Evaluation of automated pediatric sleep stage classification using U-Sleep: a convolutional neural network.

Journal: Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine
Published Date: Feb 1, 2025

Abstract

STUDY OBJECTIVES: U-Sleep is a publicly available automated sleep stager, but has not been independently validated using pediatric data. We aimed to (1) test the hypothesis that U-Sleep performance is equivalent to trained humans, using a concordance dataset of 50 pediatric polysomnogram excerpts scored by multiple trained scorers, and (2) identify clinical and demographic characteristics that impact U-Sleep accuracy, using a clinical dataset of 3,114 polysomnograms from a tertiary center.

Authors

  • Ajay Kevat
    Department of Paediatrics, Monash University, Melbourne, Australia. ajaykevat@gmail.com.
  • Rylan Steinkey
    The University of Queensland, Brisbane, Queensland, Australia.
  • Sadasivam Suresh
    Department of Respiratory and Sleep Medicine, Queensland Children's Hospital, Brisbane, Queensland, Australia.
  • Warren R Ruehland
    Department of Respiratory and Sleep Medicine, Austin Health, Melbourne, Victoria, Australia.
  • Jasneek Chawla
    Department of Respiratory and Sleep Medicine, Queensland Children's Hospital, Brisbane, Queensland, Australia.
  • Philip I Terrill
    The University of Queensland, Brisbane, Queensland, Australia.
  • Andrew Collaro
    Department of Respiratory and Sleep Medicine, Queensland Children's Hospital, Brisbane, Queensland, Australia.
  • Kartik Iyer
    The University of Queensland, Brisbane, Queensland, Australia.

Keywords

External Resources

Popular Topics
Recent Journals