Deep Learning Enables Accurate Automatic Sleep Staging Based on Ambulatory Forehead EEG

Akseli Leino,Jari Ahlberg,Sami Nikkonen,Susanna Westeren-Punnonen,Katja Myllymaa,Johanna Sahlman,Esa Mervaala,Tomi Miettinen,Laura Kalevo,Alexander Ryan,Samu Kainulainen,Brett Duce,Henri Korkalainen,Juha Toyras,Sami Myllymaa,Kirsi Sipila,Timo Leppanen

doi:10.1109/access.2022.3154899

Abstract

We have previously developed an ambulatory electrode set (AES) for the measurement of electroencephalography (EEG), electrooculography (EOG), and electromyography (EMG). The AES has been proven to be suitable for manual sleep staging and self-application in in- home polysomnography (PSG). To further facilitate the diagnostics of various sleep disorders, this study aimed to utilize a deep learning-based automated sleep staging approach for EEG signals acquired with the AES. The present neural network architecture comprises a combination of convolutional and recurrent neural networks previously shown to achieve excellent sleep scoring accuracy with a single standard EEG channel (F4-M1). In this study, the model was re- trained and tested with 135 EEG signals recorded with AES. The recordings were conducted for subjects suspected of sleep apnea or sleep bruxism. The performance of the deep learning model was evaluated with 10-fold cross-validation using manual scoring of the AES signals as a reference. The accuracy of the neural network sleep staging was 79.7% ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\kappa =0.729$ </tex-math></inline-formula> ) for five sleep stages (W, N1, N2, N3, and R), 84.1% ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\kappa =0.773$ </tex-math></inline-formula> ) for four sleep stages (W, light sleep, deep sleep, R), and 89.1% ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\kappa =0.801$ </tex-math></inline-formula> ) for three sleep stages (W, NREM, R). The utilized neural network was able to accurately determine sleep stages based on EEG channels measured with the AES. The accuracy is comparable to the inter-scorer agreement of standard EEG scorings between international sleep centers. The automatic AES-based sleep staging could potentially improve the availability of PSG studies by facilitating the arrangement of self-administrated in- home PSGs.

Highlights

Current guidelines defined by the American Academy of Sleep Medicine (AASM) divide sleep into five stages: wake (W), N1, N2, N3, and rapid eye movement (R) [1]
The stages are identified based on electroencephalography (EEG), electrooculography (EOG), and chin electromyography (EMG) signals recorded during polysomnography (PSG)
The first dataset consists of 80 home sleep apnea tests (HSAT) supplemented with ambulatory electrode set (AES) that were conducted at Kuopio University Hospital (Kuopio, Finland) and City of Helsinki Unit of Specialized Oral Care in the Metropolitan Area and Kirkkonummi (Helsinki, Finland) for 50 subjects with suspected sleep bruxism [16] in 2015–2017

Summary

Introduction

Current guidelines defined by the American Academy of Sleep Medicine (AASM) divide sleep into five stages: wake (W), N1, N2, N3, and rapid eye movement (R) [1]. PSG is usually conducted in a sleep laboratory (type I PSG), as the standard 10-20 system EEG electrodes (Fig. 1c) require pre-application by a trained expert and standard type II PSG EEG electrodes are too complex to be fully selfadministrated in a home environment. To overcome this shortcoming of the PSG, various types of headbands and electrode sets have been developed for EEG measurement [2]–[4]. AES recordings have been shown to be comparable to conventional type II in-home PSGs [5], [7]

Objectives

Methods

Results

Conclusion