EEG synchrony analysis for early diagnosis of Alzheimer's disease: A study with several synchrony measures and EEG data sets

It has frequently been reported in the medical literature that the EEG of Alzheimer disease (AD) patients is less synchronous than in healthy subjects. In this paper, it is explored whether loss in EEG synchrony can be used to diagnose AD at an early stage. Multiple synchrony measures are applied to two different EEG data sets: (1) EEG of pre-dementia patients and control subjects; (2) EEG of mild AD patients and control subjects; the two data sets are from different patients, different hospitals, and obtained through different recording systems. It is observed that both Granger causality and stochastic event synchrony indicate statistically significant loss of EEG synchrony, for the two data sets; those two synchrony measures are then combined as features in linear and quadratic discriminant analysis (with crossvalidation), yielding classification rates of 83% and 88% for the pre-dementia data set and mild AD data set respectively. These results suggest that loss in EEG synchrony is indicative for early AD.

[1]  Ly-Mee Yu,et al.  A Randomised, Blinded, Placebo-Controlled Trial in Dementia Patients Continuing or Stopping Neuroleptics (The DART-AD Trial) , 2008, PLoS medicine.

[2]  Naomi Yatomi,et al.  Influence of Deteriorating Ability of Emotional Comprehension on Interpersonal Behavior in Alzheimer-Type Dementia , 2001, Brain and Cognition.

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

[4]  Hualou Liang,et al.  Causal influence: advances in neurosignal analysis. , 2005, Critical reviews in biomedical engineering.

[5]  Andrzej Cichocki,et al.  Measuring Neural Synchrony by Message Passing , 2007, NIPS.

[6]  J. Fermaglich Electric Fields of the Brain: The Neurophysics of EEG , 1982 .

[7]  B. Winblad,et al.  Predictors of progression from mild cognitive impairment to Alzheimer disease , 2007, Neurology.

[8]  M. Mattson Pathways towards and away from Alzheimer's disease , 2004, Nature.

[9]  Andrzej Cichocki,et al.  Quantifying Statistical Interdependence by Message Passing on Graphs—Part I: One-Dimensional Point Processes , 2009, Neural Computation.

[10]  Rémi Gervais,et al.  A machine learning approach to the analysis of time-frequency maps, and its application to neural dynamics , 2007, Neural Networks.

[11]  Andrzej Cichocki,et al.  Quantifying Statistical Interdependence PART III: n > 2 Multi-Dimensional Point Processes , 2009 .

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

[13]  R Quian Quiroga,et al.  Performance of different synchronization measures in real data: a case study on electroencephalographic signals. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

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

[15]  F. Varela,et al.  Measuring phase synchrony in brain signals , 1999, Human brain mapping.