o.; females: 60.7%) and 476 healthy participants (age: 33.3 ± 11.0 y.o.; females: 56.7%). We found significant relative hypoconnectivity within somatosensory motor (SMN), salience (SN) networks and between SMN, SN, dorsal attention (DAN), and visual (VN) networks in MDD patients. No significant differences were detected within the default mode (DMN) and frontoparietal networks (FPN). In addition, alterations in network organization were observed in terms of significantly lower network segregation of SMN in MDD patients. Although medicated patients showed significantly lower FC within DMN, FPN, and SN than unmedicated patients, there were no differences between medicated and unmedicated groups in terms of network organization in SMN. We conclude that the network organization of cortical networks, involved in processing of sensory information, might be a more stable neuroimaging marker for MDD than previously assumed alterations in higher-order neural networks like DMN and FPN.

Neurobiological predictors for clinical trajectories in fully remitted depressed patients.

BACKGROUND: Serious long term health and economic detriment accompany residual depressive symptoms even in fully remitted depressed patients (rMDD). Neurobiological predictors for rMDD patients' illness trajectory are absent. METHODS: rMDD patients (n = 39, female = 26) underwent magnetic resonance imaging. Baseline analyses of brain structure via voxel-based morphometry and brain function via functional connectivity (FC) at rest were correlated with changes in the Hamilton Depression Rating Scale between baseline and follow-up, and incidence of a recurrent major depressive episode (MDE) within a 2-year period. RESULTS: Gray matter increases in default mode (DN) regions in the posterior cingulate cortex (PCC) and increased resting-state FC within the DN both predicted change of depressive symptoms. Patients with recurrent MDE had larger bilateral nucleus accumbens and left insula volumes. Post hoc exploratory analysis of nucleus accumbens and insula conceptualized as part of the brain's reward circuit demonstrated reduced connectivity in patients with recurrent MDE. CONCLUSIONS: Higher DN connectivity and PCC volume coinciding with a more favorable course of symptoms suggest neural mechanisms of self-recovery beyond the phase of active medical treatment. Alterations in the brain's reward circuit might be a starting point for designing maintenance treatments that prevent recurrent MDEs in rMDD patients.

On the relationship of first-episode psychosis to the amphetamine-sensitized state: a dopamine D2/3 receptor agonist radioligand study.

Schizophrenia is characterized by increased behavioral and neurochemical responses to dopamine-releasing drugs. This prompted the hypothesis of psychosis as a state of "endogenous" sensitization of the dopamine system although the exact basis of dopaminergic disturbances and the possible role of prefrontal cortical regulation have remained uncertain. To show that patients with first-episode psychosis release more dopamine upon amphetamine-stimulation than healthy volunteers, and to reveal for the first time that prospective sensitization induced by repeated amphetamine exposure increases dopamine-release in stimulant-naïve healthy volunteers to levels observed in patients, we collected data on amphetamine-induced dopamine release using the dopamine D2/3 receptor agonist radioligand [11C]-(+)-PHNO and positron emission tomography. Healthy volunteers (n = 28, 14 female) underwent a baseline and then a post-amphetamine scan before and after a mildly sensitizing regimen of repeated oral amphetamine. Unmedicated patients with first-episode psychosis (n = 21; 6 female) underwent a single pair of baseline and then post-amphetamine scans. Furthermore, T1 weighted magnetic resonance imaging of the prefrontal cortex was performed. Patients with first-episode psychosis showed larger release of dopamine compared to healthy volunteers. After sensitization of healthy volunteers their dopamine release was significantly amplified and no longer different from that seen in patients. Healthy volunteers showed a negative correlation between prefrontal cortical volume and dopamine release. There was no such relationship after sensitization or in patients. Our data in patients with untreated first-episode psychosis confirm the "endogenous sensitization" hypothesis and support the notion of impaired prefrontal control of the dopamine system in schizophrenia.

Prefrontal networks dynamically related to recovery from major depressive disorder: a longitudinal pharmacological fMRI study.

Due to lacking predictors of depression recovery, successful treatment of major depressive disorder (MDD) is frequently only achieved after therapeutic optimization leading to a prolonged suffering of patients. This study aimed to determine neural prognostic predictors identifying non-remitters prior or early after treatment initiation. Moreover, it intended to detect time-sensitive neural mediators indicating depression recovery. This longitudinal, interventional, single-arm, open-label, phase IV, pharmacological functional magnetic resonance imaging (fMRI) study comprised four scans at important stages prior (day 0) and after escitalopram treatment initiation (day 1, 28, and 56). Totally, 22 treatment-free MDD patients (age mean ± SD: 31.5 ± 7.7; females: 50%) suffering from a concurrent major depressive episode without any comorbid DSM-IV axis I diagnosis completed the study protocol. Primary outcome were neural prognostic predictors of depression recovery. Enhanced de-activation of anterior medial prefrontal cortex (amPFC, single neural mediator) indicated depression recovery correlating with MADRS score and working memory improvements. Strong dorsolateral PFC (dlPFC) activation and weak dlPFC-amPFC, dlPFC-posterior cingulate cortex (PCC), dlPFC-parietal lobe (PL) coupling (three prognostic predictors) hinted at depression recovery at day 0 and 1. Preresponse prediction of continuous (dlPFC-PL: R2day1 = 55.9%, 95% CI: 22.6-79%, P < 0.005) and dichotomous (specificity/sensitivity: SP/SNday1 = 0.91/0.82) recovery definitions remained significant after leave-one-out cross-validation. Identified prefrontal neural predictors might propel the future development of fMRI markers for clinical decision making, which could lead to increased response rates and adherence during acute phase treatment periods. Moreover, this study underscores the importance of the amPFC in depression recovery.

Midday and nadir salivary cortisol appear superior to cortisol awakening response in burnout assessment and monitoring.

Burnout and work-related stress symptoms of anxiety disorder and depression cause prolonged work absenteeism and early retirement. Hence, reliable identification of patients under risk and monitoring of treatment success is highly warranted. We aimed to evaluate stress-specific biomarkers in a population-based, "real-world" cohort (burnouts: n = 40, healthy controls: n = 26), recruited at a preventive care ward, at baseline and after a four-month follow up, during which patients received medical and psychological treatment. At baseline, significantly higher levels of salivary cortisol were observed in the burnout group compared to the control group. This was even more pronounced in midday- (p < 0.001) and nadir samples (p < 0.001) than for total morning cortisol secretion (p < 0.01). The treatment program resulted in a significant reduction of stress, anxiety, and depression scores (all p < 0.001), with 60% of patients showing a clinically relevant improvement. This was accompanied by a ~30% drop in midday cortisol levels (p < 0.001), as well as a ~25% decrease in cortisol nadir (p < 0.05), although not directly correlating with score declines. Our data emphasize the potential usefulness of midday and nadir salivary cortisol as markers in the assessment and biomonitoring of burnout.

Oppositional COMT Val158Met effects on resting state functional connectivity in adolescents and adults.

Prefrontal dopamine levels are relatively increased in adolescence compared to adulthood. Genetic variation of COMT (COMT Val158Met) results in lower enzymatic activity and higher dopamine availability in Met carriers. Given the dramatic changes of synaptic dopamine during adolescence, it has been suggested that effects of COMT Val158Met genotypes might have oppositional effects in adolescents and adults. The present study aims to identify such oppositional COMT Val158Met effects in adolescents and adults in prefrontal brain networks at rest. Resting state functional connectivity data were collected from cross-sectional and multicenter study sites involving 106 healthy young adults (mean age 24 ± 2.6 years), gender matched to 106 randomly chosen 14-year-olds. We selected the anterior medial prefrontal cortex (amPFC) as seed due to its important role as nexus of the executive control and default mode network. We observed a significant age-dependent reversal of COMT Val158Met effects on resting state functional connectivity between amPFC and ventrolateral as well as dorsolateral prefrontal cortex, and parahippocampal gyrus. Val homozygous adults exhibited increased and adolescents decreased connectivity compared to Met homozygotes for all reported regions. Network analyses underscored the importance of the parahippocampal gyrus as mediator of observed effects. Results of this study demonstrate that adolescent and adult resting state networks are dose-dependently and diametrically affected by COMT genotypes following a hypothetical model of dopamine function that follows an inverted U-shaped curve. This study might provide cues for the understanding of disease onset or dopaminergic treatment mechanisms in major neuropsychiatric disorders such as schizophrenia and attention deficit hyperactivity disorder.

fMRI measurements of amygdala activation are confounded by stimulus correlated signal fluctuation in nearby veins draining distant brain regions.

Imaging the amygdala with functional MRI is confounded by multiple averse factors, notably signal dropouts due to magnetic inhomogeneity and low signal-to-noise ratio, making it difficult to obtain consistent activation patterns in this region. However, even when consistent signal changes are identified, they are likely to be due to nearby vessels, most notably the basal vein of rosenthal (BVR). Using an accelerated fMRI sequence with a high temporal resolution (TR = 333 ms) combined with susceptibility-weighted imaging, we show how signal changes in the amygdala region can be related to a venous origin. This finding is confirmed here in both a conventional fMRI dataset (TR = 2000 ms) as well as in information of meta-analyses, implying that "amygdala activations" reported in typical fMRI studies are likely confounded by signals originating in the BVR rather than in the amygdala itself, thus raising concerns about many conclusions on the functioning of the amygdala that rely on fMRI evidence alone.