Severity Assessment of Social Anxiety Disorder Using Deep Learning Models on Brain Effective Connectivity

Abstract

Neuroimaging investigations have proven that social anxiety disorder (SAD) is associated with aberrations in the connectivity of human brain functions.The assessment of the effective connectivity (EC) of the brain and its impact on the detection and medication of neurodegenerative pathophysiology is hence a crucial concern that needs to be addressed. Nevertheless, there are no clinically certain diagnostic biomarkers that can be linked to SAD. Therefore, investigating neural connectivity biomarkers of SAD based on deep learning models (DL) has a promising approach with its recent underlined potential results. In this study, an electroencephalography (EEG)-based detection model for SAD is constructed through directed causal influences combined with a deep convolutional neural network (CNN) and the long shortterm memory (LSTM). The EEG data were classified by applying three different DL models, namely, CNN, LSTM, and CNN+LSTM to discriminate the severity of SAD (severe, moderate, mild) and healthy controls (HC) at different frequency bands (delta, theta, alpha, low beta, and high beta) in the default mode network (DMN) under resting-state condition. The DL model uses the EC features as input, which are derived from the cortical correlation within different EEG rhythms for certain cortical areas that are more susceptible to SAD. Experimental results revealed that the proposed model (CNN+LSTM) outperforms the other models in SAD recognition. For our dataset, the highest recognition accuracies of 92.86%, 92.86%, 96.43%, and 89.29%, specificities of 95.24%, 95.24%, 100%, and 90.91%, and sensitivities of 85.71%, 85.71%, 87.50%, and 83.33% were achieved by using CNN+LSTM model for severe, moderate, mild, and HC, respectively. The fundamental contribution of this analysis is the characterization of neural brain features using different DL models to categorize the severity of SAD, which can represent a potential biomarker for SAD.INDEX TERMS Effective connectivity network, convolutional neural networks (CNNs), social anxiety disorder (SAD), default mode network (DMN), deep learning models, partial directed coherence (PDC), Electroencephalogram (EEG), human brain mapping.

Aberrated Multidimensional EEG Characteristics in Patients with Generalized Anxiety Disorder: A Machine-Learning Based Analysis Framework

“…We expect to reveal neurobiological markers via the proposed analytical framework. In addition, among the existed studies [ 26 , 27 , 28 ], the highest classification accuracy between GAD and HC group, to our knowledge, is 93% with a deep learning model using task EEG signals. We also hope the proposed analysis framework could provide an effective and reliable GAD identification method to achieve better classification performance with machine learning models.…”

“…Park et al reported their highest accuracy of 91.03% with elastic net classifier using resting-state EEG data [ 28 ]. Al-Ezzi et al achieved the accuracies of 92.86%, 92.86%, 96.43%, and 89.29% for severe, moderate, mild anxiety and HC by using a deep learning model (convolutional neural network + long short-term memory) with task-state EEG data, respectively [ 27 ]. Moreover, lower classification accuracies were reported using other modalities data [ 50 , 51 , 52 ], such as an accuracy of 87.4% with Self-Rating Anxiety Scale questionnaires data [ 12 ], and an accuracy of 86% with language-based features [ 53 ].…”

Epileptic Seizures Detection in EEG Signals Using Fusion Handcrafted and Deep Learning Features

“…Additionally, another future work is to use fuzzy methods [114,115] in epileptic seizure detection. In other future works, effective connectivity techniques may be used to diagnose epileptic seizures [116][117][118]; first, EEG signals are transformed into 2D images using effective connectivity methods. Then, these 2 D images are applied to different 2D deep learning networks.…”

Machine Learning for Anxiety Detection Using Biosignals: A Review

“…We noted a majority of male participants in the studies, and more than half did not report the gender of their participants. Only two studies, including those by Al-Ezzi et al [ 25 ] and Perpetuini et al [ 26 ], used a sample size of more than 80 subjects. Four studies had around 55 to 57 subjects, three had between 20 and 40 subjects, and the rest had less than 20 subjects.…”

“…The comparison between anxiety and anxiety disorder is one of the limitations of this review. Indeed, some studies [ 23 , 24 , 26 , 27 , 31 , 35 , 37 ], focus on detecting anxiety as an induced experience in danger, whereas others [ 15 , 16 , 19 , 25 , 26 , 28 , 32 ] aim to detect ADs subjects which need a timeline to be categorized, from health control.…”