Neuroimaging Study of Brain Functional Differences in Generalized Anxiety Disorder and Depressive Disorder

Abstract

Generalized anxiety disorder (GAD) and depressive disorder (DD) are distinct mental disorders, which are characterized by complex and unique neuroelectrophysiological mechanisms in psychiatric neurosciences. The understanding of the brain functional differences between GAD and DD is crucial for the accurate diagnosis and clinical efficacy evaluation. The aim of this study was to reveal the differences in functional brain imaging between GAD and DD based on multidimensional electroencephalogram (EEG) characteristics. To this end, 10 min resting-state EEG signals were recorded from 38 GAD and 34 DD individuals. Multidimensional EEG features were subsequently extracted, which include power spectrum density (PSD), fuzzy entropy (FE), and phase lag index (PLI). Then, a direct statistical analysis (i.e., ANOVA) and three ensemble learning models (i.e., Random Forest (RF), Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting (XGBoost)) were used on these EEG features for the differential recognitions. Our results showed that DD has significantly higher PSD values in the alpha1 and beta band, and a higher FE in the beta band, in comparison with GAD, along with the aberrant functional connections in all four bands between GAD and DD. Moreover, machine learning analysis further revealed that the distinct features predominantly occurred in the beta band and functional connections. Here, we show that DD has higher power and more complex brain activity patterns in the beta band and reorganized brain functional network structures in all bands compared to GAD. In sum, these findings move towards the practical identification of brain functional differences between GAD and DD.

A potential brain functional biomarker distinguishing patients with Crohn’s disease with different disease stages: a resting-state fMRI study

“…It is also noteworthy that the ALFF in the right cingulate gyrus had a positive correlation with hostility in the patients with CD in this study. This altered neurological profile was reported in patients with affective disorders or anxiety and depression (Rive et al, 2013;Qi et al, 2023;Yu et al, 2023). The frontal pole receives input from the limbic system, and plays a key role in emotional memory storage and emotional regulation (Bermpohl et al, 2006;Bramson et al, 2020).…”

Exploring Abnormal Brain Functional Connectivity in Healthy Adults, Depressive Disorder, and Generalized Anxiety Disorder through EEG Signals: A Machine Learning Approach for Triple Classification

“…While an increasing number of studies focus on diagnostic research for DD and GAD [ 12 ], fewer studies are conducted on triple-classification diagnoses with DD, GAD, and HC. More studies tend to analyze two-class scenarios (DD vs. HC, GAD vs. HC).…”

“…Furthermore, regarding the classification of mental disorders (including DD and AD) and HC groups, Xie et al employed a combination of EEG and convolutional neural networks (CNN), achieving a classification accuracy of 67.67% [ 43 ]. Qi et al used XGBoost to classify the EEG features of DD and GAD, achieving the highest classification accuracy of 99% [ 12 ]. The feature selection algorithm we proposed considers the relative importance of features across multiple training iterations.…”

“…In EEG signals, there are often numerous artifacts. In previous studies [ 11 , 12 , 13 ], we utilized an independent component analysis (ICA) combined with manual artifact removal to achieve satisfactory results. Additionally, traditional methods of EEG analysis involve linear analysis [ 14 ], nonlinear analysis [ 15 ], and brain functional connectivity analysis [ 16 ].…”

“…Among these, the Phase Lag Index (PLI) represents a prevalent method for analyzing brain functional connectivity, and its strength lies in its minimal sensitivity to volume conduction effects. It has been confirmed as an effective method for distinguishing mental disorders such as DD and GAD through the calculation of EEG features [ 11 , 12 , 17 ]. The research on Qi reveals that PLI, in comparison to linear and nonlinear features, exhibits superior classification performance [ 13 ].…”