Abstract
A new method for automated sleep stage scoring of polysomnographies is proposed that uses a random forest approach to model feature interactions and temporal effects. The model mostly relies on features based on the rules from the American Academy of Sleep Medicine, which allows medical experts to gain insights into the model. A common way to evaluate automated approaches to constructing hypnograms is to compare the one produced by the algorithm to an expert's hypnogram. However, given the same data, two expert annotators will construct (slightly) different hypnograms due to differing interpretations of the data or individual mistakes. A thorough evaluation of our method is performed on a multi-labeled dataset in which both the inter-rater variability as well as the prediction uncertainties are taken into account, leading to a new standard for the evaluation of automated sleep stage scoring algorithms. On all epochs, our model achieves an accuracy of 82.7%, which is only slightly lower than the inter-rater disagreement. When only considering the 63.3% of the epochs where both the experts and algorithm are certain, the model achieves an accuracy of 97.8%. Transition periods between sleep stages are identified and studied for the first time. Scoring guidelines for medical experts are provided to complement the certain predictions by scoring only a few epochs manually. This makes the proposed method highly time-efficient while guaranteeing a highly accurate final hypnogram.
Highlights
In polysomnographic (PSG) recordings, physiological signals like the electroencephalogram (EEG), the electromyogram (EMG), the electrooculogram (EOG), heart activity (ECG), and the patient’s breathing pattern are measured over an entire night to assess sleep disorders such as sleep apnea or insomnia
Sleep stage scoring is often performed manually by clinical experts following rules determined by the American Academy of Sleep Medicine (AASM)
A new method to perform automated sleep stage scoring is proposed that avoids constructing complex feature design, by designing a feature set that is largely based on the AASM rules
Summary
In polysomnographic (PSG) recordings, physiological signals like the electroencephalogram (EEG), the electromyogram (EMG), the electrooculogram (EOG), heart activity (ECG), and the patient’s breathing pattern are measured over an entire night to assess sleep disorders such as sleep apnea or insomnia. Sleep stage scoring is often performed manually by clinical experts following rules determined by the American Academy of Sleep Medicine (AASM). By these rules, the PSG is divided into 30-s sequential windows starting from the beginning of the PSG. Each window, called an epoch, should be annotated by one out of five sleep-wake stages (W, N1, N2, N3, or R) [1]. Each of these sleep-wake stages has its own characteristics. The wakefulness stage (W) has in general a high EMG value, dominating alpha (8–13 Hz) and beta (14–35 Hz) waves in the EEG
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
