Graph-Based Analysis of Brain Connectivity in Children and Adolescents Diagnosed with Major Depressive Disorder Compared to Aged-matched Healthy Control: An EEG Study

• Published in: IEEE Signal Processing in Medicine and Biology Symposium pp. 1 - 5
• Main Authors: Bagh, K., Najafabadi, A. Jahanian
• Format: Conference Proceeding
• Language: English
• Published: IEEE 07.12.2024
• Subjects: Brain modeling; Depression; Electroencephalography; Measurement; Medical diagnostic imaging; Neuroscience; Pediatrics; Psychology; Random forests; Signal processing
• ISSN: 2473-716X
• DOI: 10.1109/SPMB62441.2024.10842258

Major Depressive Disorder (MDD) is a complex and heterogeneous psychiatric condition that affects individuals across the lifespan, from childhood to old age [1] . Its widespread prevalence worldwide highlights the urgent need for advancements in early diagnosis and improved treatment strategies, particularly in pediatric populations. Achieving accurate early diagnosis, especially through electroencephalography (EEG), demands a multidisciplinary approach that brings together expertise in neuroscience, psychology, and computational methods. This collaborative effort is essential to meet the needs of both researchers and clinicians in addressing the challenges of MDD. In this research, in line with our previous studies focused on MDD [2] , [3] , [4] , we employ a graph-based network applied to resting-state EEG Functional Connectivity (FC) to investigate and gain deeper insights into the brain networks involved in MDD in children and adolescents. Graph-based networks are among the most widely used deep learning models for representing graph data structures, such as networks, due to their exceptional ability to handle complex pairwise relationships [5] , [6] . These relationships span both imaging and non-imaging features across different subjects, enabling more detailed and comprehensive data analysis [7] . The motivation behind this research is to enhance classification diagnostic models for MDD in children and adolescents by comparing them with healthy, age-matched controls. While most studies have focused on fMRI data, we emphasize the use of high-density EEG, a noninvasive and widely recommended method with high temporal resolution for measuring brain functional activity [8] .