3. AUTOMATED TECHNIQUES FOR IDENTIFYING DEPRESSION FROM EEG

The modern period is often called “the age of melancholy” [1]. Depression or melancholy is one of the common underdiagnosed diseases in clinical psychiatry [2]. Primary (i.e. which has no other associated cause) disorders of affect (mood) and thought are considered psychobiologic manifestations of abnormal brain mechanism. However, patients may also present with depression secondary to metabolic derangements, drug toxicity (e.g. antihypertensive drugs like reserpine, alpha methyl dopa, clonidine, propranolol; other drugs like levo-dopa, corticosteroids and amphetamine withdrawal may precipitate depression), influenza, hyperthyroidism, focal cerebral lesions, epilepsy or degenerative brain diseases [3]. There is some commonalty in the overt emotional behavior in all mammalian species from mouse to man. Burghardt [4] urges neuroscientists to join the collective effort to address the entire issue of mentalism, especially to use electroencephalography for comparing humans to animals where specific animal behavioral models of human mental states are known or can be developed. In most cases, before performing experiments with human beings, it is customary to test the validity of the results in lower animals. Several valid animal models of depression have been developed [5–7] which mimic most of the somatic symptoms of clinical depression. Electroencephalography (EEG) reflects the spontaneous electrical activity of the brain during the various states of sleep and wakefulness. It is recorded usually with scalp electrodes in human beings. The presence of “Brain waves” (undulations in

[1]  G. DeFriese,et al.  Physical Activity Counseling for Healthy Adults as a Primary Preventive Intervention in the Clinical Setting: Report for the US Preventive Services Task Force , 1989 .

[2]  D. J. Mapps,et al.  Knowledge-based enhancement of human EEG signals , 1990 .

[3]  P. Willner.  Animal models of depression: an overview. , 1990, Pharmacology & therapeutics.

[4]  F H Duffy,et al.  Altered topography of EEG spectral content in schizophrenia. , 1983, Electroencephalography and clinical neurophysiology.

[5]  D. Regan.  Human brain electrophysiology: Evoked potentials and evoked magnetic fields in science and medicine , 1989 .

[6]  Elias S. Manolakos,et al.  Parallel Processing for Biomedical Signal Processing Higher Order Spectral Analysis - An Application , 1991 .

[7]  L. Grunhaus,et al.  Sleep Electroencephalographic Studies After ECT: Age and Clinical Response. , 1994, The American journal of geriatric psychiatry : official journal of the American Association for Geriatric Psychiatry.

[8]  D. Kupfer,et al.  Childbearing in women with and without a history of affective disorder. II. Electroencephalographic sleep. , 1994, Comprehensive psychiatry.

[9]  Ernst Fernando Lopes Da Silva Niedermeyer,et al.  Electroencephalography, basic principles, clinical applications, and related fields , 1982 .

[10]  W. Morgan.  Physical activity, fitness and depression , 1994 .

[11]  M. Matousek,et al.  Relationships between EEG and clinical characteristics in major depressive disorder , 1986, Acta psychiatrica Scandinavica.

[12]  G. Burghardt.  Current Perceptions and Historical Perspective , 1985 .

[13]  C. Shagass,et al.  Some quantitative EEG findings in unmedicated and medicated major depressives. , 1988, Neuropsychobiology.

[14]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[15]  Sankar K. Pal,et al.  Fuzzy multi-layer perceptron, inferencing and rule generation , 1995, IEEE Trans. Neural Networks.

[16]  Russell C. Eberhart,et al.  EEG waveform analysis using CaseNet , 1989, Images of the Twenty-First Century. Proceedings of the Annual International Engineering in Medicine and Biology Society,.

[17]  W. Dement,et al.  Cyclic variations in EEG during sleep and their relation to eye movements, body motility, and dreaming. , 1957, Electroencephalography and clinical neurophysiology.

[18]  J R Bourne,et al.  Evaluation of a syntactic pattern recognition approach to quantitative electroencephalographic analysis. , 1981, Electroencephalography and clinical neurophysiology.

[19]  I. Feinberg,et al.  Total sleep deprivation in the rat transiently abolishes the delta amplitude response to darkness: implications for the mechanism of the "negative delta rebound". , 1993, Journal of neurophysiology.

[20]  Ivan Bruha,et al.  Need for knowledge-based subsystem in evoked potential neural-net recognition system , 1989, Images of the Twenty-First Century. Proceedings of the Annual International Engineering in Medicine and Biology Society,.

[21]  W. Schlicht.  Does physical exercise reduce anxious emotions ? A meta-analysis , 1994 .

[22]  T. Stephens,et al.  Physical activity and mental health in the United States and Canada: evidence from four population surveys. , 1988, Preventive medicine.

[23]  J. Butcher.  Psychological Assessment by Computer: Potential Gains and Problems to Avoid , 1994 .

[24]  C M Michel,et al.  Localization of the sources of EEG delta, theta, alpha and beta frequency bands using the FFT dipole approximation. , 1992, Electroencephalography and clinical neurophysiology.

[25]  Rodney Cotterill,et al.  Models of brain function , 1989 .

[26]  Thomas F. Collura,et al.  The Epilog System: Automated Long-Term EEG Monitoring for Epilepsy , 1992, Computer.

[27]  A N Mamelak,et al.  Automated staging of sleep in cats using neural networks. , 1991, Electroencephalography and clinical neurophysiology.

[28]  W. Klemm.  Are there EEG correlates of mental states in animals? , 1992, Neuropsychobiology.

[29]  G. Vogel,et al.  A new animal model of endogenous depression: A summary of present findings , 1990, Neuroscience & Biobehavioral Reviews.

[30]  S. Sarbadhikari.  A neural network confirms that physical exercise reverses EEG changes in depressed rats. , 1995, Medical engineering & physics.

[31]  B.H. Jansen,et al.  Knowledge-based approach to sleep EEG analysis-a feasibility study , 1989, IEEE Transactions on Biomedical Engineering.

[32]  Hans-Otto Carmesin.  Statistical Neurodynamics: a Model for Uni- Versal Properties of Eeg -data and Perception , 1994 .

[33]  Medical informatics--are the doctors ready? , 1995, Journal of the Indian Medical Association.

[34]  C. Hawkes,et al.  Endorphins: the basis of pleasure? , 1992, Journal of neurology, neurosurgery, and psychiatry.

[35]  M. Taylor,et al.  Differential EEG patterns in affective disorder and schizophrenia. , 1979, Archives of general psychiatry.

[36]  F. D. Silva.  Neural mechanisms underlying brain waves: from neural membranes to networks. , 1991 .

[37]  Nils J. Nilsson,et al.  Artificial Intelligence , 1974, IFIP Congress.

[38]  K. Shimohara,et al.  EEG topography recognition by neural networks , 1990, IEEE Engineering in Medicine and Biology Magazine.

[39]  C. Bouchard,et al.  Physical Activity, Fitness, and Health: International Proceedings and Consensus Statement , 1994 .

[40]  Kazuyuki Aihara,et al.  An analysis on Lyapunov spectrum of electroencephalographic (EEG) potentials , 1990 .

[41]  Julius T. Tou,et al.  Pattern Recognition Principles , 1974 .

[42]  A. Babloyantz,et al.  Evidence of Chaotic Dynamics of Brain Activity During the Sleep Cycle , 1985 .

[43]  J. Bronzino,et al.  Autoregressive and bispectral analysis techniques: EEG applications , 1990, IEEE Engineering in Medicine and Biology Magazine.

[44]  J D Frost,et al.  Automatic Recognition and Characterization of Epileptiform Discharges in the Human EEG , 1985, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[45]  Sankar K. Pal,et al.  Self-organizing neural network as a fuzzy classifier , 1994, IEEE Trans. Syst. Man Cybern..

[46]  J. Bronzino,et al.  Bispectral analysis of the rat EEG during various vigilance states , 1989, IEEE Transactions on Biomedical Engineering.

[47]  A. Ray,et al.  Chronic exercise alters EEG power spectra in an animal model of depression. , 1996, Indian journal of physiology and pharmacology.

[48]  Antoine Rémond,et al.  Clinical Applications of Computer Analysis of Eeg and Other Neurophysiological Signals , 1987 .

[49]  Samuel D. Stearns,et al.  Signal processing algorithms , 1988 .

[50]  R Jouvent,et al.  Decrease of complexity in EEG as a symptom of depression. , 1994, Neuroreport.

[51]  M. Mandal,et al.  Cerebral laterality in affect and affective illness: a review. , 1996, The Journal of psychology.

[52]  N. Kleitman,et al.  Regularly occurring periods of eye motility, and concomitant phenomena, during sleep. , 1953, Science.

[53]  H. Julia Hannay,et al.  Experimental techniques in human neuropsychology , 1986 .

[54]  Liebowitz Cs.  To release stress--exercise! , 1989 .

[55]  F. D. Silva.  The Rhythmic Slow Activity (Theta) of the Limbic Cortex: An Oscillation in Search of a Function , 1992 .

[56]  Sankar K. Pal,et al.  Logical operation based fuzzy MLP for classification and rule generation , 1994, Neural Networks.

[57]  M. Biondi,et al.  Frontal Hemisphere Lateralization and Depressive Personality Traits , 1993, Perceptual and motor skills.

[58]  R. Traub,et al.  Model of the origin of rhythmic population oscillations in the hippocampal slice. , 1989, Science.

[59]  B.H. Jansen.  Artificial neural nets for K-complex detection , 1990, IEEE Engineering in Medicine and Biology Magazine.

[60]  F. H. Lopes da Silva,et al.  Spectral characteristics of the hippocampal EEG in the freely moving rat. , 1982, Electroencephalography and clinical neurophysiology.

[61]  Claude Bouchard,et al.  Physical Activity, Fitness, and Health , 1997 .

[62]  S. Schlegel,et al.  Relationships between psychomotor retardation and EEG power spectrum in major depression. , 1992, Neuropsychobiology.

[63]  C. Tipton,et al.  Effects of exercise training on responses to central injection of CRF and noise stress , 1991, Physiology & Behavior.

[64]  Kevin Knight,et al.  Artificial intelligence (2. ed.) , 1991 .

[65]  S. Pal,et al.  An MLP-based model for identifying qEEG in depression. , 1996, International journal of bio-medical computing.

[66]  Riccardo Poli,et al.  A neural network expert system for diagnosing and treating hypertension , 1991, Computer.

[67]  B H Jansen,et al.  Quantitative analysis of electroencephalograms: is there chaos in the future? , 1991, International journal of bio-medical computing.

[68]  Bernard Widrow,et al.  30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.

[69]  R. Davidson,et al.  Frontal brain activation in repressors and nonrepressors. , 1994, Journal of abnormal psychology.

[70]  Zi-Jian Cai,et al.  The functions of sleep: Further analysis , 1991, Physiology & Behavior.

[71]  S. Sarbadhikari.  Let your dreams come true through virtual reality. , 1997, Journal of the Indian Medical Association.

[72]  P. Willner,et al.  The validity of animal models of depression , 2004, Psychopharmacology.

[73]  B. Jansen,et al.  Structural EEG analysis: an explorative study. , 1988, International journal of bio-medical computing.

[74]  A Värri,et al.  Automatic identification of significant graphoelements in multichannel EEG recordings by adaptive segmentation and fuzzy clustering. , 1991, International journal of bio-medical computing.

[75]  J R Bourne,et al.  Artificial intelligence methods in quantitative electroencephalogram analysis. , 1982, Computer programs in biomedicine.

[76]  C. Shagass,et al.  Relationships between psychiatric diagnosis and some quantitative EEG variables. , 1982, Archives of general psychiatry.

[77]  J. Borod,et al.  Interhemispheric and intrahemispheric control of emotion: a focus on unilateral brain damage. , 1992, Journal of consulting and clinical psychology.

[78]  M. Kerkhofs,et al.  Sleep Electroencephalography in Depressive Illness a Collaborative Study by the World Health Organization , 1991, British Journal of Psychiatry.

[79]  N. Fukuda,et al.  Comparative study on the behavioral and EEG changes induced by diazepam, buspirone and a novel anxioselective anxiolytic, DN-2327, in the cat. , 1992, Neuropsychobiology.

[80]  Alan V. Oppenheim,et al.  Digital Signal Processing , 1978, IEEE Transactions on Systems, Man, and Cybernetics.

[81]  A. Rechtschaffen.  A manual of Standardized Terminology , 1968 .

[82]  J. Fleiss,et al.  Constraints on the validity of computer diagnosis. , 1974, Archives of general psychiatry.

[83]  James L. McClelland,et al.  James L. McClelland, David Rumelhart and the PDP Research Group, Parallel distributed processing: explorations in the microstructure of cognition . Vol. 1. Foundations . Vol. 2. Psychological and biological models . Cambridge MA: M.I.T. Press, 1987. , 1989, Journal of Child Language.

[84]  A. Puech,et al.  Animal Behavioural Studies in the Evaluation of Antidepressant Drugs , 1992, British Journal of Psychiatry.

[85]  C. H. Vanderwolf,et al.  Hippocampal Rhythmic Slow Activity and Neocortical Low-Voltage Fast Activity: Relations to Behavior , 1975 .

[86]  Computer-Assisted Assessment of DSM-III-R Diagnoses , 1994 .

[87]  F Clemente,et al.  A flexible FFT algorithm for processing biomedical signals using a personal computer. , 1990, Journal of biomedical engineering.

[88]  A. Marmarou,et al.  Classification of somatosensory-evoked potentials recorded from patients with severe head injuries , 1990, IEEE Engineering in Medicine and Biology Magazine.

[89]  R. Lane,et al.  Heart rate differences between right and left unilateral electroconvulsive therapy. , 1994, Journal of neurology, neurosurgery, and psychiatry.

[90]  J. Tukey,et al.  An algorithm for the machine calculation of complex Fourier series , 1965 .

[91]  Sankar K. Pal,et al.  Fuzzy models for pattern recognition , 1992 .

[92]  E. Berndt,et al.  Depression: a neglected major illness. , 1993, The Journal of clinical psychiatry.

[93]  A. Walker.  Electroencephalography, Basic Principles, Clinical Applications and Related Fields , 1982 .

[94]  J. Horne.  Human Sleep, Sleep Loss and Behaviour , 1993, British Journal of Psychiatry.

[95]  G. Burghardt.  Animal awareness. Current perceptions and historical perspective. , 1985, The American psychologist.

[96]  B. Klöppel,et al.  Neural networks as a new method for EEG analysis. A basic introduction. , 1994, Neuropsychobiology.