Auto-annotating sleep stages based on polysomnographic data.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 35079710.
- Also identified by DOI 10.1016/j.patter.2021.100371 and PMC identifier 8767308.
- Licence recorded as CC BY-NC-ND.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
Sleep disorders affect the quality of life, and the clinical diagnosis of sleep disorders is a time-consuming and tedious process requiring recording and annotating polysomnographic records. In this work, we developed an auto-annotation algorithm based on polysomnographic records and a deep learning architecture that predicts sleep stages at the millisecond level. The model improves the efficiency of the polysomnographic record annotation process by automatically annotating each record within 3.8 s of computation time and with high accuracy. Disease-related sleep stages, such as arousal and apnea, can also be identified by this model, which further expands the physiological insights that the model can potentially provide. Finally, we explored the applicability of the model to data collected from a different modality to demonstrate the robustness of the model.