Pediatric SleepNet: A Deep Learning Network for Reliable Pediatric Sleep Staging Across Developmental Stages.

Area of Science:

• Pediatric Sleep Medicine
• Artificial Intelligence in Healthcare
• Computational Neuroscience

Background:

• Manual sleep staging in children is difficult due to developmental variations and inconsistent scoring, particularly in infants.
• Accurate sleep staging is crucial for diagnosing and managing pediatric sleep disorders.

Purpose of the Study:

• To develop and evaluate a multimodal deep learning model, pediatric SleepNet, for automated sleep staging in pediatric populations.
• To assess the model's performance across a wide age range and diverse clinical subgroups.

Main Methods:

• A U-Net-inspired encoder-decoder model (pediatric SleepNet) was trained using 9-channel physiological signals (EEG, EOG, EMG) from 9,150 pediatric polysomnograms (PSGs).
• Models were trained on three age groups (<6 months, 6-12 months, >1 year) and evaluated on 3,804 test recordings, with comparisons to U-Sleep and CAISR.
• Stratified analyses were conducted across ages, sexes, and disease categories, with external validation on two independent datasets.

Main Results:

• pediatric SleepNet demonstrated robust performance, with mean Cohen's Kappa increasing from 0.49 (0-6 months) to 0.72 (>12 years).
• The model significantly outperformed U-Sleep and CAISR in early developmental stages and showed comparable performance on external validation datasets (Kappa >0.69).
• Performance reductions were noted in children with epilepsy, Down syndrome, hydrocephalus, and other neurodevelopmental conditions.

Conclusions:

• pediatric SleepNet provides reliable sleep staging across pediatric development, ages, and diverse clinical conditions.
• The model's strong performance across internal and external datasets supports its utility in pediatric sleep medicine research and clinical applications.