A comparative study of synchrony measures for the early diagnosis of Alzheimer's disease based on EEG

被引:292
作者
Dauwels, J. [1 ,2 ]
Vialatte, F. [3 ]
Musha, T. [4 ]
Cichocki, A. [3 ]
机构
[1] MIT, Informat & Decis Syst Lab, Cambridge, MA 02139 USA
[2] RIKEN, Brain Sci Inst, Amari Res Unit, Saitama, Japan
[3] RIKEN, Brain Sci Inst, Lab Adv Brain Signal Proc, Saitama, Japan
[4] Brain Funct Lab Inc, Yokohama, Kanagawa, Japan
基金
日本学术振兴会;
关键词
Alzheimer's disease (AD); Mild cognitive impairment (MCI); Electroencephalography (EEG); Synchrony; Correlation coefficient; Coherence function; Corr-entropy coefficient; Coh-entropy coefficient; Wav-entropy coefficient; Granger causality; Information-theoretic divergence measures; Phase synchrony; State space based synchronization; S-estimator; Omega complexity; Non-linear interdependence; Stochastic event synchrony; Hilbert transform; Wavelet transform; MILD COGNITIVE IMPAIRMENT; QUANTIFYING STATISTICAL INTERDEPENDENCE; EVENT-RELATED POTENTIALS; INFORMATION-FLOW; DYNAMICAL ANALYSIS; COHERENCE; ELECTROENCEPHALOGRAPHY; CONNECTIVITY; EXTRACTION; COMPLEXITY;
D O I
10.1016/j.neuroimage.2009.06.056
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
It is well known that EEG signals of Alzheimer's disease (AD) patients are generally less synchronous than in age-matched control subjects. However, this effect is not always easily detectable. This is especially the case for patients in the pre-symptomatic phase, commonly referred to as mild cognitive impairment (MCI), during which neuronal degeneration is occurring prior to the clinical symptoms appearance. In this paper, various synchrony measures are studied in the context of AD diagnosis, including the correlation coefficient, mean-square and phase coherence, Granger causality, phase synchrony indices, information-theoretic divergence measures, state space based measures, and the recently proposed stochastic event synchrony measures. Experiments with EEG data show that many of those measures are strongly correlated (or anti-correlated) with the correlation coefficient, and hence, provide little complementary information about EEG synchrony. Measures that are only weakly correlated with the correlation coefficient include the phase synchrony indices, Granger causality measures, and stochastic event synchrony measures. In addition, those three families of synchrony measures are mutually uncorrelated, and therefore, they each seem to capture a specific kind of interdependence. For the data set at hand, only two synchrony measures are able to convincingly distinguish MCI patients from age-matched control patients, i.e., Granger causality (in particular, full-frequency directed transfer function) and stochastic event synchrony. Those two measures are used as features to distinguish MCI patients from age-matched control subjects, yielding a leave-one-out classification rate of 83%. The classification performance may be further improved by adding complementary features from EEG; this approach may eventually lead to a reliable EEG-based diagnostic tool for MCI and AD. (C) 2009 Elsevier Inc. All rights reserved.
引用
收藏
页码:668 / 693
页数:26
相关论文
共 91 条
[21]   Assessment of EEG synchronization based on state-space analysis [J].
Carmeli, C ;
Knyazeva, MG ;
Innocenti, GM ;
De Feo, O .
NEUROIMAGE, 2005, 25 (02) :339-354
[22]   Low-power 2.4-GHz RF transceiver for wireless EEG module plug-and-play [J].
Carmo, J. P. ;
Dias, N. ;
Mendes, P. M. ;
Couto, C. ;
Correia, J. H. .
2006 13TH IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, CIRCUITS AND SYSTEMS, VOLS 1-3, 2006, :1144-+
[23]   Carmeli's S index assesses motion and muscle artefact reduction in rowers' electrocardiograms [J].
Celka, Patrick ;
Kilner, Brett .
PHYSIOLOGICAL MEASUREMENT, 2006, 27 (08) :737-755
[24]   Brain event-related potentials: Diagnosing early-stage Alzheimer's disease [J].
Chapman, Robert M. ;
Nowlis, Geoffrey H. ;
McCrary, John W. ;
Chapman, John A. ;
Sandoval, Tiffany C. ;
Guillily, Maria D. ;
Gardner, Margaret N. ;
Reilly, Lindsey A. .
NEUROBIOLOGY OF AGING, 2007, 28 (02) :194-201
[25]   Frequency decomposition of conditional Granger causality and application to multivariate neural field potential data [J].
Chen, YH ;
Bressler, SL ;
Ding, MZ .
JOURNAL OF NEUROSCIENCE METHODS, 2006, 150 (02) :228-237
[26]   Analyzing multiple nonlinear time series with extended Granger causality [J].
Chen, YH ;
Rangarajan, G ;
Feng, JF ;
Ding, MZ .
PHYSICS LETTERS A, 2004, 324 (01) :26-35
[27]   EEG filtering based on blind source separation (BSS) for early detection of Alzheimer's disease [J].
Cichocki, A ;
Shishkin, SL ;
Musha, T ;
Leonowicz, Z ;
Asada, T ;
Kurachi, T .
CLINICAL NEUROPHYSIOLOGY, 2005, 116 (03) :729-737
[28]  
Cover T.M., 2006, ELEMENTS INFORM THEO, V2nd ed
[29]   Quantifying Statistical Interdependence by Message Passing on Graphs-Part II: Multidimensional Point Processes [J].
Dauwels, J. ;
Vialatte, F. ;
Weber, T. ;
Musha, T. ;
Cichocki, A. .
NEURAL COMPUTATION, 2009, 21 (08) :2203-2268
[30]   Quantifying Statistical Interdependence by Message Passing on Graphs-Part I: One-Dimensional Point Processes [J].
Dauwels, J. ;
Vialatte, F. ;
Weber, T. ;
Cichocki, A. .
NEURAL COMPUTATION, 2009, 21 (08) :2152-2202