An inter-rater variability study between human and automatic scorers in 5-s mini-epochs of sleep
While mini-epoch scoring agreement was generally high, it was still lower than within epochs, likely due to a lack of standard mini-epoch scoring procedure and the automatic classifier being trained on epochs. However, stage discrepancies between epochs and mini-epochs and increased stage shifting in mini-epochs support that epochs can contain several stages, and that mini-epochs could supplement more detailed sleep characterization potentially enabling more precise diagnosis and finding new polysomnographic biomarkers. Future studies should include larger datasets to refine mini-epoch scoring rules and exploit automatic classifiers e.g. via transfer learning.
Authors
- Louise Frøstrup Follin
- Berit Hjelde Hansen (ORCID: https://orcid.org/0000-0002-5988-6817)
- Hilde T Juvodden (ORCID: https://orcid.org/0000-0001-6796-7177)
- Stine Knudsen (ORCID: https://orcid.org/0000-0003-1946-1125)
- Julie Anja Engelhard Christensen (ORCID: https://orcid.org/0000-0003-4225-3359)
- Janita Vevelstad
- Rannveig Viste (ORCID: https://orcid.org/0000-0002-7475-2999)
- Anette Ramm‐Pettersen
- Tobias Kaufmann (ORCID: https://orcid.org/0000-0002-4003-1018)
- Alexander Neergaard Zahid (ORCID: https://orcid.org/0000-0001-6881-9766)
Institutions
- Oslo University Hospital (NO)
- University of Oslo (NO)
- University of Tübingen (DE)
- Technical University of Denmark (DK)
Publication Details
- Journal
- Sleep Medicine
- Published
- 2025-02-07
- DOI
- https://doi.org/10.1016/j.sleep.2025.02.005
- Citations
- 6
- Primary Topic
- Sleep and Wakefulness Research
- Type
- article
- Field-Weighted Citation Impact
- 8.59
Funders
- Helse- og Omsorgsdepartementet
- Lundbeckfonden
- Helse Sør-Øst RHF