Discrimination of Depression Levels Using Machine Learning Methods on EEG Signals

Mohammadi, Yousef; Hajian, Mojtaba; Moradi, Mohammad Hassan

doi:10.1109/iraniancee.2019.8786540

Cited by 21 publications

(23 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…31 As mentioned above, depression can alter brain activity, and causes an abnormal activity in the brain. In some cases, in addition to using the characteristics of abnormal activity, not only can we classify the depression level as a binary concept of depressed and healthy, 6,7,[32][33][34] but we can also provide a continuous estimation of the depression severity, such as BDI and HDRS. For instance, Jiang et al 35 used spectral features extracted from magnetoencephalography (MEG) signals as inputs to the Bayesian linear regression model to predict the severity of depression (HDRS scores).…”

Section: Introductionmentioning

confidence: 99%

Prediction of Depression Severity Scores Based on Functional Connectivity and Complexity of the EEG Signal

Mohammadi

Moradi

2020

Clin EEG Neurosci

Self Cite

View full text Add to dashboard Cite

Background Depression is one of the most common mental disorders and the leading cause of functional disabilities. This study aims to specify whether functional connectivity and complexity of brain activity can predict the severity of depression (Beck Depression Inventory–II scores). Methods Resting-state, eyes-closed EEG data were recorded from 60 depressed patients. A phase synchronization measure was used to estimate functional connectivity between all pairs of the EEG channels in the delta (1-4 Hz), theta (4-8 Hz), alpha (8-13 Hz), and beta (13-30 Hz) frequency bands. To quantify the local value of functional connectivity, 2 graph theory metrics, degree, and clustering coefficient (CC), were measured. Moreover, Lempel-Ziv complexity (LZC) and fuzzy entropy (FuzzyEn) were used to measure the complexity of the EEG signal. Results Through correlation analysis, a significant negative relationship was found between graph metrics and depression severity in the alpha band. This association was strongly positive for the complexity measures in alpha and delta bands. Also, the linear regression model represented a substantial performance of depression severity prediction based on EEG features of the alpha band ( r = 0.839; P < .0001, root mean square error score of 7.69). Conclusion We found that the brain activity of patients with depression was related to depression severity. Abnormal brain activity reflects an increase in the severity of depression. The presented regression model provides a quantitative depression severity prediction, which can inform the development of EEG state and exhibit potential desirable application for the medical treatment of the depressive disorder.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of Depression Severity Scores Based on Functional Connectivity and Complexity of the EEG Signal

Mohammadi

Moradi

2020

Clin EEG Neurosci

Self Cite

View full text Add to dashboard Cite

show abstract

“…(2021) could prove to be a more a reliable and less controversial means to identify EEG patterns as biomarkers of mental illness. In the field of EEG-based classification, there have already been several successful demonstrations regarding classification of depression (Acharya et al, 2018;Hosseinifard et al, 2013;Wan et al, 2019), diagnosis of depression subtypes (Zelenina & Prata, 2019), depression severity (Mohammadi et al, 2019), and treatment response (Hasanzadeh et al, 2019;Jaworska et al, 2019;Khodayari-Rostamabad et al, 2013).…”

Section: Discussionmentioning

confidence: 99%

Enabling #EEGManyLabs: Quality in Automatically Preprocessed EEG Data and Psychopathological Associations of Frontal Alpha Asymmetry

Schürmann¹

2022

Preprint

View full text Add to dashboard Cite

Neuroscience is facing a replication crisis. Little effort is invested in replication projects and low power in many studies indicates a potentially poor state of research. To assess replicability of EEG research, the #EEGManyLabs project aims to reproduce the most influential original EEG studies. A spin-off to the main project shall investigate the relationship between frontal alpha asymmetries and psychopathological symptoms, the predictive qualities of which have lately been considered controversial. To ensure that preprocessing of EEG data can be conducted automatically (via Automagic), we tested 47 healthy participants in an EEG resting state paradigm and collected psychopathological measures. We analyzed reliability and quality of manual and automated preprocessing and performed multiple regressions to investigate the association of frontal alpha asymmetries and depression, worry, trait anxiety and COVID-19 related worry. We hypothesized comparably good interrater reliability of preprocessing methods and higher data quality in automatically preprocessed data. We expected associations of leftward frontal alpha asymmetries and higher depression and anxiety scores and significant associations of rightward frontal alpha asymmetries and higher worrying and COVID-19- related worrying. Interrater reliability of preprocessing methods was mostly good, automatically preprocessed data achieved higher quality scores than manually preprocessed data. We uncovered an association of relative rightward lateralization of alpha power at one electrode pair and depressive symptoms. No further associations of interest emerged. We conclude that Automagic is an appropriate tool for large-scale preprocessing. Findings regarding associations of frontal alpha asymmetries and psychopathology likely stem from sample limitations and shrinking effect sizes.

show abstract

“…Mohammadi et al [65] proposed a fuzzy function-based ML classifier trained by three nonlinear features (fuzzy entropy, Katz fractal dimension, and fuzzy fractal dimension) to distinguish depression levels. To reflect variation of brain activities, the researchers collected EEG signals from depression patient groups, based on which all the features were calculated.…”

Section: Discussionmentioning

confidence: 99%

Depression Level Classification Using Machine Learning Classifiers Based on Actigraphy Data

Choi

Han

2021

IEEE Access

View full text Add to dashboard Cite

Estimating and classifying depression status are critical in the clinical and psychological domains to map the course of treatment. Prior researchers used biosignal time-series data to reflect the variation in factors associated with depression. In addition, machine learning algorithms were applied to determine the underlying relationships between depressive symptoms and these factors. In this study, we introduce a classification framework for depression levels using actigraphy data based on machine learning algorithms. Fourteen circadian rhythm features (minimum, amplitude, alpha, beta, acrotime, upmesor, downmesor, mesor, f_pseudo, interdaily stability (IS), intradaily variability (IV), relative amplitude (RA), M10, and L5) extracted from accelerometer-based actigraphy data were used to model depression status with survey variables. Six evaluation metrics (accuracy, precision, recall, F1-score, receiver operating characteristic curve, and area under the curve) were applied to validate the performance of the proposed framework. Among the four candidate classifiers (XGBoost classifier, support vector classifier, multilayer perceptron, and logistic regression), the XGBoost classifier was the best at classifying depression levels. Moreover, we confirmed that the actigraphy data of two days were optimal for feature extraction and classification. The results of this study provide novel insights into the relationship between depression and physical activity in terms of both identification of depression and application of actigraphy data. INDEX TERMSAccelerometer-based actigraphy data, classification algorithm, circadian rhythm, depression level, machine learning, multi-level classification, physical activity.

show abstract

Discrimination of Depression Levels Using Machine Learning Methods on EEG Signals

Cited by 21 publications

References 18 publications

Prediction of Depression Severity Scores Based on Functional Connectivity and Complexity of the EEG Signal

Prediction of Depression Severity Scores Based on Functional Connectivity and Complexity of the EEG Signal

Enabling #EEGManyLabs: Quality in Automatically Preprocessed EEG Data and Psychopathological Associations of Frontal Alpha Asymmetry

Depression Level Classification Using Machine Learning Classifiers Based on Actigraphy Data

Contact Info

Product

Resources

About