Effectiveness of Sleep Apnea Detection Based on One vs. Two Symmetrical EEG Channels

Typically, two symmetrical EEG channels are recorded during polysomnography (PSG). As a rule, only the recommended channel is used for sleep stage scoring or sleep apnea detection, and the other for backup. Concurrently, there are many works demonstrating the asymmetry in brain activity. The aim of this work was to compare the accuracy of sleep apnea detection with the use of features obtained from one (C3-A2 or C4-A1) versus these two symmetrical EEG channels. To this end, the relevant data from the PhysioBank database (25 whole-night PSGs) were used. The same methodology of feature extraction and selection was applied for one and combined EEG channels. Automated classification was performed using the k-nearest neighbors algorithm (kNN) with k = 12 and cityblock metric for the three classes of EEG epochs, representing normal breathing, obstructive apnea and hypopnea, and central apnea and hypopnea. The accuracy of kNN-based classification was 63.8 %, 64.3 % and 70.3 % for C3-A2, C4-A1 and both EEG channels, respectively. The statistical tests have indicated that the accuracy of classification based on two combined symmetrical EEG channels is significantly higher compared to the single-channel cases.

[1]  Adam G. Polak,et al.  Effect of Feature Extraction on Automatic Sleep Stage Classification by Artificial Neural Network , 2017 .

[2]  K. Ramar,et al.  An Intelligent Sleep Apnea Classification System Based on EEG Signals , 2019, Journal of Medical Systems.

[3]  M. Hsu,et al.  OVERCOMING THE NEGATIVE FREQUENCIES - INSTANTANEOUS FREQUENCY AND AMPLITUDE ESTIMATION USING OSCULATING CIRCLE METHOD , 2011 .

[4]  David M Holtzman,et al.  Comparison of a single‐channel EEG sleep study to polysomnography , 2016, Journal of sleep research.

[5]  N. Kajimura,et al.  Asymmetric interhemispheric delta waves during all-night sleep in humans , 2000, Clinical Neurophysiology.

[6]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[7]  Bijaya K. Panigrahi,et al.  A comparative study of wavelet families for EEG signal classification , 2011, Neurocomputing.

[8]  Chien-Chang Hsu,et al.  A novel sleep apnea detection system in electroencephalogram using frequency variation , 2011, Expert Syst. Appl..

[9]  Touradj Ebrahimi,et al.  Classification of EEG signals using Dempster Shafer theory and a k-nearest neighbor classifier , 2009, 2009 4th International IEEE/EMBS Conference on Neural Engineering.

[10]  Miad Faezipour,et al.  Efficient obstructive sleep apnea classification based on EEG signals , 2015, 2015 Long Island Systems, Applications and Technology.

[11]  M. Bertini,et al.  Night-time right hemisphere superiority and daytime left hemisphere superiority: A repatterning of laterality across wake–sleep–wake states , 2008, Biological Psychology.

[12]  Ya-Ju Fan,et al.  On the Time Series $K$-Nearest Neighbor Classification of Abnormal Brain Activity , 2007, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[13]  Jing Zhou,et al.  Automatic detection of sleep apnea based on EEG detrended fluctuation analysis and support vector machine , 2015, Journal of Clinical Monitoring and Computing.

[14]  A. Gamundi,et al.  Asymmetric sleep in apneic human patients. , 2013, American journal of physiology. Regulatory, integrative and comparative physiology.

[15]  Thierry Denoeux.  A k -Nearest Neighbor Classification Rule Based on Dempster-Shafer Theory , 2008, Classic Works of the Dempster-Shafer Theory of Belief Functions.

[16]  Julián J. González,et al.  Interhemispheric differences in awake and sleep human EEG: a comparison between non-linear and spectral measures , 1999, Neuroscience Letters.

[17]  Peter Achermann,et al.  Frequency and state specific hemispheric asymmetries in the human sleep EEG , 1999, Neuroscience Letters.

[18]  Stefan Conrad,et al.  An approach for automatic sleep stage scoring and apnea-hypopnea detection , 2010, 2010 IEEE International Conference on Data Mining.

[19]  G. Tononi,et al.  Regional reductions in sleep electroencephalography power in obstructive sleep apnea: a high-density EEG study. , 2014, Sleep.

[20]  Celia Shahnaz,et al.  Sub-frame based apnea detection exploiting delta band power ratio extracted from EEG signals , 2016, 2016 IEEE Region 10 Conference (TENCON).

[21]  Adam G. Polak,et al.  Analysis of Features Extracted from EEG Epochs by Discrete Wavelet Decomposition and Hilbert Transform for Sleep Apnea Detection , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[22]  V. Swarnkar,et al.  Statistical analysis of EEG arousals in sleep apnea syndrome , 2006 .

[23]  Arnab Bhattacharjee,et al.  An approach for automatic sleep apnea detection based on entropy of multi-band EEG signal , 2016, 2016 IEEE Region 10 Conference (TENCON).

[24]  A. Chesson,et al.  The American Academy of Sleep Medicine (AASM) Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications , 2007 .

[25]  A. Chesson,et al.  The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology, and Techinical Specifications , 2007 .