Automatic detection of spindles and K-complexes in sleep EEG using switching multiple models

Abstract This work investigates the use of switching linear Gaussian state space models for the segmentation and automatic labelling of Stage 2 sleep EEG data characterised by spindles and K-complexes. The advantage of this approach is that it offers a unified framework of detecting multiple transient events within background EEG data. Specifically for the identification of background EEG, spindles and K-complexes, a true positive rate (false positive rate) of 76.04% (33.47%), 83.49% (47.26%) and 52.02% (7.73%) respectively was obtained on a sample by sample basis. A novel semi-supervised model allocation approach is also proposed, allowing new unknown modes to be learnt in real time.

[1]  V.V.Shete,et al.  Detection of K-Complex in Sleep Eeg Signal with Matched Filter and Neural Network , 2012 .

[2]  Peter S. Maybeck,et al.  Reconfigurable flight control via multiple model adaptive control methods , 1991 .

[3]  T. Dutoit,et al.  Automatic K-complexes detection in sleep EEG recordings using likelihood thresholds , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[4]  Pierre Baldi,et al.  Bioinformatics - the machine learning approach (2. ed.) , 2000 .

[5]  Visakan Kadirkamanathan,et al.  Functional Adaptive Control: An Intelligent Systems Approach , 2012 .

[6]  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 .

[7]  K. Blinowska,et al.  Micro- and macrostructure of sleep EEG , 2006, IEEE Engineering in Medicine and Biology Magazine.

[8]  Vasileios Kokkinos,et al.  Human non‐rapid eye movement stage II sleep spindles are blocked upon spontaneous K‐complex coincidence and resume as higher frequency spindles afterwards , 2011, Journal of sleep research.

[9]  Ping Yu,et al.  Electronic Health Record , 2012, Encyclopedia of Gerontology and Population Aging.

[10]  Zoubin Ghahramani,et al.  An Introduction to Hidden Markov Models and Bayesian Networks , 2001, Int. J. Pattern Recognit. Artif. Intell..

[11]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[12]  Mikel M. Miller,et al.  Novel electrocardiogram segmentation algorithm using a multiple model adaptive estimator , 2002, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[13]  Vahid Tarokh,et al.  DiBa: A Data-Driven Bayesian Algorithm for Sleep Spindle Detection , 2012, IEEE Transactions on Biomedical Engineering.

[14]  I. Bankman,et al.  Feature-based detection of the K-complex wave in the human electroencephalogram using neural networks , 1992, IEEE Transactions on Biomedical Engineering.

[15]  S. Chokroverty,et al.  The visual scoring of sleep in adults. , 2007, Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine.

[16]  B. Evans,et al.  Demonstration pf a 3–5s periodicity between the spindle bursts in NREM sleep in man , 1995 .

[17]  A.F.C. Infantosi,et al.  On the selection of autoregressive order for electroencephalographic (EEG) signals , 1995, 38th Midwest Symposium on Circuits and Systems. Proceedings.

[18]  Ata Akin,et al.  Detection of sleep spindles by discrete wavelet transform , 1998, Proceedings of the IEEE 24th Annual Northeast Bioengineering Conference (Cat. No.98CH36210).

[19]  R. Shumway,et al.  Dynamic linear models with switching , 1991 .

[20]  John A. Quinn,et al.  Factorial Switching Linear Dynamical Systems Applied to Physiological Condition Monitoring , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Thierry Dutoit,et al.  Automatic sleep spindles detection — Overview and development of a standard proposal assessment method , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[22]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[23]  Klaus Pawelzik,et al.  Hidden Markov mixtures of experts with an application to EEG recordings from sleep , 1999 .

[24]  P. Anderer,et al.  Topographic distribution of sleep spindles in young healthy subjects , 1997, Journal of sleep research.

[25]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[26]  Nikolaos K. Uzunoglu,et al.  Sleep spindle detection using artificial neural networks trained with filtered time-domain EEG: A feasibility study , 2005, Comput. Methods Programs Biomed..

[27]  Laura B Ray,et al.  Validating an automated sleep spindle detection algorithm using an individualized approach , 2010, Journal of sleep research.

[28]  D. L. Schomer,et al.  Niedermeyer's Electroencephalography: Basic Principles, Clinical Applications, and Related Fields , 2012 .

[29]  J. R. Smith,et al.  Automatic detection of the K-complex in sleep electroencephalograms. , 1970, IEEE transactions on bio-medical engineering.

[30]  William D. Penny,et al.  Dynamic Models for Nonstationary Signal Segmentation , 1999, Comput. Biomed. Res..