SLEEPNET: Automated Sleep Staging System via Deep Learning
This work addresses the need for automated sleep analysis to make expert-level diagnostics more widely available for millions affected by sleep disorders, representing a strong specific gain rather than a foundational advancement.
The researchers tackled the problem of automating sleep staging from EEG data to diagnose sleep disorders, achieving human-level performance with 85.76% accuracy and 79.46% inter-rater agreement on a test set of 1,000 EEGs.
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.