TY - JOUR
T1 - A robust deep-learning model to detect Major Depressive Disorder utilising EEG signals
AU - Anik, Israq Ahmed
AU - Kamal, A. H.M.
AU - Kabir, Muhammad Ashad
AU - Uddin, Shahadat
AU - Moni, Mohammad Ali
N1 - Publisher Copyright:
IEEE
PY - 2024
Y1 - 2024
N2 - Major Depressive Disorder (MDD), commonly called depression, is a prevalent psychiatric condition diagnosed via questionnaire-based mental status assessments. However, this method often yields inconsistent and inaccurate results. Furthermore, there is currently a lack of a comprehensive diagnostic framework for MDD that assesses various brainwaves (alpha, theta, gamma, etc.) of EEG signals as potential biomarkers, aiming to identify the most effective one for achieving accurate and robust diagnostic outcomes. To address this issue, we propose an innovative approach employing a deep convolutional neural network (DCNN) for MDD diagnosis utilising the brainwaves present in electroencephalogram (EEG) signals. Our proposed model, an extended 11-layer one-dimensional convolutional neural network (Ex-1DCNN), is designed to automatically learn from input EEG signals, foregoing the need for manual feature selection. By harnessing intrinsic brainwave patterns, our model demonstrates adaptability in classifying EEG signals into depressive and healthy categories. We have conducted an extensive analysis to identify optimal brainwave features and epoch duration for accurate MDD diagnosis. Leveraging EEG data from 34 MDD patients and 30 healthy subjects, we have identified that the Gamma brainwave at a 15-second epoch duration is the most effective configuration, achieving an accuracy of 99.60%, sensitivity of 100%, specificity of 99.21%, and an F1-score of 99.60%. This study highlights the potential of deep learning techniques in streamlining the diagnostic process for MDD and offering a reliable aid to clinicians in MDD diagnosis.
AB - Major Depressive Disorder (MDD), commonly called depression, is a prevalent psychiatric condition diagnosed via questionnaire-based mental status assessments. However, this method often yields inconsistent and inaccurate results. Furthermore, there is currently a lack of a comprehensive diagnostic framework for MDD that assesses various brainwaves (alpha, theta, gamma, etc.) of EEG signals as potential biomarkers, aiming to identify the most effective one for achieving accurate and robust diagnostic outcomes. To address this issue, we propose an innovative approach employing a deep convolutional neural network (DCNN) for MDD diagnosis utilising the brainwaves present in electroencephalogram (EEG) signals. Our proposed model, an extended 11-layer one-dimensional convolutional neural network (Ex-1DCNN), is designed to automatically learn from input EEG signals, foregoing the need for manual feature selection. By harnessing intrinsic brainwave patterns, our model demonstrates adaptability in classifying EEG signals into depressive and healthy categories. We have conducted an extensive analysis to identify optimal brainwave features and epoch duration for accurate MDD diagnosis. Leveraging EEG data from 34 MDD patients and 30 healthy subjects, we have identified that the Gamma brainwave at a 15-second epoch duration is the most effective configuration, achieving an accuracy of 99.60%, sensitivity of 100%, specificity of 99.21%, and an F1-score of 99.60%. This study highlights the potential of deep learning techniques in streamlining the diagnostic process for MDD and offering a reliable aid to clinicians in MDD diagnosis.
KW - Brain modeling
KW - Brainwaves
KW - CNN
KW - Deep Learning
KW - Deep learning
KW - Depression
KW - EEG
KW - Electroencephalography
KW - Feature extraction
KW - Major Depressive Disorder (MDD)
KW - Noise
KW - Support vector machines
UR - http://www.scopus.com/inward/record.url?scp=85192196223&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85192196223&partnerID=8YFLogxK
U2 - 10.1109/TAI.2024.3394792
DO - 10.1109/TAI.2024.3394792
M3 - Article
AN - SCOPUS:85192196223
SN - 2691-4581
VL - 5
SP - 4938
EP - 4947
JO - IEEE Transactions on Artificial Intelligence
JF - IEEE Transactions on Artificial Intelligence
IS - 10
ER -