EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Scoring sleep with artificial intelligence enables quantification of sleep stage ambiguity: hypnodensity based on multiple expert scorers and auto-scoring

Jessie P Bakker iD, Marco Ross iD, Andreas Cerny iD, Ray Vasko, Edmund Shaw, Samuel Kuna, Ulysses J Magalang iD, Naresh M Punjabi, Peter Anderer iD

Sleep · 2023

DOI: 10.1093/sleep/zsac154 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sleep, 2023. Verfasst von Jessie P Bakker und 8 weiteren Autor:innen. Beteiligte Einrichtung: Philips Sleep and Respiratory Care, Pittsburgh, PA,USA. Hauptthemen laut MEDLINE: Artificial Intelligence, Sleep. Die Arbeit wurde bisher 68-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Study Objectives To quantify the amount of sleep stage ambiguity across expert scorers and to validate a new auto-scoring platform against sleep staging performed by multiple scorers.

Methods

We applied a new auto-scoring system to three datasets containing 95 PSGs scored by 6–12 scorers, to compare sleep stage probabilities (hypnodensity; i.e. the probability of each sleep stage being assigned to a given epoch) as the primary output, as well as a single sleep stage per epoch assigned by hierarchical majority rule.

Results

The percentage of epochs with 100% agreement across scorers was 46 ± 9%, 38 ± 10% and 32 ± 9% for the datasets with 6, 9, and 12 scorers, respectively. The mean intra-class correlation coefficient between sleep stage probabilities from auto- and manual-scoring was 0.91, representing excellent reliability. Within each dataset, agreement between auto-scoring and consensus manual-scoring was significantly higher than agreement between manual-scoring and consensus manual-scoring (0.78 vs. 0.69; 0.74 vs. 0.67; and 0.75 vs. 0.67; all p < 0.01).

Conclusions

Analysis of scoring performed by multiple scorers reveals that sleep stage ambiguity is the rule rather than the exception. Probabilities of the sleep stages determined by artificial intelligence auto-scoring provide an excellent estimate of this ambiguity. Compared to consensus manual-scoring, sleep staging derived from auto-scoring is for each individual PSG noninferior to manual-scoring meaning that auto-scoring output is ready for interpretation without the need for manual adjustment.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceSleepHumansReproducibility of ResultsObserver VariationSleep Stages

Stichwörter der Autor:innen

artificial intelligencehypnodensitymachine learningpolysomnographysleep stagesvalidation

Autor:innen und Institutionen

  • Philips Sleep and Respiratory Care, Pittsburgh, PA,USA.
  • Philips Sleep and Respiratory Care, Vienna, Austria.
  • Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA,USA.
  • Corporal Michael J. Crescenz Veterans Affairs Medical Center, Philadelphia, PA,USA.
  • Division of Pulmonary, Critical Care, and Sleep Medicine, Ohio State University Wexner Medical Center, Columbus, OH, USA.
  • Division of Pulmonary, Critical Care, and Sleep Medicine, University of Miami, Miami FL, USA.

ORCID-Profile: Jessie P Bakker, Marco Ross, Andreas Cerny, Ulysses J Magalang, Peter Anderer

Zitieren

APA

Bakker, J. P., Ross, M., Cerny, A., Vasko, R., Shaw, E., Kuna, S., Magalang, U. J., Punjabi, N. M., & Anderer, P. (2023). Scoring sleep with artificial intelligence enables quantification of sleep stage ambiguity: hypnodensity based on multiple expert scorers and auto-scoring. Sleep. https://doi.org/10.1093/sleep/zsac154

Vancouver

Bakker JP, Ross M, Cerny A, Vasko R, Shaw E, Kuna S, et al. Scoring sleep with artificial intelligence enables quantification of sleep stage ambiguity: hypnodensity based on multiple expert scorers and auto-scoring. Sleep. 2023. doi:10.1093/sleep/zsac154

BibTeX
@article{Bakker2023,
  author = {Bakker, Jessie P and Ross, Marco and Cerny, Andreas and Vasko, Ray and Shaw, Edmund and Kuna, Samuel and Magalang, Ulysses J and Punjabi, Naresh M and Anderer, Peter},
  title = {Scoring sleep with artificial intelligence enables quantification of sleep stage ambiguity: hypnodensity based on multiple expert scorers and auto-scoring},
  journal = {Sleep},
  year = {2023},
  doi = {10.1093/sleep/zsac154}
}
Kostenlos starten →