Multivariate Pattern Analysis of EEG-Based Functional Connectivity: A Study on the Identification of Depression

Abstract

Resting-state electroencephalography (EEG) studies have shown significant group differences in functional connectivity networks between patients with depression and healthy controls. The present study aims to identify the altered EEG resting-state functional connectivity patterns of depressed patients, which can be used to test the feasibility of distinguishing individuals with depression from healthy controls. In the present study, the phase lag index was employed to construct functional connectivity matrices. An altered Kendall rank correlation coefficient was used to identify the features with high discriminative power, and several classifiers were employed to classify a total of 27 depressed patients and 28 demographically matched healthy volunteers. Permutation tests were used to evaluate classifier performance. The best classification results demonstrate that more than 92% of subjects were correctly classified by binary linear SVM through leave-one-out cross-validation for the full frequency band, and the AUC was 0.98. Our findings suggest that the depression affects brain activity in nearly the whole cortex and that changes in brain oscillation patterns in the delta, theta, and beta frequency bands are more significant than those in the alpha frequency band. The current study sheds new light on the pathological mechanism of depression and suggests that EEG restingstate functional connectivity analysis may identify potentially effective biomarkers for its clinical diagnosis.

Predicting Depression Symptoms in an Arabic Psychological Forum

“…Recall = TP TP + FN (8) F − Score = Precision × Recall Precision + Recall (9) Additional evaluation metrics are the area under the curve (AUC) and the receiver operating characteristic curve (ROC). ROC corresponds to the true positive rate (TPR) versus the false positive rate (FPR), which is used to evaluate the performance of a model with binary classes under various thresholds of classification.…”

“…However, these data require advance analysis tools such as natural language processing (NLP), data mining, and machine learning for the extraction of valuable information, e.g., for detecting or predicting depression. There are many approaches for predicting mental disorders in English-language platforms, which effectively contribute to making therapy more efficient [5]- [8]. References [5], [7], [8] used electroencephalogram (EEG) data to discriminate between cases with versus without depression and applied various processing approaches.…”

“…There are many approaches for predicting mental disorders in English-language platforms, which effectively contribute to making therapy more efficient [5]- [8]. References [5], [7], [8] used electroencephalogram (EEG) data to discriminate between cases with versus without depression and applied various processing approaches. Reference [5] classified the selected features, which include the Bhattacharya distance and the t-test result, using logistic regression (LR), support vector machine (SVM) and naïve Bayes (NB) classifiers with 10-fold cross-validation.…”

“…Reference [7] utilized forehead EEG in conjunction with sensors and algorithms to process the generated signals. Reference [8] collected EEG data from a resting state paradigm and applied SVM, NB, decision tree (DT) and K-nearest neighbour (KNN). Reference [6] utilized NLP to detect depression from social media by creating a lexicon of terms that are commonly used by depressed users.…”

Brain Functional Networks Based on Resting-State EEG Data for Major Depressive Disorder Analysis and Classification

“…N OWADAYS major depressive disorder (MDD) has quietly become the second largest disease in the worldwide [1], and its typical symptoms include slow thinking, persistent low mood, anhedonia, and cognition impairment of brain function [2]. According to data disclosed by the World Health Organization (WHO), there are more than 350 million people suffering from MDD and the growth rate of patients in the past decade is about 18% [3]. It is estimated that about 850,000 suicides caused by MDD each year [4], accounting for 53.7% of all suicides [5].…”