Artificial intelligence or sleep experts: comparing polysomnographic sleep staging in children and adolescents
Overall, there is a high degree of agreement between manual and automatic scoring. This suggests that U-sleep is a valid and effective method for identifying sleep stages based on normal PSGs in a pediatric population. The disagreement was within what is expected for interscorer variation. Further evaluation needs of AI sleep-scoring models include analysis of outliers and pathological sleep staging-which is also a challenge in manual annotation.
Authors
- Cecilie Paulsrud (ORCID: https://orcid.org/0000-0002-2255-3322)
- Jannet Svensson (ORCID: https://orcid.org/0000-0002-9365-0728)
- Nanette Mol Debes (ORCID: https://orcid.org/0000-0003-0279-1865)
- Steffen Ullitz Thorsen (ORCID: https://orcid.org/0000-0003-4783-2931)
- Mathias Perslev (ORCID: https://orcid.org/0000-0002-0358-4692)
- Poul Jennum (ORCID: https://orcid.org/0000-0001-6986-5254)
- Alexander Mœller (ORCID: https://orcid.org/0000-0001-7284-4251)
- Helle Leonthin
Institutions
- University of Copenhagen (DK)
- Steno Diabetes Centers (DK)
- Herlev Hospital (DK)
- Glostrup Hospital (DK)
- Gentofte Hospital (DK)
- Rigshospitalet (DK)
Publication Details
- Journal
- SLEEP
- Published
- 2025-02-28
- DOI
- https://doi.org/10.1093/sleep/zsaf053
- Citations
- 8
- Primary Topic
- Sleep and related disorders
- Type
- article
- Field-Weighted Citation Impact
- 16.95