A convolutional neural network outperforming state-of-the-art sleep staging algorithms for both preterm and term infants

OBJECTIVE To classify sleep states using electroencephalogram (EEG) that reliably works over a wide range of preterm ages, as well as term age. METHODS A convolutional neural network is developed to perform 2- and 4-class sleep classification in neonates. The network takes as input an 8-channel 30-second EEG segment and outputs the sleep state probabilities. Apart from simple downsampling of the input and smoothing of the output, the suggested network is an end-to-end algorithm that avoids the need for hand-crafted feature selection or complex pre/post processing steps. To train and test this method, 113 EEG recordings from 42 infants are used. RESULTS For quiet sleep detection (the 2-class problem), mean kappa between the network estimate and the ground truth annotated by EEG human experts is 0.76. The sensitivity and specificity are 90% and 88%, respectively. For 4-class classification, mean kappa is 0.64. The averaged sensitivity and specificity (1 vs. all) respectively equal 72% and 91%. The results outperform current state-of-the-art methods for which kappa ranges from 0.66 to 0.70 in preterm and from 0.51 to 0.61 in term infants, based on training and testing using the same database. SIGNIFICANCE The proposed method has the highest reported accuracy for EEG sleep state classification for both preterm and term age neonates.

[1]  Sabine Van Huffel,et al.  Quiet sleep detection in preterm infants using deep convolutional neural networks , 2018, Journal of neural engineering.

[2]  Yan Wu,et al.  Automatic sleep stage classification of single-channel EEG by using complex-valued convolutional neural network , 2017, Biomedizinische Technik. Biomedical engineering.

[3]  Alexander Bertrand,et al.  EEG-based detection of the attended speaker and the locus of auditory attention with convolutional neural networks , 2018, bioRxiv.

[4]  J. S. Barlow,et al.  Computer characterization of tracé alternant and REM sleep patterns in the neonatal EEG by adaptive segmentation--an exploratory study. , 1985, Electroencephalography and clinical neurophysiology.

[5]  U. Rajendra Acharya,et al.  Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals , 2017, Comput. Biol. Medicine.

[6]  Oliver Y. Chén,et al.  SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging , 2018, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[7]  Hubert Cecotti,et al.  Convolutional Neural Network with embedded Fourier Transform for EEG classification , 2008, 2008 19th International Conference on Pattern Recognition.

[8]  K. Leeb,et al.  Babies admitted to NICU/ICU: province of birth and mode of delivery matter. , 2011, Healthcare quarterly.

[9]  Sabine Van Huffel,et al.  Review of sleep-EEG in preterm and term neonates. , 2017, Early human development.

[10]  Sabine Van Huffel,et al.  Automated EEG sleep staging in the term-age baby using a generative modelling approach , 2018, Journal of neural engineering.

[11]  Geraldine B. Boylan,et al.  Neonatal seizure detection using convolutional neural networks , 2017, 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP).

[12]  Michael Breakspear,et al.  Cortical burst dynamics predict clinical outcome early in extremely preterm infants. , 2015, Brain : a journal of neurology.

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

[14]  Lenka Lhotská,et al.  Neonatal EEG Sleep Stages Modelling by Temporal Profiles , 2007, EUROCAST.

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

[16]  Michael D. Weiss,et al.  Sleep Disturbances in Newborns , 2017, Children.

[17]  P. Garg,et al.  NICU in a community level hospital , 2005, Indian journal of pediatrics.

[18]  L. Lhotska,et al.  Automatic Detection of Sleep Stages in Neonatal EEG Using the Structural Time Profiles , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[19]  R. Locke,et al.  Variation in NICU Admission Rates Without Identifiable Cause. , 2016, Hospital pediatrics.

[20]  Kenneth A. Loparo,et al.  Automated detection of neonate EEG sleep stages , 2009, Comput. Methods Programs Biomed..

[21]  Jiaquan Xu,et al.  Deaths: final data for 2005. , 2008, National vital statistics reports : from the Centers for Disease Control and Prevention, National Center for Health Statistics, National Vital Statistics System.

[22]  Wolfram Burgard,et al.  Deep learning with convolutional neural networks for EEG decoding and visualization , 2017, Human brain mapping.

[23]  Mercedes Colomar,et al.  Preferences for mode of delivery in nulliparous Argentinean women: a qualitative study , 2013, Reproductive Health.

[24]  Lars Kai Hansen,et al.  Deep convolutional neural networks for interpretable analysis of EEG sleep stage scoring , 2017, 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP).

[25]  Perumpillichira J. Cherian,et al.  Technical standards for recording and interpretation of neonatal electroencephalogram in clinical practice , 2009, Annals of Indian Academy of Neurology.

[26]  Sampsa Vanhatalo,et al.  Early Brain Activity Relates to Subsequent Brain Growth in Premature Infants. , 2015, Cerebral cortex.

[27]  Hubert Cecotti,et al.  Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Oliver Y. Chén,et al.  Joint Classification and Prediction CNN Framework for Automatic Sleep Stage Classification , 2018, IEEE Transactions on Biomedical Engineering.

[29]  S. Vanhatalo,et al.  Measuring brain activity cycling (BAC) in long term EEG monitoring of preterm babies. , 2014, Physiological measurement.

[30]  Laurent Vercueil,et al.  A convolutional neural network for sleep stage scoring from raw single-channel EEG , 2018, Biomed. Signal Process. Control..

[31]  K. Allen.  Promoting and Protecting Infant Sleep , 2012, Advances in neonatal care : official journal of the National Association of Neonatal Nurses.

[32]  S. Vanhatalo,et al.  Automated classification of neonatal sleep states using EEG , 2017, Clinical Neurophysiology.

[33]  Sabine Van Huffel,et al.  Neonatal Seizure Detection Using Deep Convolutional Neural Networks , 2019, Int. J. Neural Syst..

[34]  Sabine Van Huffel,et al.  An Automated Quiet Sleep Detection Approach in Preterm Infants as a Gateway to Assess Brain Maturation , 2017, Int. J. Neural Syst..

[35]  Sampsa Vanhatalo,et al.  Sleep wake cycling in early preterm infants: Comparison of polysomnographic recordings with a novel EEG-based index , 2013, Clinical Neurophysiology.

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

[37]  Joy Lawn,et al.  Born Too Soon: The global epidemiology of 15 million preterm births , 2013, Reproductive Health.