MDD-TSVM: A novel semisupervised-based method for major depressive disorder detection using electroencephalogram signals

Major depressive disorder (MDD) is a common mental illness characterized by persistent feeling of depressed mood and loss of interest. It would cause, in a severe case, suicide behaviors. In clinical settings, automatic MDD detection is mainly based on electroencephalogram (EEG) signals with supervised learning techniques. However, supervised-based MDD detection methods encounter two ineviTable bottlenecks: firstly, such methods rely heavily on an EEG training dataset with MDD labels annotated by a physical therapist, leading to subjectivity and high cost; secondly, most of EEG signals are unlabeled in a real scenario. In this paper, a novel semisupervised-based MDD detection method named MDD-TSVM is presented. Specifically, the MDD-TSVM utilizes the semisupervised method of transductive support vector machine (TSVM) as its backbone, further dividing the unlabeled penalty item of the TSVM objective function into two pseudo-labeled penalty items with or without MDD. By such improvement, the MDD-SVM can make full use of labeled and unlabeled datasets as well as alleviate the class imbalance problem. Experiment results showed that our proposed MDD-TSVM achieved F1 score of 0.85 ± 0.05 and accuracy of 0.89 ± 0.03 on identifying MDD patients, which is superior to the state-of-the-art methods.

[1]  Julio López,et al.  Dealing with high-dimensional class-imbalanced datasets: Embedded feature selection for SVM classification , 2018, Appl. Soft Comput..

[2]  Dilip Singh Sisodia,et al.  Alcohol use disorder detection using EEG Signal features and flexible analytical wavelet transform , 2019, Biomed. Signal Process. Control..

[3]  Shifei Ding,et al.  An overview on semi-supervised support vector machine , 2017, Neural Computing and Applications.

[4]  R. Homan,et al.  Cerebral location of international 10-20 system electrode placement. , 1987, Electroencephalography and clinical neurophysiology.

[5]  Amit Konar,et al.  Adaptive Parameterized AdaBoost Algorithm with application in EEG Motor Imagery Classification , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[6]  B. Jeong,et al.  Data-driven analysis using multiple self-report questionnaires to identify college students at high risk of depressive disorder , 2020, Scientific Reports.

[7]  Charalampos Bratsas,et al.  Geriatric depression symptoms coexisting with cognitive decline: A comparison of classification methodologies , 2016, Biomed. Signal Process. Control..

[8]  Amit P. Sheth,et al.  Semi-Supervised Approach to Monitoring Clinical Depressive Symptoms in Social Media , 2017, ASONAM.

[9]  U. Rajendra Acharya,et al.  Automated Depression Detection Using Deep Representation and Sequence Learning with EEG Signals , 2019, Journal of Medical Systems.

[10]  Bin Hu,et al.  A Pervasive Approach to EEG-Based Depression Detection , 2018, Complex..

[11]  Bijan Raahemi,et al.  Data mining EEG signals in depression for their diagnostic value , 2015, BMC Medical Informatics and Decision Making.

[12]  Bin He,et al.  Quantifying and Characterizing Tonic Thermal Pain Across Subjects From EEG Data Using Random Forest Models , 2017, IEEE Transactions on Biomedical Engineering.

[13]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[14]  U. Rajendra Acharya,et al.  Automated EEG-based screening of depression using deep convolutional neural network , 2018, Comput. Methods Programs Biomed..

[15]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Xiaolong Xu,et al.  Lightweight EEG Classification Model Based on EEG-sensor with Few Channels , 2019, 2019 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC).

[17]  Philip Levis,et al.  Rehashing Kernel Evaluation in High Dimensions , 2019, ICML.

[18]  Soomaayeh Heysieattalab,et al.  Changes of the brain’s bioelectrical activity in cognition, consciousness, and some mental disorders , 2017, Medical journal of the Islamic Republic of Iran.

[19]  R. McIntyre,et al.  Early improvement in HAMD-17 and HAMD-7 scores predict response and remission in depressed patients treated with fluoxetine or electroconvulsive therapy. , 2019, Journal of affective disorders.

[20]  S.Dhananjay Kumar,et al.  Prediction of Depression from EEG Signal Using Long Short Term Memory(LSTM) , 2019, 2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI).

[21]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[22]  Swati Aggarwal,et al.  EEG Based Participant Independent Emotion Classification using Gradient Boosting Machines , 2018, 2018 IEEE 8th International Advance Computing Conference (IACC).

[23]  Thorsten Joachims,et al.  Transductive Inference for Text Classification using Support Vector Machines , 1999, ICML.

[24]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Ming Cao,et al.  Design and Implementation of Human-Computer Interaction Systems Based on Transfer Support Vector Machine and EEG Signal for Depression Patients' Emotion Recognition , 2021, J. Medical Imaging Health Informatics.

[26]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[27]  Xiaowei Li,et al.  A Deep Learning Approach for Mild Depression Recognition Based on Functional Connectivity Using Electroencephalography , 2020, Frontiers in Neuroscience.

[28]  Cuntai Guan,et al.  Enhancing EEG-Based Classification of Depression Patients Using Spatial Information , 2021, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[29]  Ahmad Shalbaf,et al.  Major depressive disorder diagnosis based on effective connectivity in EEG signals: a convolutional neural network and long short-term memory approach , 2020, Cognitive Neurodynamics.

[30]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[31]  Shervin Shirmohammadi,et al.  More attention, less deficit: Wearable EEG-based serious game for focus improvement , 2017, 2017 IEEE 5th International Conference on Serious Games and Applications for Health (SeGAH).

[32]  Sanchita Paul,et al.  Classification of Depression Patients and Normal Subjects Based on Electroencephalogram (EEG) Signal Using Alpha Power and Theta Asymmetry , 2019, Journal of Medical Systems.

[33]  Aiguo Song,et al.  Optimizing Single-Trial EEG Classification by Stationary Matrix Logistic Regression in Brain–Computer Interface , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[34]  Yasuhiro Omiya,et al.  Feasibility Study for Estimation of Depression Severity using Voice Analysis , 2018, 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[35]  Subha D. Puthankattil,et al.  CLASSIFICATION OF EEG SIGNALS IN NORMAL AND DEPRESSION CONDITIONS BY ANN USING RWE AND SIGNAL ENTROPY , 2012 .

[36]  Z. Nahas,et al.  Adaptation and initial validation of the Patient Health Questionnaire – 9 (PHQ-9) and the Generalized Anxiety Disorder – 7 Questionnaire (GAD-7) in an Arabic speaking Lebanese psychiatric outpatient sample , 2016, Psychiatry Research.

[37]  Xun Chen,et al.  Emotion Recognition From Multi-Channel EEG via Deep Forest , 2020, IEEE Journal of Biomedical and Health Informatics.

[38]  Alexander Kuc,et al.  Spatio-temporal cortical activity during a visual task accomplishing , 2019, 2019 3rd School on Dynamics of Complex Networks and their Application in Intellectual Robotics (DCNAIR).

[39]  Kazuhiko Nakamura,et al.  Items of the Montgomery-Åsberg Depression Rating Scale Associated With Response to Paroxetine Treatment in Patients With Major Depressive Disorder , 2016, Clinical neuropharmacology.

[40]  J. Cohn,et al.  Dyadic Behavior Analysis in Depression Severity Assessment Interviews , 2014, ICMI.

[41]  Xiang Li,et al.  PC-GAIN: Pseudo-label Conditional Generative Adversarial Imputation Networks for Incomplete Data , 2020, Neural Networks.

[42]  Kartik Audhkhasi,et al.  Improved Knowledge Distillation from Bi-Directional to Uni-Directional LSTM CTC for End-to-End Speech Recognition , 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

[43]  Joel Swendsen,et al.  Major depression in the national comorbidity survey-adolescent supplement: prevalence, correlates, and treatment. , 2015, Journal of the American Academy of Child and Adolescent Psychiatry.

[44]  Junhao Wen,et al.  Semi-supervised learning combining transductive support vector machine with active learning , 2015, Neurocomputing.

[45]  E Weinan,et al.  Can Shallow Neural Networks Beat the Curse of Dimensionality? A Mean Field Training Perspective , 2020, IEEE Transactions on Artificial Intelligence.