Deep residual networks for automatic sleep stage classification of raw polysomnographic waveforms

Alexander Neergaard Olesen, Poul Jennum, Paul Peppard, Emmanuel Mignot, Helge Bjarup Dissing Sørensen

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

80 Downloads (Pure)

Abstract

We have developed an automatic sleep stage classification algorithm based on deep residual neural networks and raw polysomnogram signals. Briefly, the raw data is passed through 50 convolutional layers before subsequent classification into one of five sleep stages. Three model configurations were trained on 1850 polysomnogram recordings and subsequently tested on 230 independent recordings. Our best performing model yielded an accuracy of 84.1% and a Cohen’s kappa of 0.746, improving on previous reported results by other groups also using only raw polysomnogram data. Most errors were made on non-REM stage 1 and 3 decisions, errors likely resulting from the definition of these stages. Further testing on independent cohorts is needed to verify performance for clinical use.
Original languageEnglish
Title of host publicationProceedings of 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
PublisherIEEE
Publication date2018
Pages3713-3716
ISBN (Print)9781538636459
DOIs
Publication statusPublished - 2018
Event40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Hawaii Convention Center, Honolulu, United States
Duration: 17 Jul 201821 Jul 2018
https://embc.embs.org/2018/

Conference

Conference40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
LocationHawaii Convention Center
CountryUnited States
CityHonolulu
Period17/07/201821/07/2018
Internet address
Series2017 39th Annual International Conference of the Ieee Engineering in Medicine and Biology Society (embc)
ISSN1558-4615

Keywords

  • Sleep
  • Brain modeling
  • Electroencephalography
  • Tensile stress
  • Electrooculography

Cite this

Olesen, A. N., Jennum, P., Peppard, P., Mignot, E., & Sørensen, H. B. D. (2018). Deep residual networks for automatic sleep stage classification of raw polysomnographic waveforms. In Proceedings of 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 3713-3716). IEEE. 2017 39th Annual International Conference of the Ieee Engineering in Medicine and Biology Society (embc) https://doi.org/10.1109/EMBC.2018.8513080