Ubiquitous Depression Detection of Sleep Physiological Data by Using Combination Learning and Functional Networks

Nowadays, depression has become a common mental disorder with high morbidity and mortality. Due to the limitations of traditional interview-based depression detection, it has become an urgent problem to realize objective, convenient and fast detection. This study is to explore ubiquitous methods of depression detection based on combination learning and functional networks, using sleep physiological data. Sleep physiological data were collected using a portable physiological data instrument, and then preprocess and extract several related features. We applied combination learning to discover the best sleep stage, the optimal features subset, and the most effective classifier, which are hidden behind physiological features, to detect depression. Physiological features in the optimal feature subset based on Euclidean distance are mapped to nodes to construct the functional network. The optimal feature subset was combined with the functional network attributes as the input of the most effective classifier to get the ultimate performance of depression detection. Controlled trials based on ubiquitous sleep physiological data were conducted on different genders. Experiments show that the best results for male and female were derived from slow wave sleep (SWS) and rapid eye movement (REM), with performances of 92.21% and 94.56%, AUC of 0.944 and 0.971, respectively. Thus, our study may provide an effective and ubiquitous method for detect depression.

[1]  Asoke K. Nandi,et al.  Significantly Fast and Robust Fuzzy C-Means Clustering Algorithm Based on Morphological Reconstruction and Membership Filtering , 2018, IEEE Transactions on Fuzzy Systems.

[2]  Bin Hu,et al.  Attention Recognition in EEG-Based Affective Learning Research Using CFS+KNN Algorithm , 2018, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[3]  L. Arnold,et al.  Lyapunov exponents: A survey , 1986 .

[4]  T. Cecchin,et al.  Seizure lateralization in scalp EEG using Hjorth parameters , 2010, Clinical Neurophysiology.

[5]  Theiler,et al.  Spurious dimension from correlation algorithms applied to limited time-series data. , 1986, Physical review. A, General physics.

[6]  Wang Bing-Hong,et al.  Node importance measurement based on the degree and clustering coefficient information , 2013 .

[7]  A. Borbély,et al.  Sleep, sleep deprivation and depression. A hypothesis derived from a model of sleep regulation. , 1982, Human neurobiology.

[8]  Sana Tmar-Ben Hamida,et al.  Deep Learning and Insomnia: Assisting Clinicians With Their Diagnosis , 2017, IEEE Journal of Biomedical and Health Informatics.

[9]  Xiang Zhang,et al.  HyCLASSS: A Hybrid Classifier for Automatic Sleep Stage Scoring , 2018, IEEE Journal of Biomedical and Health Informatics.

[10]  Urbano Nunes,et al.  Automatic sleep staging: A computer assisted approach for optimal combination of features and polysomnographic channels , 2013, Expert Syst. Appl..

[11]  D. Dijk,et al.  Sex differences in the sleep EEG of young adults: visual scoring and spectral analysis. , 1989, Sleep.

[12]  H. McNulty,et al.  Diet, nutrition and the ageing brain: current evidence and new directions , 2018, Proceedings of the Nutrition Society.

[13]  Natheer Khasawneh,et al.  Automated sleep stage identification system based on time-frequency analysis of a single EEG channel and random forest classifier , 2012, Comput. Methods Programs Biomed..

[14]  D. Riemann,et al.  REM sleep in depression—an overview , 1993 .

[15]  Laura Manea,et al.  Screening and case finding for major depressive disorder using the Patient Health Questionnaire (PHQ-9): a meta-analysis. , 2015, General hospital psychiatry.

[16]  Joel E. W. Koh,et al.  Computer-Aided Diagnosis of Depression Using EEG Signals , 2015, European Neurology.

[17]  Zhenyu Liu,et al.  Investigation of different speech types and emotions for detecting depression using different classifiers , 2017, Speech Commun..

[18]  Xiang Li,et al.  Deep fusion of multi-channel neurophysiological signal for emotion recognition and monitoring , 2017, Int. J. Data Min. Bioinform..

[19]  U. Rajendra Acharya,et al.  Non-linear analysis of EEG signals at various sleep stages , 2005, Comput. Methods Programs Biomed..

[20]  Bingtao Zhang,et al.  Dual-modal Physiological Feature Fusion-based Sleep Recognition Using CFS and RF Algorithm , 2019, International Journal of Automation and Computing.

[21]  Henri Depoortere,et al.  Evaluation of the stability and quality of sleep using hjorth's descriptors , 1993, Physiology & Behavior.

[22]  H. Akaike.  Fitting autoregressive models for prediction , 1969 .

[23]  Dimitrios Hatzinakos,et al.  ECG Pattern Analysis for Emotion Detection , 2012, IEEE Transactions on Affective Computing.

[24]  E. Arrigoni,et al.  Neural Circuitry of Wakefulness and Sleep , 2017, Neuron.

[25]  Bin Hu,et al.  Effective brain network analysis with resting-state EEG data: a comparison between heroin abstinent and non-addicted subjects , 2017, Journal of neural engineering.

[26]  Bin Hu,et al.  EEG-based mild depressive detection using feature selection methods and classifiers , 2016, Comput. Methods Programs Biomed..

[27]  Leen Kim,et al.  Sleep and sleep disorders in depression , 2018 .

[28]  Bin Hu,et al.  Study on Feature Selection Methods for Depression Detection Using Three-Electrode EEG Data , 2018, Interdisciplinary Sciences: Computational Life Sciences.

[29]  Xintao Hu,et al.  A Comparative Study of Theoretical Graph Models for Characterizing Structural Networks of Human Brain , 2013, Int. J. Biomed. Imaging.

[30]  R. Armitage,et al.  Sleep EEG, depression and gender. , 2001, Sleep medicine reviews.

[31]  Haiyan Zhou,et al.  Randomized EEG functional brain networks in major depressive disorders with greater resilience and lower rich-club coefficient , 2018, Clinical Neurophysiology.

[32]  B. Hjorth.  EEG analysis based on time domain properties. , 1970, Electroencephalography and clinical neurophysiology.

[33]  J. Lépine,et al.  The increasing burden of depression , 2011, Neuropsychiatric disease and treatment.

[34]  E. Wolpert.  A Manual of Standardized Terminology, Techniques and Scoring System for Sleep Stages of Human Subjects. , 1969 .

[35]  P. Danielsson.  Euclidean distance mapping , 1980 .

[36]  Gregory D. Roach,et al.  Alternatives to polysomnography (PSG): A validation of wrist actigraphy and a partial-PSG system , 2014, Behavior Research Methods.

[37]  Jing Zhu,et al.  Multivariate Pattern Analysis of EEG-Based Functional Connectivity: A Study on the Identification of Depression , 2019, IEEE Access.

[38]  R. Huber,et al.  Increased frontal sleep slow wave activity in adolescents with major depression , 2015, NeuroImage: Clinical.

[39]  Bin Hu,et al.  A Case-Based Reasoning Model for Depression Based on Three-Electrode EEG Data , 2020, IEEE Transactions on Affective Computing.

[40]  P. Lovibond,et al.  The structure of negative emotional states: comparison of the Depression Anxiety Stress Scales (DASS) with the Beck Depression and Anxiety Inventories. , 1995, Behaviour research and therapy.

[41]  Bin Hu,et al.  EEG-Based Mild Depressive Detection Using Differential Evolution , 2019, IEEE Access.

[42]  Xin Li,et al.  Automated Depression Diagnosis Based on Facial Dynamic Analysis and Sparse Coding , 2015, IEEE Transactions on Information Forensics and Security.

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

[44]  Stefano Sello,et al.  Cross-correlation time-frequency analysis for multiple EMG signals in Parkinson's disease: a wavelet approach. , 2003, Medical engineering & physics.

[45]  Hong Liu,et al.  EEG-Based Automatic Sleep Staging Using Ontology and Weighting Feature Analysis , 2018, Comput. Math. Methods Medicine.

[46]  Jing Zhu,et al.  Graph Theory Analysis of Functional Connectivity in Major Depression Disorder With High-Density Resting State EEG Data , 2019, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[47]  A J Rush,et al.  Biological rhythm disturbance in depression: temporal coherence of ultradian sleep EEG rhythms , 1999, Psychological Medicine.

[48]  N Sitaram,et al.  Sleep and depression. , 1987, Psychopathology.

[49]  Sheng-Fu Liang,et al.  Automatic Stage Scoring of Single-Channel Sleep EEG by Using Multiscale Entropy and Autoregressive Models , 2012, IEEE Transactions on Instrumentation and Measurement.

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

[51]  JENNIFER A. BUNN,et al.  Current State of Commercial Wearable Technology in Physical Activity Monitoring 2015–2017 , 2018, International journal of exercise science.

[52]  Eckehard Olbrich,et al.  Dynamics of human sleep EEG , 2003, Neurocomputing.

[53]  Gerd Wagner,et al.  Fronto-cingulate effective connectivity in major depression: A study with fMRI and dynamic causal modeling , 2008, NeuroImage.

[54]  Ciyong Lu,et al.  Association between sleep duration, suicidal ideation, and suicidal attempts among Chinese adolescents: The moderating role of depressive symptoms. , 2017, Journal of affective disorders.

[55]  D. Kupfer,et al.  All-night spectral analysis of the sleep EEG in untreated depressives and normal controls , 1984, Psychiatry Research.

[56]  Daniel J Buysse,et al.  Sleep, gender, and depression: An analysis of gender effects on the electroencephalographic sleep of 302 depressed outpatients , 1990, Biological Psychiatry.

[57]  Jing Zhu,et al.  A Resting-State Brain Functional Network Study in MDD Based on Minimum Spanning Tree Analysis and the Hierarchical Clustering , 2017, Complex..

[58]  Bin Hu,et al.  An EEG-based study on coherence and brain networks in mild depression cognitive process , 2016, 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[59]  Mark A. Hall,et al.  Correlation-based Feature Selection for Machine Learning , 2003 .