Expert-in-the-loop Learning for Sleep EEG Data

This work addresses the area of a computer-assisted sleep staging using a standard scalp EEG recordings and AASM 2012 scoring rules. We focused on real clinical EEG data containing a large amount of artifacts and/or missing electrodes. The sleep-related features were extracted for 30-seconds segments. Power-in-band features were estimated by a method using Continuous Wavelet Transform (CWT). In addition, entropy, spectral entropy, fractal dimensions and statistical features were used as the input of classifiers. Inter-personal differences and the characteristics of extracted features were evaluated for individual sleep classes. Two expert-in-the-loop strategies and three different classifiers were used to classify data into sleep stages. The results were compared with a fully automated classification and with gold standard expert sleep staging. Due to the proposed improvements the final mean classification sensitivity of expertin-the-loop approach was increased up to 18.4%.The implemented solution allows to classify sleep recordings contaminated by a large amount of the naturally occurring artifacts that are impossible to process by traditional automated classification methods.

[1]  Rishemjit Kaur,et al.  Binary social impact theory based optimization and its applications in pattern recognition , 2014, Neurocomputing.

[2]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[3]  Lenka Lhotská,et al.  Automatic identification of artifacts and unwanted physiologic signals in EEG and EOG during wakefulness , 2017, Biomed. Signal Process. Control..

[4]  Martin Buss,et al.  Feature Extraction and Selection for Emotion Recognition from EEG , 2014, IEEE Transactions on Affective Computing.

[5]  N. Punjabi,et al.  Misclassification of OSA severity with automated scoring of home sleep recordings. , 2015, Chest.

[6]  Vance Gao,et al.  Multiple classifier systems for automatic sleep scoring in mice , 2016, Journal of Neuroscience Methods.

[7]  Konstantina S. Nikita,et al.  Comparison of fractal dimension estimation algorithms for epileptic seizure onset detection , 2008, BIBE.

[8]  S. Quan,et al.  AASM Scoring Manual Updates for 2017 (Version 2.4). , 2017, Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine.

[9]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[10]  Klaus-Robert Müller,et al.  Interpretable deep neural networks for single-trial EEG classification , 2016, Journal of Neuroscience Methods.

[11]  Musa Peker,et al.  A Comparative Study on Classification of Sleep Stage Based on EEG Signals Using Feature Selection and Classification Algorithms , 2014, Journal of Medical Systems.

[12]  Timothy M. Ellmore,et al.  Identifying sleep spindles with multichannel EEG and classification optimization , 2017, Comput. Biol. Medicine.

[13]  Georg Dorffner,et al.  Computer-Assisted Automated Scoring of Polysomnograms Using the Somnolyzer System. , 2015, Sleep.

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

[15]  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 .

[16]  J. Ross Quinlan,et al.  Learning decision tree classifiers , 1996, CSUR.

[17]  H. Jasper,et al.  The ten-twenty electrode system of the International Federation. The International Federation of Clinical Neurophysiology. , 1999, Electroencephalography and clinical neurophysiology. Supplement.

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

[19]  Rafael Robles,et al.  The convolution theorem for the continuous wavelet tranform , 2004, Signal Process..

[20]  Mohammed Imamul Hassan Bhuiyan,et al.  Automated identification of sleep states from EEG signals by means of ensemble empirical mode decomposition and random under sampling boosting , 2017, Comput. Methods Programs Biomed..

[21]  S. Chokroverty,et al.  Overview of sleep & sleep disorders. , 2010, The Indian journal of medical research.

[22]  Fionn Murtagh,et al.  Ward’s Hierarchical Agglomerative Clustering Method: Which Algorithms Implement Ward’s Criterion? , 2011, Journal of Classification.

[23]  Alberto Guillén,et al.  Combination of Heterogeneous EEG Feature Extraction Methods and stacked Sequential Learning for Sleep Stage Classification , 2013, Int. J. Neural Syst..

[24]  Charles K. Chui,et al.  An Introduction to Wavelets , 1992 .

[25]  Vladimir Krajca,et al.  A Fully Unsupervised Clustering on Adaptively Segmented Long-term EEG Data , 2015 .

[26]  Vladimir Krajca,et al.  PSGLab Matlab toolbox for polysomnographic data processing: Development and practical application , 2010, Proceedings of the 10th IEEE International Conference on Information Technology and Applications in Biomedicine.

[27]  Abdennaceur Kachouri,et al.  Sleep spindle and K-complex detection using tunable Q-factor wavelet transform and morphological component analysis , 2015, Front. Hum. Neurosci..

[28]  Sarah Jane Delany.  k-Nearest Neighbour Classifiers , 2007 .

[29]  Panagiotis D. Bamidis,et al.  Achieving Accurate Automatic Sleep Staging on Manually Pre-processed EEG Data Through Synchronization Feature Extraction and Graph Metrics , 2018, Front. Hum. Neurosci..

[30]  Huan Liu,et al.  Feature Selection for Classification , 1997, Intell. Data Anal..

[31]  Olga Sourina,et al.  Large-Scale Automated Sleep Staging , 2017, Sleep.