A Fully Unsupervised Clustering on Adaptively Segmented Long-term EEG Data

Several new procedures for efficient processing of long-term EEG recordings has been validated on long-term comatose EEG data. The proposed solution is based on the use of cluster analysis over a set of various features derived from adaptively segmented EEG data. Special attention was given to utilization of clinically relevant information from multichannel EEG data. Methods for validation of the cluster analysis results were implemented and tested. Suggested algorithms speeds up a subsequent evaluation of the data and simplify a tedious and time-consuming work of neurologists or sleep technicians, making the evaluation more objective, and represent results in an understandable form.

[1]  Dietrich Lehmann,et al.  EEG Microstates During Resting Represent Personality Differences , 2011, Brain Topography.

[2]  Lenka Lhotská,et al.  Multivariate Analysis of Full-Term Neonatal Polysomnographic Data , 2009, IEEE Transactions on Information Technology in Biomedicine.

[3]  Gang Niu,et al.  Information-Maximization Clustering Based on Squared-Loss Mutual Information , 2014, Neural Computation.

[4]  Kenneth Loparo,et al.  Automated State Analyses: Proposed Applications to Neonatal Neurointensive Care , 2005, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[5]  Brian E. Wallace,et al.  A History and Review of Quantitative Electroencephalography in Traumatic Brain Injury , 2001, The Journal of head trauma rehabilitation.

[6]  Nurettin Acir,et al.  Automatic recognition of sleep spindles in EEG by using artificial neural networks , 2004, Expert Syst. Appl..

[7]  K. Chiappa,et al.  Evaluation and prognostication in coma. , 1998, Electroencephalography and clinical neurophysiology.

[8]  J. Starmark,et al.  The Reaction Level Scale (RLS 85) , 1988, Acta Neurochirurgica.

[9]  R. Sclabassi,et al.  Computer classification of sleep in preterm and full-term neonates at similar postconceptional term ages. , 1996, Sleep.

[10]  G. Lightbody,et al.  A comparison of quantitative EEG features for neonatal seizure detection , 2008, Clinical Neurophysiology.

[11]  Lenka Lhotská,et al.  System Approach to Complex Signal Processing Task , 2009, EUROCAST.

[12]  I. Lemahieu,et al.  Automatic detection of sleep stages using the EEG , 2001, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society.