Spotlight on Sleep Stage Classification Based on EEG

Abstract

The recommendations for identifying sleep stages based on the interpretation of electrophysiological signals (electroencephalography [EEG], electro-oculography [EOG], and electromyography [EMG]), derived from the Rechtschaffen and Kales manual, were published in 2007 at the initiative of the American Academy of Sleep Medicine, and regularly updated over years. They offer an important tool to assess objective markers in different types of sleep/wake subjective complaints. With the aims and advantages of simplicity, reproducibility and standardization of practices in research and, most of all, in sleep medicine, they have overall changed little in the way they describe sleep. However, our knowledge on sleep/wake physiology and sleep disorders has evolved since then. High-density electroencephalography and intracranial electroencephalography studies have highlighted local regulation of sleep mechanisms, with spatio-temporal heterogeneity in vigilance states. Progress in the understanding of sleep disorders has allowed the identification of electrophysiological biomarkers better correlated with clinical symptoms and outcomes than standard sleep parameters. Finally, the huge development of sleep medicine, with a demand for explorations far exceeding the supply, has led to the development of alternative studies, which can be carried out at home, based on a smaller number of electrophysiological signals and on their automatic analysis. In this perspective article, we aim to examine how our description of sleep has been constructed, has evolved, and may still be reshaped in the light of advances in knowledge of sleep physiology and the development of technical recording and analysis tools. After presenting the strengths and limitations of the classification of sleep stages, we propose to challenge the “EEG-EOG-EMG” paradigm by discussing the physiological signals required for sleep stages identification, provide an overview of new tools and automatic analysis methods and propose avenues for the development of new approaches to describe and understand sleep/wake states.

Reproducible, data-driven characterization of sleep based on brain dynamics and transitions from whole-night fMRI

“…Secondly, in terms of spatial resolution, the functional atlas used in our study encompassed 300 ROIs, offering a more detailed view of activation patterns across the entire brain, including subcortical and cerebellar regions that are ignored in PSG-based sleep staging. Third, our approach is mostly automated and objective, eliminating concerns related to inter-rater reliability issues and human error ( Lambert and Peter-Derex, 2023 ; Lee et al, 2022 ; Rosenberg and Van, 2013 ). Lastly, identifying transitions between sleep stages can pose challenges when relying solely on PSG data.…”

“…Neuroimaging studies using techniques such as Positron Emission Tomography (PET) and functional MRI (fMRI) have identified unique activity patterns for each PSG stage, contributing to our understanding of sleep's functional role (Braun et al, 1997;Damaraju et al, 2020;Picchioni et al, 2013;Rué-Queralt et al, 2021;Tagliazucchi and Laufs, 2014;Tagliazucchi and van Someren, 2017;Zhou et al, 2019). While these PSG-guided neuroimaging studies provided new information about sleep function, our understanding of brain dynamics is limited by the low temporal resolution of PSG-based sleep scoring rules (i.e., 30-second epochs), low spatial resolution (i.e., limited EEG channels on the scalp), and the subjective visual inspection rules (Decat et al, 2022;Himanen and Hasan, 2000;Lambert and Peter-Derex, 2023). Alternative to PSG-based sleep staging, applying an unsupervised learning method, the Hidden Markov Model (HMM) (Stevner et al, 2019;Vidaurre et al, 2017), to sleep fMRI data can objectively model the time series of sleep and infer sleep brain states that recur at different points during sleep.…”

“…While these PSG-guided neuroimaging studies provided new information about sleep function, our understanding of brain dynamics is limited by the low temporal resolution of PSG-based sleep scoring rules (i.e., 30-second epochs), low spatial resolution (i.e., limited EEG channels on the scalp), and the subjective visual inspection rules ( Decat et al, 2022 ; Himanen and Hasan, 2000 ; Lambert and Peter-Derex, 2023 ). Alternative to PSG-based sleep staging, applying an unsupervised learning method, the Hidden Markov Model (HMM) ( Stevner et al, 2019 ; Vidaurre et al, 2017 ), to sleep fMRI data can objectively model the time series of sleep and infer sleep brain states that recur at different points during sleep.…”

The Relationship between Sleep Parameters Measured by Polysomnography and Selected Neurotrophic Factors

“…EEG is used in neurological diagnostics, but it can also be helpful in the differential diagnosis of sleep disorders such as insomnia, obstructive sleep apnea, narcolepsy, and parasomnias. Changes in EEG are observed in different sleep phases: alpha and theta waves dominate in the N1 NREM phase; theta waves, sleep spindles, and K complexes dominate in the N2 phase; delta waves dominate in the N3 phase; and low-voltage mixed-frequency EEG activity without sleep spindles and K complexes is observed in the REM phase [17].…”