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.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.