Pediatric Automatic Sleep Staging: A Comparative Study of State-of-the-Art Deep Learning Methods.

Area of Science:

• Computational neuroscience
• Pediatric sleep medicine
• Artificial intelligence in healthcare

Background:

• Current automatic sleep staging algorithms excel in adults but their generalization to children, who have unique polysomnography (PSG) characteristics, is unknown.
• Pediatric sleep disorders, like obstructive sleep apnea (OSA), require accurate sleep staging for diagnosis and management.

Purpose of the Study:

• To evaluate the efficacy of state-of-the-art deep learning algorithms for automatic sleep staging in a large pediatric cohort.
• To compare the performance of individual deep neural networks and their ensemble models in pediatric sleep staging.

Main Methods:

• A large-scale comparative study involving over 1,200 children with varying obstructive sleep apnea (OSA) severity.
• Six distinct deep neural network architectures were employed for automatic sleep staging.
• Ensemble models were created by combining the predictions of individual deep learning models.

Main Results:

• Individual automated pediatric sleep stagers achieved expert-level performance comparable to adult studies.
• Ensemble models significantly improved staging accuracy to 88.8% accuracy, 0.852 Cohen's kappa, and 85.8% macro F1-score.
• The algorithms demonstrated robustness to concept drift and were reliable even with data recorded months apart and post-intervention.

Conclusions:

• State-of-the-art deep learning models, particularly ensemble approaches, demonstrate high accuracy in pediatric sleep staging.
• Despite high accuracy, the clinical significance of these automated staging improvements requires further investigation.
• The agreement among automatic stagers suggests limited scope for further enhancement of current algorithms.