Epoch-based Entropy for Early Screening of Alzheimer's Disease

In this paper, we introduce a novel entropy measure, termed epoch-based entropy. This measure quantifies disorder of EEG signals both at the time level and spatial level, using local density estimation by a Hidden Markov Model on inter-channel stationary epochs. The investigation is led on a multi-centric EEG database recorded from patients at an early stage of Alzheimer's disease (AD) and age-matched healthy subjects. We investigate the classification performances of this method, its robustness to noise, and its sensitivity to sampling frequency and to variations of hyperparameters. The measure is compared to two alternative complexity measures, Shannon's entropy and correlation dimension. The classification accuracies for the discrimination of AD patients from healthy subjects were estimated using a linear classifier designed on a development dataset, and subsequently tested on an independent test set. Epoch-based entropy reached a classification accuracy of 83% on the test dataset (specificity = 83.3%, sensitivity = 82.3%), outperforming the two other complexity measures. Furthermore, it was shown to be more stable to hyperparameter variations, and less sensitive to noise and sampling frequency disturbances than the other two complexity measures.

[1]  A. Cichocki,et al.  Diagnosis of Alzheimer's disease from EEG signals: where are we standing? , 2010 .

[2]  H. Adeli,et al.  EEG/MEG- and imaging-based diagnosis of Alzheimer’s disease , 2013, Reviews in the neurosciences.

[3]  Hojjat Adeli,et al.  New diagnostic EEG markers of the Alzheimer’s disease using visibility graph , 2010, Journal of Neural Transmission.

[4]  S. Sanei,et al.  Regional coherence evaluation in mild cognitive impairment and Alzheimer's disease based on adaptively extracted magnetoencephalogram rhythms , 2011, Physiological measurement.

[5]  M. P. Griffin,et al.  Sample entropy analysis of neonatal heart rate variability. , 2002, American journal of physiology. Regulatory, integrative and comparative physiology.

[6]  Soo-Yong Kim,et al.  Non-linear dynamical analysis of the EEG in Alzheimer's disease with optimal embedding dimension. , 1998, Electroencephalography and clinical neurophysiology.

[7]  Madalena Costa,et al.  Multiscale entropy analysis of complex physiologic time series. , 2002, Physical review letters.

[8]  Tim Curran,et al.  Investigation of changes in EEG complexity during memory retrieval: the effect of midazolam , 2012, Cognitive Neurodynamics.

[9]  L. Rabiner,et al.  An introduction to hidden Markov models , 1986, IEEE ASSP Magazine.

[10]  Y. Pesin.  CHARACTERISTIC LYAPUNOV EXPONENTS AND SMOOTH ERGODIC THEORY , 1977 .

[11]  Alexandre Andrade,et al.  Correlation Dimension Maps of EEG from Epileptic Absences , 1999, Brain Topography.

[12]  A. Cichocki,et al.  Diagnosis of Alzheimer's disease from EEG signals: where are we standing? , 2010, Current Alzheimer research.

[13]  Walter J Freeman,et al.  A cinematographic hypothesis of cortical dynamics in perception. , 2006, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[14]  Ning Xinbao.  Multiscale entropy analysis of complex physiologic time series , 2007 .

[15]  Hiroaki Kazui,et al.  Does donepezil treatment slow the progression of hippocampal atrophy in patients with Alzheimer's disease? , 2005, The American journal of psychiatry.

[16]  M. Folstein,et al.  Clinical diagnosis of Alzheimer's disease , 1984, Neurology.

[17]  H. Tai,et al.  Correlation dimensions of EEG changes during mental tasks , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[18]  Li Li,et al.  Systematic Identification of Risk Factors for Alzheimer's Disease Through Shared Genetic Architecture and Electronic Medical Records , 2012, Pacific Symposium on Biocomputing.

[19]  Seth Kiser,et al.  Early detection of Alzheimer's disease using nonlinear analysis of EEG via Tsallis entropy , 2010, 2010 Biomedical Sciences and Engineering Conference.

[20]  P. F. Meier,et al.  Dimensional complexity and spectral properties of the human sleep EEG , 2003, Clinical Neurophysiology.

[21]  Claudio Del Percio,et al.  Development and assessment of methods for detecting dementia using the human electroencephalogram , 2006, IEEE Transactions on Biomedical Engineering.

[22]  C. Stam,et al.  Nonlinear EEG analysis in early Alzheimer's disease , 1999, Acta neurologica Scandinavica.

[23]  J Wackermann,et al.  Global dimensional complexity of multichannel EEG in mild Alzheimer's disease and age-matched cohorts. , 1997, Dementia and geriatric cognitive disorders.

[24]  P. Grassberger,et al.  Measuring the Strangeness of Strange Attractors , 1983 .

[25]  G. Bodenstein,et al.  Feature extraction from the electroencephalogram by adaptive segmentation , 1977, Proceedings of the IEEE.

[26]  M. Tsolaki,et al.  Electroencephalogram and Alzheimer's Disease: Clinical and Research Approaches , 2014, International journal of Alzheimer's disease.

[27]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[28]  Andrew J. Szeri,et al.  A probabilistic framework for a physiological representation of dynamically evolving sleep state , 2013, Journal of Computational Neuroscience.

[29]  Hojjat Adeli,et al.  Alzheimer's disease and models of computation: imaging, classification, and neural models. , 2005, Journal of Alzheimer's disease : JAD.

[30]  Soo-Yong Kim,et al.  Nonlinear Dynamic Analysis of the EEG in Patients with Alzheimer’s Disease and Vascular Dementia , 2001, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[31]  Dietrich Lehmann,et al.  Mapping event-related brain potential microstates to sentence endings , 2005, Brain Topography.

[32]  C. Sparrow.  The Fractal Geometry of Nature , 1984 .

[33]  P. Grassberger.  Generalized dimensions of strange attractors , 1983 .

[34]  H. Adeli,et al.  Wavelet Coherence Model for Diagnosis of Alzheimer Disease , 2012, Clinical EEG and neuroscience.

[35]  Georg Dorffner,et al.  A reliable probabilistic sleep stager based on a single EEG signal , 2005, Artif. Intell. Medicine.

[36]  H. Kantz,et al.  Nonlinear time series analysis , 1997 .

[37]  Andrzej Cichocki,et al.  Slowing and Loss of Complexity in Alzheimer's EEG: Two Sides of the Same Coin? , 2011, International journal of Alzheimer's disease.

[38]  Hojjat Adeli,et al.  Alzheimer's Disease: Models of Computation and Analysis of EEGs , 2005, Clinical EEG and neuroscience.

[39]  Alexander A. Fingelkurts,et al.  Nonstationary nature of the brain activity as revealed by EEG/MEG: Methodological, practical and conceptual challenges , 2005, Signal Process..

[40]  A. Cichocki,et al.  Techniques for early detection of Alzheimer's disease using spontaneous EEG recordings , 2007, Physiological measurement.

[41]  Elisabet Englund,et al.  Regional pattern of degeneration in Alzheimer's disease: neuronal loss and histopathological grading. , 2002, Histopathology.

[42]  Andrzej Cichocki,et al.  A comparative study of synchrony measures for the early diagnosis of Alzheimer's disease based on EEG , 2010, NeuroImage.

[43]  Alexey Mekler,et al.  Calculation of EEG correlation dimension: Large massifs of experimental data , 2008, Comput. Methods Programs Biomed..

[44]  Benoit B. Mandelbrot,et al.  Fractal Geometry of Nature , 1984 .

[45]  C. Stam,et al.  Decrease of non-linear structure in the EEG of Alzheimer patients compared to healthy controls , 1999, Clinical Neurophysiology.

[46]  Andrzej Cichocki,et al.  Multiway array decomposition analysis of EEGs in Alzheimer's disease , 2012, Journal of Neuroscience Methods.

[47]  Chris Chatfield,et al.  The Analysis of Time Series : An Introduction, Sixth Edition , 2003 .

[48]  D. Abásolo,et al.  Entropy analysis of the EEG background activity in Alzheimer's disease patients , 2006, Physiological measurement.

[49]  Steven M. Pincus.  Approximate entropy as a measure of irregularity for psychiatric serial metrics. , 2006, Bipolar disorders.

[50]  Roberto Hornero,et al.  Analysis of regularity in the EEG background activity of Alzheimer's disease patients with Approximate Entropy , 2005, Clinical Neurophysiology.

[51]  Tetsuya Takahashi.  Complexity of spontaneous brain activity in mental disorders , 2013, Progress in Neuro-Psychopharmacology and Biological Psychiatry.

[52]  Nathaniel H. Hunt,et al.  The Appropriate Use of Approximate Entropy and Sample Entropy with Short Data Sets , 2012, Annals of Biomedical Engineering.

[53]  G. Dreyfus,et al.  Stationary epoch-based entropy estimation for early diagnosis of Alzheimer's disease , 2013, 2013 IEEE Faible Tension Faible Consommation.

[54]  C. J. Stam,et al.  Global dynamical analysis of the EEG in Alzheimer’s disease: Frequency-specific changes of functional interactions , 2008, Clinical Neurophysiology.

[55]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[56]  D. Ruelle,et al.  Fundamental limitations for estimating dimensions and Lyapunov exponents in dynamical systems , 1992 .

[57]  H. Braak,et al.  Neuropathological stageing of Alzheimer-related changes , 2004, Acta Neuropathologica.

[58]  Jaeseung Jeong.  EEG dynamics in patients with Alzheimer's disease , 2004, Clinical Neurophysiology.

[59]  J. Gore,et al.  Mutual information analysis of the EEG in patients with Alzheimer's disease , 2001, Clinical Neurophysiology.

[60]  Hojjat Adeli,et al.  Probabilistic neural networks for diagnosis of Alzheimer's disease using conventional and wavelet coherence , 2011, Journal of Neuroscience Methods.

[61]  D. Lehmann,et al.  Reference-free identification of components of checkerboard-evoked multichannel potential fields. , 1980, Electroencephalography and clinical neurophysiology.

[62]  Hojjat Adeli,et al.  Functional community analysis of brain: A new approach for EEG-based investigation of the brain pathology , 2011, NeuroImage.

[63]  Joseph Tabrikian,et al.  Classification of multichannel EEG patterns using parallel hidden Markov models , 2012, Medical & Biological Engineering & Computing.

[64]  Roberto Hornero,et al.  Analysis of electroencephalograms in Alzheimer's disease patients with multiscale entropy. , 2006 .

[65]  Roberto Hornero,et al.  Analysis of EEG background activity in Alzheimer's disease patients with Lempel-Ziv complexity and central tendency measure. , 2006, Medical engineering & physics.

[66]  H. Adeli,et al.  A spatio-temporal wavelet-chaos methodology for EEG-based diagnosis of Alzheimer's disease , 2008, Neuroscience Letters.

[67]  H. Adeli,et al.  Fractality and a Wavelet-chaos-Methodology for EEG-based Diagnosis of Alzheimer Disease , 2011, Alzheimer disease and associated disorders.

[68]  H. Adeli,et al.  Intrahemispheric, interhemispheric, and distal EEG coherence in Alzheimer’s disease , 2011, Clinical Neurophysiology.

[69]  Q. Bassat,et al.  Duration of protection with RTS,S/AS02A malaria vaccine in prevention of Plasmodium falciparum disease in Mozambican children: single-blind extended follow-up of a randomised controlled trial , 2005, The Lancet.

[70]  Leonard A. Smith.  Intrinsic limits on dimension calculations , 1988 .

[71]  Aaas News,et al.  Book Reviews , 1893, Buffalo Medical and Surgical Journal.

[72]  H. Adeli,et al.  Automated EEG-Based Diagnosis of Neurological Disorders: Inventing the Future of Neurology , 2010 .

[73]  C. Behl,et al.  Concepts for the treatment of Alzheimer's disease: molecular mechanisms and clinical application , 2005, International journal of experimental pathology.

[74]  M. Essig,et al.  Distribution of cerebral atrophy assessed by magnetic resonance imaging reflects patterns of neuropsychological deficits in Alzheimer's dementia , 2004, Neuroscience Letters.