| Title:
|
Cross-Frequency Phase–Amplitude Coupling–Derived EEG Connectivity for MDD Classification
|
| Author(s):
|
1
|
| Subject:
|
Personalized Interventions and Diagnosis of Complex Neurological Disorders
|
|
|
|
Presenter Author:
|
|
| Name:
|
Shabnam GholamiMehrabadi
|
|
|
|
Author:
|
|
| Name 1:
|
Shabnam GholamiMehrabadi - Corresponding - Presenter
|
| Affiliation 1:
|
Graduate Master of Science in Biomedical Engineering, Islamic Azad University, Qazvin, Iran
|
|
|
| Name 2:
|
Ali Motie Nasrabadi
|
| Affiliation 2:
|
Department of Biomedical Engineering, Islamic Azad University, Qazvin, Iran
|
|
|
| Name 3:
|
|
| Affiliation 3:
|
|
|
|
| Name 4:
|
|
| Affiliation 4:
|
|
|
|
| Name 5:
|
|
| Affiliation 5:
|
|
|
|
| Name 6:
|
|
| Affiliation 6:
|
|
|
|
| Name 7:
|
|
| Affiliation 7:
|
|
|
|
| Name 8:
|
|
| Affiliation 8:
|
|
|
|
| Name 9:
|
|
| Affiliation 9:
|
|
|
|
| Name 10:
|
|
| Affiliation 10:
|
|
|
|
Abstract
|
Original Research
|
|
introduction :
|
Depression is one of the most prevalent mental health disorders worldwide, and early and accurate diagnosis can substantially improve treatment outcomes. Previous studies suggest that depression affects both neural oscillatory activity and large-scale brain functional connectivity. In this context, phase–amplitude coupling (PAC) has emerged as a promising biomarker for characterizing abnormal cross-frequency interactions in the depressed brain.
This study aimed to investigate differences in Gaussian copula–based PAC-derived functional brain connectivity between healthy individuals and patients with major depressive disorder (MDD) using electroencephalography (EEG) signals under eyes-open and eyes-closed resting-state conditions.
|
|
Methods:
|
EEG recordings from 34 patients with MDD and 30 healthy controls were analyzed. Theta–gamma PAC was estimated using the Gaussian Copula Mutual Information approach. A temporal segmentation strategy was applied, in which 2-second epochs were aggregated into 10-second feature matrices to enhance data variability. PAC-derived connectivity features, including raw matrices, statistical descriptors, and PCA-reduced features, were classified using support vector machine (SVM), linear discriminant analysis (LDA), k-nearest neighbor (KNN), and multilayer perceptron (MLP) classifiers.
|
|
Results:
|
Among the evaluated classifiers, the MLP achieved the highest performance, reaching a cross-validation accuracy of 83% in the eyes-open condition and a test accuracy of 75 ± 5%, with 80% sensitivity and 66% specificity. Significant PAC connectivity differences between depressed and healthy individuals were predominantly observed in frontal–parietal connections (FP2–PZ and F3–P3) during the eyes-open condition, and in parietal–central connections (C3–P3, P3–P4, and C4–PZ) during the eyes-closed condition.
|
|
Conclusion:
|
The findings demonstrate that phase–amplitude coupling captures meaningful alterations in functional brain connectivity associated with depression. PAC-based connectivity features combined with machine learning classifiers show strong potential as objective biomarkers to support the diagnosis of depressive disorders.
|
| Attachment:
|
|
| Keywords:
|
Depressive disorder, brain functional connectivity, phase-amplitude coupling, classification, support vector machine, machine learning, multilayer perceptron
|
| Key message:
|
|
| Do you want your abstract to be indexed, if this is selected as one of the top 100
articles?
|
