Simultaneous EEG + fMRI study of brain activity during an emotional Stroop task in individuals in remission from depression.

Individuals in remission from depression (MDDR) tend to experience lingering cognitive and emotional processing alterations. However, little is known about the neural profiles underlying these features. Using simultaneous EEG+fMRI, we assessed neural profiles during the emotional word Stroop task (eStroop) in people with MDDR and healthy volunteers (HVs). Event-related potentials (ERPs) were extracted (N450, N2 & P3). Assessments of brain activation, as modulated by ERPs, were carried out, as were fMRI-informed ERP analyses. A trend for greater P3 amplitudes in MDDR versus HV groups existed. HV versus MDDR groups had greater brain activation to emotional versus neutral words in various regions, including the left amygdala, inferior frontal gyrus (IFG); this appeared to be driven by elevated activity to neutral words in the MDDR group (neutral > emotional). HVs showed greater activation (emotional > neutral) modulated by N450 amplitude in various regions, while MDDRs showed greater neutral > emotional activation modulated by N450 amplitude in the left IFG and left precuneus. Our EEG+fMRI findings indicate that people with MDDR appear to have blunted neural differentiation to emotional versus neutral stimuli or elevated neural responses to neutral information processing. This might represent altered neuronal processing (i.e., underlying attention and conflict processing) during a cognitive task with an emotional component in individuals remitted from depression, or elevated neural responses to ambiguous or neutral information. In sum, subtle lingering neuronal features not accompanied by performance differences appear to exist in people with MDDR.

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.

Atypical Temporal Dynamics of Resting State Shapes Stimulus-Evoked Activity in Depression-An EEG Study on Rest-Stimulus Interaction.

Major depressive disorder (MDD) is a complex psychiatric disorder characterized by changes in both resting state and stimulus-evoked activity. Whether resting state changes are carried over to stimulus-evoked activity, however, is unclear. We conducted a combined rest (3 min) and task (three-stimulus auditory oddball paradigm) EEG study in n=28 acute depressed MDD patients, comparing them with n=25 healthy participants. Our focus was on the temporal dynamics of both resting state and stimulus-evoked activity for which reason we measured peak frequency (PF), coefficient of variation (CV), Lempel-Ziv complexity (LZC), and trial-to-trial variability (TTV). Our main findings are: i) atypical temporal dynamics in resting state, specifically in the alpha and theta bands as measured by peak frequency (PF), coefficient of variation (CV) and power; ii) decreased reactivity to external deviant stimuli as measured by decreased changes in stimulus-evoked variance and complexity-TTV, LZC, and power and frequency sliding (FS and PS); iii) correlation of stimulus related measures (TTV, LZC, PS, and FS) with resting state measures. Together, our findings show that resting state dynamics alone are atypical in MDD and, even more important, strongly shapes the dynamics of subsequent stimulus-evoked activity. We thus conclude that MDD can be characterized by an atypical temporal dynamic of its rest-stimulus interaction; that, in turn, makes it difficult for depressed patients to react to relevant stimuli such as the deviant tone in our paradigm.