Muscle artifacts in single trial EEG data distinguish patients with Parkinson's disease from healthy individuals

Parkinson's disease (PD) is known to lead to marked alterations in cortical-basal ganglia activity that may be amenable to serve as a biomarker for PD diagnosis. Using non-linear delay differential equations (DDE) for classification of PD patients on and off dopaminergic therapy (PD-on, PD-off, respectively) from healthy age-matched controls (CO), we show that 1 second of quasi-resting state clean and raw electroencephalogram (EEG) data can be used to classify CO from PD-on/off based on the area under the receiver operating characteristic curve (AROC). Raw EEG is shown to classify more robustly (AROC=0.59-0.86) than clean EEG data (AROC=0.57-0.72). Decomposition of the raw data into stereotypical and non-stereotypical artifacts provides evidence that increased classification of raw EEG time series originates from muscle artifacts. Thus, non-linear feature extraction and classification of raw EEG data in a low dimensional feature space is a potential biomarker for Parkinson's disease.

[1]  Thomas M. Cover,et al.  Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition , 1965, IEEE Trans. Electron. Comput..

[2]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[3]  T. Sejnowski,et al.  Removing electroencephalographic artifacts by blind source separation. , 2000, Psychophysiology.

[4]  E. Růžička,et al.  Investigation of non-linear properties of multichannel EEG in the early stages of Parkinson's disease , 2001, Clinical Neurophysiology.

[5]  N. Birbaumer,et al.  Investigation of brain dynamics in Parkinson's disease by methods derived from nonlinear dynamics , 2001, Experimental Brain Research.

[6]  William H. Press,et al.  Numerical recipes in C , 2002 .

[7]  H. Braak,et al.  Staging of brain pathology related to sporadic Parkinson’s disease , 2003, Neurobiology of Aging.

[8]  J. Obeso,et al.  Challenges in Parkinson's disease: restoration of the nigrostriatal dopamine system is not enough , 2004, The Lancet Neurology.

[9]  Arnaud Delorme,et al.  EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis , 2004, Journal of Neuroscience Methods.

[10]  A. S. Rodionov,et al.  Comparison of linear, nonlinear and feature selection methods for EEG signal classification , 2004, International Conference on Actual Problems of Electron Devices Engineering, 2004. APEDE 2004..

[11]  Klaus Lehnertz,et al.  Epilepsy and Nonlinear Dynamics , 2008, Journal of biological physics.

[12]  J. Jankovic Parkinson’s disease: clinical features and diagnosis , 2008, Journal of Neurology, Neurosurgery, and Psychiatry.

[13]  T. Sejnowski,et al.  Non-Linear Dynamical Analysis of EEG Time Series Distinguishes Patients with Parkinson’s Disease from Healthy Individuals , 2013, Front. Neurol..

[14]  S. Hillyard,et al.  Parkinson’s disease patients show impaired corrective grasp control and eye–hand coupling when reaching to grasp virtual objects , 2013, Neuroscience.

[15]  T. Sejnowski,et al.  Electrocardiogram classification using delay differential equations. , 2013, Chaos.

[16]  E. Katunina,et al.  [Epidemiology of Parkinson's disease]. , 2013, Zhurnal nevrologii i psikhiatrii imeni S.S. Korsakova.

[17]  Terrence J. Sejnowski,et al.  Non-Linear Dynamical Classification of Short Time Series of the Rössler System in High Noise Regimes , 2013, Front. Neurol..

[18]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .