SLEEPNET: Automated Sleep Staging System via Deep Learning

Sleep disorders, such as sleep apnea, parasomnias, and hypersomnia, affect 50-70 million adults in the United States (Hillman et al., 2006). Overnight polysomnography (PSG), including brain monitoring using electroencephalography (EEG), is a central component of the diagnostic evaluation for sleep disorders. While PSG is conventionally performed by trained technologists, the recent rise of powerful neural network learning algorithms combined with large physiological datasets offers the possibility of automation, potentially making expert-level sleep analysis more widely available. We propose SLEEPNET (Sleep EEG neural network), a deployed annotation tool for sleep staging. SLEEPNET uses a deep recurrent neural network trained on the largest sleep physiology database assembled to date, consisting of PSGs from over 10,000 patients from the Massachusetts General Hospital (MGH) Sleep Laboratory. SLEEPNET achieves human-level annotation performance on an independent test set of 1,000 EEGs, with an average accuracy of 85.76% and algorithm-expert inter-rater agreement (IRA) of kappa = 79.46%, comparable to expert-expert IRA.

[1]  R. Broughton,et al.  Sleep patterns in the intensive care unit and on the ward after acute myocardial infarction. , 1978, Electroencephalography and clinical neurophysiology.

[2]  D. Thomson,et al.  Spectrum estimation and harmonic analysis , 1982, Proceedings of the IEEE.

[3]  R. Harrell,et al.  Postcardiotomy confusion and sleep loss. , 1987, The Journal of clinical psychiatry.

[4]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[5]  A. Muzet,et al.  Sleep stage scoring using the neural network model: comparison between visual and automatic analysis in normal subjects and patients. , 1996, Sleep.

[6]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[7]  M. Ferraz,et al.  Stressors in ICU: perception of the patient, relatives and health care team , 1999, Intensive Care Medicine.

[8]  J. Gabor,et al.  Sleep disruption in the intensive care unit , 2001, Current opinion in critical care.

[9]  Brian Litt,et al.  Line length: an efficient feature for seizure onset detection , 2001, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[10]  T. Guo,et al.  The sedative component of anesthesia is mediated by GABAA receptors in an endogenous sleep pathway , 2002, Nature Neuroscience.

[11]  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..

[12]  Koen B. E. Böcker,et al.  The international 10–20 system revisited: Cartesian and spherical co-ordinates , 2005, Brain Topography.

[13]  A. Schlögl,et al.  An E-Health Solution for Automatic Sleep Classification according to Rechtschaffen and Kales: Validation Study of the Somnolyzer 24 × 7 Utilizing the Siesta Database , 2005, Neuropsychobiology.

[14]  D. Hillman,et al.  The economic cost of sleep disorders. , 2006, Sleep.

[15]  J. Mattout,et al.  Automatic analysis of single-channel sleep EEG: validation in healthy individuals. , 2007, Sleep.

[16]  Jürgen Schmidhuber,et al.  Unconstrained On-line Handwriting Recognition with Recurrent Neural Networks , 2007, NIPS.

[17]  Abdulhamit Subasi,et al.  EEG signal classification using wavelet feature extraction and a mixture of expert model , 2007, Expert Syst. Appl..

[18]  F. Mormann,et al.  Seizure prediction: the long and winding road. , 2007, Brain : a journal of neurology.

[19]  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 .

[20]  Suzanne Lesecq,et al.  Feature selection for sleep/wake stages classification using data driven methods , 2007, Biomed. Signal Process. Control..

[21]  Yann LeCun,et al.  Comparing SVM and convolutional networks for epileptic seizure prediction from intracranial EEG , 2008, 2008 IEEE Workshop on Machine Learning for Signal Processing.

[22]  P. Anderer,et al.  Interrater reliability for sleep scoring according to the Rechtschaffen & Kales and the new AASM standard , 2009, Journal of sleep research.

[23]  H. Dickhaus,et al.  Classification of Sleep Stages Using Multi-wavelet Time Frequency Entropy and LDA , 2010, Methods of Information in Medicine.

[24]  Ali H. Shoeb,et al.  Application of Machine Learning To Epileptic Seizure Detection , 2010, ICML.

[25]  P. Anderer,et al.  Computer-Assisted Sleep Classification according to the Standard of the American Academy of Sleep Medicine : Validation Study of the AASM Version of the Somnolyzer 24 ! 7 , 2010 .

[26]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[27]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[28]  V. Ranieri,et al.  Sleep disturbances in the critically ill patients: role of delirium and sedative agents. , 2011, Minerva anestesiologica.

[29]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[30]  Alex Graves,et al.  Generating Sequences With Recurrent Neural Networks , 2013, ArXiv.

[31]  Erich Elsen,et al.  Deep Speech: Scaling up end-to-end speech recognition , 2014, ArXiv.

[32]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[33]  Fei-Fei Li,et al.  Large-Scale Video Classification with Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[34]  D. van Dijk.  Long-term cognitive impairment after critical illness. , 2014, The New England journal of medicine.

[35]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[36]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[37]  K. Loparo,et al.  Evaluation of an automated single-channel sleep staging algorithm , 2015, Nature and science of sleep.

[38]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  Mohammed Yeasin,et al.  Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks , 2015, ICLR.

[40]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[41]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[42]  Subhashini Venugopalan,et al.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. , 2016, JAMA.

[43]  Charles Elkan,et al.  Learning to Diagnose with LSTM Recurrent Neural Networks , 2015, ICLR.

[44]  Walter F. Stewart,et al.  Doctor AI: Predicting Clinical Events via Recurrent Neural Networks , 2015, MLHC.

[45]  Jimeng Sun,et al.  Using recurrent neural network models for early detection of heart failure onset , 2016, J. Am. Medical Informatics Assoc..

[46]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[47]  Brent Lance,et al.  EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces , 2016, Journal of neural engineering.