A dimensional approach to affective disorder: The relations between Scl-90 subdimensions and QEEG parameters

Non-suicidal Self-injury and Quantified Electroencephalogram in Adolescents and Young Adults with Depression

Objective

: This study investigated the association between non-suicidal self-injury (NSSI) and quantified electroencephalogram (QEEG) in patients with depression. We aimed to identify clinical features of NSSI and differences in QEEG findings.

Methods

: This retrospective study used the medical records of 52 inpatients with major depressive episodes, aged from 15 to 30. The patients were categorized according to their history of NSSI. Their main diagnosis and sex were also considered. To evaluate clinical symptoms, self-reported scales were used. The absolute power and the Z-scores of various waves were included.

Results

: NSSI was associated with suicidal ideations (p = 0.001) and trauma history (p = 0.014). In the binary logistic regression analysis, the Z-score of absolute alpha power was higher on the FP2 node (p = 0.029), lower on the F4 node (p = 0.029) in the NSSI group. The absolute high beta power in the NSSI group was higher on the FP2 and the F3 node, but lower on the F7 and F8 node. Patients with NSSI showed higher Z-score of the absolute delta power at the FP2 node (p = 0.044). The absolute gamma power was higher on the FP2 (p = 0.012) and the F3 node (0.043), lower on the FP1 (p = 0.019) and the F7 node (0.018) in the NSSI group. The absolute high gamma power at the FP2 (p = 0.017) and F8 nodes (p = 0.045) were higher in the NSSI group.

Conclusion

: Patients with NSSI may have clinical features distinct from those of patients without NSSI. QEEG results have shown some differences, although it is less applicable due to some limitations.

Exploring Adaptive Graph Topologies and Temporal Graph Networks for EEG-Based Depression Detection

In recent years, Graph Neural Networks (GNNs) based on deep learning techniques have achieved promising results in EEG-based depression detection tasks but still have some limitations. Firstly, most existing GNN-based methods use pre-computed graph adjacency matrices, which ignore the differences in brain networks between individuals. Additionally, methods based on graph-structured data do not consider the temporal dependency information of brain networks. To address these issues, we propose a deep learning algorithm that explores adaptive graph topologies and temporal graph networks for EEG-based depression detection. Specifically, we designed an Adaptive Graph Topology Generation (AGTG) module that can adaptively model the real-time connectivity of the brain networks, revealing differences between individuals. In addition, we designed a Graph Convolutional Gated Recurrent Unit (GCGRU) module to capture the temporal dynamical changes of brain networks. To further explore the differential features between depressed and healthy individuals, we adopt Graph Topology-based Max-Pooling (GTMP) module to extract graph representation vectors accurately. We conduct a comparative analysis with several advanced algorithms on both public and our own datasets. The results reveal that our final model achieves the highest Area Under the Receiver Operating Characteristic Curve (AUROC) on both datasets, with values of 83% and 99%, respectively. Furthermore, we perform extensive validation experiments demonstrating our proposed method's effectiveness and advantages. Finally, we present a comprehensive discussion on the differences in brain networks between healthy and depressed individuals based on the outputs of our final model's AGTG and GTMP modules.