Characteristics of the Structural Connectivity in Patients with Brain Injury and Chronic Health Symptoms: A Pilot Study.

Diffusion properties from diffusion tensor imaging (DTI) are exquisitely sensitive to white matter abnormalities incurred during traumatic brain injury (TBI), especially for those patients with chronic post-TBI symptoms such as headaches, dizziness, fatigue, etc. The evaluation of structural and functional connectivity using DTI has become a promising method for identifying subtle alterations in brain connectivity associated with TBI that are otherwise not visible with conventional imaging. This study assessed whether TBI patients with (n = 17) or without (n = 16) chronic symptoms (TBIcs/TBIncs) exhibit any changes in structural connectivity (SC) and mean fractional anisotropy (mFA) of intra- and inter-hemispheric connections when compared to a control group (CG) (n = 13). Reductions in SC and mFA were observed for TBIcs compared to CG, but not for TBIncs. More connections were found to have mFA reductions than SC reductions. On the whole, SC is dominated by ipsilateral connections for all the groups after the comparison of contralateral and ipsilateral connections. More contra-ipsi reductions of mFA were found for TBIcs than TBIncs compared to CG. These findings suggest that TBI patients with chronic symptoms not only demonstrate decreased global and regional mFA but also reduced structural network connectivity.

Accelerated Aging after Traumatic Brain Injury: An ENIGMA Multi-Cohort Mega-Analysis.

OBJECTIVE: The long-term consequences of traumatic brain injury (TBI) on brain structure remain uncertain. Given evidence that a single significant brain injury event increases the risk of dementia, brain-age estimation could provide a novel and efficient indexing of the long-term consequences of TBI. Brain-age procedures use predictive modeling to calculate brain-age scores for an individual using structural magnetic resonance imaging (MRI) data. Complicated mild, moderate, and severe TBI (cmsTBI) is associated with a higher predicted age difference (PAD), but the progression of PAD over time remains unclear. We sought to examine whether PAD increases as a function of time since injury (TSI) and if injury severity and sex interacted to influence this progression. METHODS: Through the ENIGMA Adult Moderate and Severe (AMS)-TBI working group, we examine the largest TBI sample to date (n = 343), along with controls, for a total sample size of n = 540, to replicate and extend prior findings in the study of TBI brain age. Cross-sectional T1w-MRI data were aggregated across 7 cohorts, and brain age was established using a similar brain age algorithm to prior work in TBI. RESULTS: Findings show that PAD widens with longer TSI, and there was evidence for differences between sexes in PAD, with men showing more advanced brain age. We did not find strong evidence supporting a link between PAD and cognitive performance. INTERPRETATION: This work provides evidence that changes in brain structure after cmsTBI are dynamic, with an initial period of change, followed by relative stability in brain morphometry, eventually leading to further changes in the decades after a single cmsTBI. ANN NEUROL 2024;96:365-377.

ENIGMA's simple seven: Recommendations to enhance the reproducibility of resting-state fMRI in traumatic brain injury.

Resting state functional magnetic resonance imaging (rsfMRI) provides researchers and clinicians with a powerful tool to examine functional connectivity across large-scale brain networks, with ever-increasing applications to the study of neurological disorders, such as traumatic brain injury (TBI). While rsfMRI holds unparalleled promise in systems neurosciences, its acquisition and analytical methodology across research groups is variable, resulting in a literature that is challenging to integrate and interpret. The focus of this narrative review is to address the primary methodological issues including investigator decision points in the application of rsfMRI to study the consequences of TBI. As part of the ENIGMA Brain Injury working group, we have collaborated to identify a minimum set of recommendations that are designed to produce results that are reliable, harmonizable, and reproducible for the TBI imaging research community. Part one of this review provides the results of a literature search of current rsfMRI studies of TBI, highlighting key design considerations and data processing pipelines. Part two outlines seven data acquisition, processing, and analysis recommendations with the goal of maximizing study reliability and between-site comparability, while preserving investigator autonomy. Part three summarizes new directions and opportunities for future rsfMRI studies in TBI patients. The goal is to galvanize the TBI community to gain consensus for a set of rigorous and reproducible methods, and to increase analytical transparency and data sharing to address the reproducibility crisis in the field.

Military environmental exposures and risk of breast cancer in active-duty personnel and veterans: a scoping review.

Background: The effects of military environmental exposures (MEE) such as volatile organic compounds (VOCs), endocrine-disrupting chemicals (EDCs), tactile herbicides, airborne hazards and open burn pits (AHOBP), and depleted uranium on health are salient concerns for service members and Veterans. However, little work has been done to investigate the relationship between MEE and risk of breast cancer. Data sources and methods: We conducted a scoping review on MEE, military deployment/service, and risk of breast cancer among active-duty service members and Veterans. PRISMA was used. PubMed, Embase, and citations of included articles were searched, resulting in 4,364 articles to screen: 28 articles were included. Results: Most papers on military deployment and military service found a lower/equivalent risk of breast cancer when comparing rates to those without deployment or civilians. Exposure to VOCs due to military occupation or contaminated groundwater was associated with a slightly higher risk of breast cancer. Exposure to Agent Orange was not associated with an increased risk of breast cancer. Evidence regarding EDCs was limited. No paper directly measured exposure to AHOBP or depleted uranium, but deployments with known exposures to AHOBP or depleted uranium were associated with an equivalent/lower risk of breast cancer. Conclusions: Women are the fastest growing population within the military, and breast cancer poses a unique risk to women Veterans who were affected by MEE during their service. Unfortunately, the literature on MEE and breast cancer is mixed and limited, in part due to the Healthy Soldier Paradox and poor classification of exposure(s).

Impulsivity and Psychiatric Diagnoses as Mediators of Suicidal Ideation and Suicide Attempts Among Veterans With Traumatic Brain Injury.

OBJECTIVE: Traumatic brain injury (TBI) is a risk factor for suicide, but questions related to mechanisms remain unanswered. Impulsivity is a risk factor for suicide and is a common sequela of TBI. The authors explored the relationships between TBI and both suicidal ideation and suicide attempts and explored whether impulsivity and comorbid psychiatric diagnoses mediate these relationships. METHODS: This cross-sectional retrospective chart review study included 164 veterans enrolled in a previous study. Sixty-nine veterans had no TBI history, and 95 had a TBI history (mild, N=44; moderate, N=13; severe, N=12; and unclear severity, N=26). To examine the associations between TBI and suicidal ideation or suicide attempts, as well as potential mediators of these relationships, chi-square tests, t tests, and logistic regression models were used. RESULTS: Unadjusted analyses indicated that veterans with TBI were more likely to report suicidal ideation; however, in analyses controlling for mediators, this relationship was no longer significant. Among veterans with TBI, suicidal ideation was related most strongly to high impulsivity (odds ratio=15.35, 95% CI=2.43-96.79), followed by depression (odds ratio=5.73, 95% CI=2.53-12.99) and posttraumatic stress disorder (odds ratio=2.57, 95% CI=1.03-6.42). TBI was not related to suicide attempts, yet suicide attempts were related to high impulsivity (odds ratio=6.95, 95% CI=1.24-38.75) and depression (odds ratio=3.89, 95% CI=1.56-9.40). CONCLUSIONS: These findings suggest that impulsivity, followed by psychiatric diagnoses, most strongly mediate the relationships between TBI and both suicidal ideation and suicide attempts. Impulsivity may be mechanistically related to, and serve as a future treatment target for, suicidality among veterans with TBI.

Magnesium-ibogaine therapy in veterans with traumatic brain injuries.

Traumatic brain injury (TBI) is a leading cause of disability. Sequelae can include functional impairments and psychiatric syndromes such as post-traumatic stress disorder (PTSD), depression and anxiety. Special Operations Forces (SOF) veterans (SOVs) may be at an elevated risk for these complications, leading some to seek underexplored treatment alternatives such as the oneirogen ibogaine, a plant-derived compound known to interact with multiple neurotransmitter systems that has been studied primarily as a treatment for substance use disorders. Ibogaine has been associated with instances of fatal cardiac arrhythmia, but coadministration of magnesium may mitigate this concern. In the present study, we report a prospective observational study of the Magnesium-Ibogaine: the Stanford Traumatic Injury to the CNS protocol (MISTIC), provided together with complementary treatment modalities, in 30 male SOVs with predominantly mild TBI. We assessed changes in the World Health Organization Disability Assessment Schedule from baseline to immediately (primary outcome) and 1 month (secondary outcome) after treatment. Additional secondary outcomes included changes in PTSD (Clinician-Administered PTSD Scale for DSM-5), depression (Montgomery-Åsberg Depression Rating Scale) and anxiety (Hamilton Anxiety Rating Scale). MISTIC resulted in significant improvements in functioning both immediately (Pcorrected < 0.001, Cohen's d = 0.74) and 1 month (Pcorrected < 0.001, d = 2.20) after treatment and in PTSD (Pcorrected < 0.001, d = 2.54), depression (Pcorrected < 0.001, d = 2.80) and anxiety (Pcorrected < 0.001, d = 2.13) at 1 month after treatment. There were no unexpected or serious adverse events. Controlled clinical trials to assess safety and efficacy are needed to validate these initial open-label findings. ClinicalTrials.gov registration: NCT04313712 .

Neural mechanisms of emotional health in traumatic brain injury patients undergoing rTMS treatment.

Emotional dysregulation such as that seen in depression, are a long-term consequence of mild traumatic brain injury (TBI), that can be improved by using neuromodulation treatments such as repetitive transcranial magnetic stimulation (rTMS). Previous studies provide insights into the changes in functional connectivity related to general emotional health after the application of rTMS procedures in patients with TBI. However, these studies provide little understanding of the underlying neuronal mechanisms that drive the improvement of the emotional health in these patients. The current study focuses on inferring the effective (causal) connectivity changes and their association with emotional health, after rTMS treatment of cognitive problems in TBI patients (N = 32). Specifically, we used resting state functional magnetic resonance imaging (fMRI) together with spectral dynamic causal model (spDCM) to investigate changes in brain effective connectivity, before and after the application of high frequency (10 Hz) rTMS over left dorsolateral prefrontal cortex. We investigated the effective connectivity of the cortico-limbic network comprised of 11 regions of interest (ROIs) which are part of the default mode, salience, and executive control networks, known to be implicated in emotional processing. The results indicate that overall, among extrinsic connections, the strength of excitatory connections decreased while that of inhibitory connections increased after the neuromodulation. The cardinal region in the analysis was dorsal anterior cingulate cortex (dACC) which is considered to be the most influenced during emotional health disorders. Our findings implicate the altered connectivity of dACC with left anterior insula and medial prefrontal cortex, after the application of rTMS, as a potential neural mechanism underlying improvement of emotional health. Our investigation highlights the importance of these brain regions as treatment targets in emotional processing in TBI.

The Emerging Role of Virtual Reality as an Adjunct to Procedural Sedation and Anesthesia: A Narrative Review.

Over the past 20 years, there has been a significant reduction in the incidence of adverse events associated with sedation outside of the operating room. Non-pharmacologic techniques are increasingly being used as peri-operative adjuncts to facilitate and promote anxiolysis, analgesia and sedation, and to reduce adverse events. This narrative review will briefly explore the emerging role of immersive reality in the peri-procedural care of surgical patients. Immersive virtual reality (VR) is intended to distract patients with the illusion of "being present" inside the computer-generated world, drawing attention away from their anxiety, pain, and discomfort. VR has been described for a variety of procedures that include colonoscopies, venipuncture, dental procedures, and burn wound care. As VR technology develops and the production costs decrease, the role and application of VR in clinical practice will expand. It is important for medical professionals to understand that VR is now available for prime-time use and to be aware of the growing body in the literature that supports VR.

Bridging Big Data: Procedures for Combining Non-equivalent Cognitive Measures from the ENIGMA Consortium.

Investigators in neuroscience have turned to Big Data to address replication and reliability issues by increasing sample sizes, statistical power, and representativeness of data. These efforts unveil new questions about integrating data arising from distinct sources and instruments. We focus on the most frequently assessed cognitive domain - memory testing - and demonstrate a process for reliable data harmonization across three common measures. We aggregated global raw data from 53 studies totaling N = 10,505 individuals. A mega-analysis was conducted using empirical bayes harmonization to remove site effects, followed by linear models adjusting for common covariates. A continuous item response theory (IRT) model estimated each individual's latent verbal learning ability while accounting for item difficulties. Harmonization significantly reduced inter-site variance while preserving covariate effects, and our conversion tool is freely available online. This demonstrates that large-scale data sharing and harmonization initiatives can address reproducibility and integration challenges across the behavioral sciences.

Fixel-based analysis of the diffusion properties of the patients with brain injury and chronic health symptoms.

The diffusion properties from diffusion tensor imaging (DTI) are sensitive to white matter (WM) abnormalities and could serve as indicators of diffuse axonal damages incurred during a traumatic brain injury (TBI). Analyses of diffusion metrics in the regions of interest (ROIs) were used to compare the differences in the 18 major fiber tracts in 46 participants, between TBI participants with (n = 17) or without (n = 16) chronic symptoms (CS) and a control group (CG, n = 13). In addition to the widely used diffusion metrics, such as fractional anisotropy (FA), mean (MD), axial (AD) and radial (RD) diffusivities, apparent fiber density (AFD), complexity (CX) and fixel number (FN) derived from Mrtrix3 software package were used to characterize WM tracts and compare between participant groups in the ROIs defined by the fixel numbers. Significant differences were found in FA, AFD, MD, RD and CX in ROIs with different FNs in the corpus callosum forceps minor, left and right inferior longitudinal fasciculus, and left and right uncinate fasciculus for both TBI groups compared to controls. Diffusion properties in ROIs with different FNs can serve as detailed biomarkers of WM abnormalities, especially for individuals with chronic TBI related symptoms.

Comparison of veterans affairs and NIDILRR traumatic brain injury model systems participants with disorders of consciousness.

OBJECTIVE: To characterize demographic, pre-injury, and outcome data within the National Institute on Disability, Independent Living, and Rehabilitation Research (NIDILRR) and Veterans Affairs (VA) Traumatic Brain Injury Model Systems (TBIMS) cohorts with severe traumatic brain injury (TBI) with no command-following ability at time of admission to acute rehabilitation. DESIGN: Retrospective cohort. SETTING: NIDILRR and VA TBI Model Systems (TBIMS) centers. PARTICIPANTS: 396 NIDILRR and 72 VA participants without command-following ability who experienced TBI with subsequent Disorder of Consciousness (DoC). MAIN OUTCOME MEASURE: Pre-injury and injury characteristics, rehabilitation outcomes, and 1-year self-reported outcomes. RESULTS: VA TBIMS cohort included individuals who were active duty or had military service before their injury. The VA cohort were more likely to be re-hospitalized at 1-year follow-up or residing in a long-term care or rehab setting. The NIDILRR TBIMS cohort had higher FIM and DRS scores at rehabilitation discharge, while the VA participants saw longer lengths of stay and higher numbers of "violent" injury types. CONCLUSIONS: This study allows for a better understanding of the comparability between VA and NIDILRR DoC cohorts providing guidance on how veteran and civilian samples might be merged in future TBIMS studies to explore predictors of recovery from a DoC.

Altered lateralization of the cingulum in deployment-related traumatic brain injury: An ENIGMA military-relevant brain injury study.

Traumatic brain injury (TBI) in military populations can cause disruptions in brain structure and function, along with cognitive and psychological dysfunction. Diffusion magnetic resonance imaging (dMRI) can detect alterations in white matter (WM) microstructure, but few studies have examined brain asymmetry. Examining asymmetry in large samples may increase sensitivity to detect heterogeneous areas of WM alteration in mild TBI. Through the Enhancing Neuroimaging Genetics Through Meta-Analysis Military-Relevant Brain Injury working group, we conducted a mega-analysis of neuroimaging and clinical data from 16 cohorts of Active Duty Service Members and Veterans (n = 2598). dMRI data were processed together along with harmonized demographic, injury, psychiatric, and cognitive measures. Fractional anisotropy in the cingulum showed greater asymmetry in individuals with deployment-related TBI, driven by greater left lateralization in TBI. Results remained significant after accounting for potentially confounding variables including posttraumatic stress disorder, depression, and handedness, and were driven primarily by individuals whose worst TBI occurred before age 40. Alterations in the cingulum were also associated with slower processing speed and poorer set shifting. The results indicate an enhancement of the natural left laterality of the cingulum, possibly due to vulnerability of the nondominant hemisphere or compensatory mechanisms in the dominant hemisphere. The cingulum is one of the last WM tracts to mature, reaching peak FA around 42 years old. This effect was primarily detected in individuals whose worst injury occurred before age 40, suggesting that the protracted development of the cingulum may lead to increased vulnerability to insults, such as TBI.

Electrophysiological and behavioral effects of unilateral and bilateral rTMS; A randomized clinical trial on rumination and depression.

BACKGROUND: Rumination is significantly frequent in major depressive disorder (MDD). However, not a lot of studies have investigated the effects of repetitive transcranial magnetic stimulation (rTMS) on rumination. METHODS: 61 participants with a minimum Hamilton Depression Rating Scale (HAM-D) score of 20 were randomly assigned to sham, bilateral stimulation (BS) or unilateral stimulation (US) groups. EEG, The Ruminative Response Scale (RRS), and HAM-D were administered before and after the 20 sessions of rTMS. Phase locked values (PLV) were calculated as a measure of connectivity. RESULTS: There was a significant decrease in HAM-D scores in both BS and US. In responders, BS and US differed significantly in RRS total scores, with greater reduction in BS. PLV significantly changed in the default mode network (DMN) in delta, theta, alpha, and beta in BS, in responders of which PLV decreased in the DMN in beta and gamma. Positive correlations between PLV and brooding in delta and theta, and negative correlations between PLV and reflection were found in theta, alpha, and beta. In US, connectivity in the DMN increased in beta, and PLV increased in theta and beta, and decreased in alpha and beta in its responders. Positive correlations between PLV and brooding in the delta and theta, as well as negative correlations between PLV and reflection in theta were observed in the DMN. CONCLUSION: US and BS resulted in different modulations in the DMN, however, both could alleviate both rumination and depression. Reductions in the beta and alpha frequency bands in the DMN can be considered as potential EEG-based markers of response to bilateral and unilateral rTMS, respectively.

Headache Diary Mobile Application for Monitoring and Characterizing Posttraumatic Headaches.

OBJECTIVE: This study analyzed the data collected using a headache diary mobile application to characterize posttraumatic headaches (PTHs) in a sample of US veterans. Specifically, we measured patient engagement with the mobile application and compared our findings with previous literature regarding PTHs. SETTING: A Headache Center of Excellence (HCoE) in a Veterans Health Administration facility. PARTICIPANTS: Forty-nine veterans currently being treated for ongoing PTH-related complaints with English fluency, reliable access to the internet, and a mobile phone. DESIGN: Observational study of PTH characteristics using the mobile application over the course of 1 year. MEASURES: Main outcome measures were collected via a headache diary mobile application developed for patients to track headache-associated symptoms, headache location, triggers, type, intensity, and duration. Patients also completed a baseline Headache Impact Test (HIT-6) survey. RESULTS: In total, 1569 entries were completed during the first year of application deployment. On average, patients completed 2.5 entries per week and used the application for 70 days. They frequently reported associated PTH symptoms of photophobia (56.7%) and headaches triggered by emotional stress (35.1%). Network analyses revealed patterns of co-occurrence in triggers of headache pain, associated symptoms, and headache pain location. Headache pain severity and impact ratings from the headache diary demonstrated convergent validity with the established HIT-6 measure. CONCLUSIONS: Headache diary mobile applications are a promising tool for monitoring and characterizing PTHs in veterans. Present results mirror past studies of PTH characteristics. Mobile application headache diaries may be used in both clinical and research settings to monitor headache symptoms and communicate the functional impact of headaches in real time.

Age-dependent white matter disruptions after military traumatic brain injury: Multivariate analysis results from ENIGMA brain injury.

Mild Traumatic brain injury (mTBI) is a signature wound in military personnel, and repetitive mTBI has been linked to age-related neurogenerative disorders that affect white matter (WM) in the brain. However, findings of injury to specific WM tracts have been variable and inconsistent. This may be due to the heterogeneity of mechanisms, etiology, and comorbid disorders related to mTBI. Non-negative matrix factorization (NMF) is a data-driven approach that detects covarying patterns (components) within high-dimensional data. We applied NMF to diffusion imaging data from military Veterans with and without a self-reported TBI history. NMF identified 12 independent components derived from fractional anisotropy (FA) in a large dataset (n = 1,475) gathered through the ENIGMA (Enhancing Neuroimaging Genetics through Meta-Analysis) Military Brain Injury working group. Regressions were used to examine TBI- and mTBI-related associations in NMF-derived components while adjusting for age, sex, post-traumatic stress disorder, depression, and data acquisition site/scanner. We found significantly stronger age-dependent effects of lower FA in Veterans with TBI than Veterans without in four components (q < 0.05), which are spatially unconstrained by traditionally defined WM tracts. One component, occupying the most peripheral location, exhibited significantly stronger age-dependent differences in Veterans with mTBI. We found NMF to be powerful and effective in detecting covarying patterns of FA associated with mTBI by applying standard parametric regression modeling. Our results highlight patterns of WM alteration that are differentially affected by TBI and mTBI in younger compared to older military Veterans.

Transdiagnostic role of glutamate and white matter damage in neuropsychiatric disorders: A Systematic Review.

Neuropsychiatric disorders including generalized anxiety disorder (GAD), obsessive-compulsive disorder (OCD), major depressive disorder (MDD), bipolar disorder (BD), and schizophrenia (SZ) have been considered distinct categories of diseases despite their overlapping characteristics and symptomatology. We aimed to provide an in-depth review elucidating the role of glutamate/Glx and white matter (WM) abnormalities in these disorders from a transdiagnostic perspective. The PubMed online database was searched for studies published between 2010 and 2021. After careful screening, 401 studies were included. The findings point to decreased levels of glutamate in the Anterior Cingulate Cortex in both SZ and BD, whereas Glx is elevated in the Hippocampus in SZ and MDD. With regard to WM abnormalities, the Corpus Callosum and superior Longitudinal Fascicle were the most consistently identified brain regions showing decreased fractional anisotropy (FA) across all the reviewed disorders, except GAD. Additionally, the Uncinate Fasciculus displayed decreased FA in all disorders, except OCD. Decreased FA was also found in the inferior Longitudinal Fasciculus, inferior Fronto-Occipital Fasciculus, Thalamic Radiation, and Corona Radiata in SZ, BD, and MDD. Decreased FA in the Fornix and Corticospinal Tract were found in BD and SZ patients. The Cingulum and Anterior Limb of Internal Capsule exhibited decreased FA in MDD and SZ patients. The results suggest a gradual increase in severity from GAD to SZ defined by the number of brain regions with WM abnormality which may be partially caused by abnormal glutamate levels. WM damage could thus be considered a potential marker of some of the main neuropsychiatric disorders.

Sex differences in cortical thickness and diffusion properties in patients with traumatic brain injury: a pilot study.

OBJECTIVE: Cortical thickness and diffusion properties are important measures of gray and white matter integrity in those with traumatic brain injury (TBI). Many studies show that healthy adult females have greater cortical thickness than males across numerous brain sites. In this study, we explored this sex difference in patients with TBI. METHOD: Participants consisted of 32 patients with TBI and 21 neurologically healthy controls. All were scanned by magnetic resonance imaging (MRI). Differences in cortical thickness and diffusion properties were examined between groups (i.e., TBI/control, male/female). RESULTS: Patients with TBI had more cortical thinning (both hemispheres) compared to controls. They also showed decreased fractional anisotropy (FA) for several major white matter tracts. Healthy females had significantly greater cortical thickness compared to healthy males. However, this difference was smaller among the patients with TBI. We found no sex differences in diffusion properties. There were moderate correlations between cortical thickness, diffusion properties, and cognitive performance, as measured by the Trail Making Test B. CONCLUSION: These findings contribute to a growing discussion on sex differences in cortical thickness and diffusion properties. Sexual dimorphism could necessitate different clinical profiles, targets, and rehabilitation strategies in patients with TBI.

Depression Diagnosis Modeling With Advanced Computational Methods: Frequency-Domain eMVAR and Deep Learning.

Electroencephalogram (EEG)-based automated depression diagnosis systems have been suggested for early and accurate detection of mood disorders. EEG signals are highly irregular, nonlinear, and nonstationary in nature and are traditionally studied from a linear viewpoint by means of statistical and frequency features. Since, linear metrics present certain limitations and nonlinear methods have proven to be an efficient tool in understanding the complexities of the brain in the identification of underlying behavior of biological signals, such as electrocardiogram, EEG and magnetoencephalogram and thus, can be applied to all nonstationary signals. Various nonlinear algorithms can be used in the analysis of EEG signals. In this research paper, we aim to develop a novel methodology for EEG-based depression diagnosis utilizing 2 advanced computational techniques: frequency-domain extended multivariate autoregressive (eMVAR) and deep learning (DL). We proposed a hybrid method comprising a pretrained ResNet-50 and long-short term memory (LSTM) to capture depression-specific information and compared with a strong conventional machine learning (ML) framework having eMVAR connectivity features. The following 8 causality measures, which interpret the interaction mechanisms among spectrally decomposed oscillations, were used to extract features from multivariate EEG time series: directed coherence (DC), directed transfer function (DTF), partial DC (PDC), generalized PDC (gPDC), extended DC (eDC), delayed DC (dDC), extended PDC (ePDC), and delayed PDC (dPDC). The classification accuracies were 84% with DC, 85% with DTF, 95.3% with PDC, 95.1% with gPDC, 84.8% with eDC, 84.6% with dDC, 84.2% with ePDC, and 95.9% with dPDC for the eMVAR framework. Through a DL framework (ResNet-50 + LSTM), the classification accuracy was achieved as 90.22%. The results demonstrate that our DL methodology is a competitive alternative to the strong feature extraction-based ML methods in depression classification.