Expert-level automated sleep staging of long-term scalp electroencephalography recordings using deep learning
- 12 November 2020
- journal article
- research article
- Published by Oxford University Press (OUP) in Sleep
- Vol. 43 (11)
- https://doi.org/10.1093/sleep/zsaa112
Abstract
Develop a high-performing, automated sleep scoring algorithm that can be applied to long-term scalp electroencephalography (EEG) recordings. Using a clinical dataset of polysomnograms from 6,431 patients (MGH-PSG dataset), we trained a deep neural network to classify sleep stages based on scalp EEG data. The algorithm consists of a convolutional neural network (CNN) for feature extraction, followed by a recurrent neural network (RNN) that extracts temporal dependencies of sleep stages. The algorithm’s inputs are 4 scalp EEG bipolar channels (F3-C3, C3-O1, F4-C4, C4-O2), which can be derived from any standard PSG or scalp EEG recording. We initially trained the algorithm on the MGH-PSG dataset and used transfer learning to fine-tune it on a dataset of long-term (24-72 hour) scalp EEG recordings from 112 patients (scalpEEG dataset). The algorithm achieved a Cohen’s kappa of 0.74 on the MGH-PSG holdout testing set and cross-validated Cohen’s kappa of 0.78 after optimization on the scalpEEG dataset. The algorithm also performed well on two publicly available PSG datasets, demonstrating high generalizability. Performance on all datasets was comparable to the inter-rater agreement of human sleep staging experts (Cohen’s kappa ~ 0.75±0.11). The algorithm’s performance on long-term scalp EEGs was robust over a wide age range and across common EEG background abnormalities. We developed a deep learning algorithm that achieves human expert level sleep staging performance on long-term scalp EEG recordings. This algorithm, which we have made publicly available, greatly facilitates the use of large long-term EEG clinical datasets for sleep-related research.Keywords
Funding Information
- American Academy of Neurology Institute
- Glenn Foundation
- American Federation for Aging Research
- National Institutes of Health (1R01NS102190, 1R01NS102574, 1R01NS107291, 1RF1AG064312)
- National Heart, Lung, and Blood Institute
This publication has 45 references indexed in Scilit:
- Why Are Seizures Rare in Rapid Eye Movement Sleep? Review of the Frequency of Seizures in Different Sleep StagesEpilepsy Research and Treatment, 2013
- Automatic sleep stage recurrent neural classifier using energy features of EEG signalsNeurocomputing, 2013
- The American Academy of Sleep Medicine Inter-scorer Reliability Program: Sleep Stage ScoringSleep Medicine, 2013
- A Multisite Randomized Trial of Portable Sleep Studies and Positive Airway Pressure Autotitration Versus Laboratory-Based Polysomnography for the Diagnosis and Treatment of Obstructive Sleep Apnea: The HomePAP StudySleep, 2012
- A rule-based automatic sleep staging methodJournal of Neuroscience Methods, 2012
- AUTOMATED SLEEP STAGING TECHNIQUE BASED ON THE EMPIRICAL MODE DECOMPOSITION ALGORITHM: A PRELIMINARY STUDYAdvances in Adaptive Data Analysis, 2010
- Classification of Sleep Stages Using Multi-wavelet Time Frequency Entropy and LDAMethods of Information in Medicine, 2010
- Interrater reliability for sleep scoring according to the Rechtschaffen & Kales and the new AASM standardJournal of Sleep Research, 2009
- Automatic sleep stage classification using two-channel electro-oculographyJournal of Neuroscience Methods, 2007
- Long Short-Term MemoryNeural Computation, 1997