Pediatric SleepNet: a deep learning network for reliable pediatric sleep staging across developmental stages
SLEEP · 14.08.2026 · 49 (8)
DOI: 10.1093/sleep/zsag064 ↗Kurz gefasst
Fachartikel in der Zeitschrift SLEEP, online erschienen am 10.03.2026. Verfasst von Ayush Tripathi und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology, Beth Israel Deaconess Medical Center, Boston, MA, United States. Hauptthemen laut MEDLINE: Deep Learning, Sleep Stages. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCRR NIH HHS, NINDS NIH HHS, NIA NIH HHS.
Abstract (Originalsprache)
Study Objectives Manual sleep staging in pediatric populations is challenging due to developmental variability and limited scoring consistency, especially in infants and toddlers. We developed a multimodal deep learning model for pediatric sleep staging and evaluated its performance across a broad age range and diverse clinical subgroups. Methods We trained a U-Net-inspired encoder-decoder model (pediatric SleepNet) using 9-channel input signals: electroencephalography (EEG), electrooculography (EOG), and chin electromyography (EMG) using 35-epoch segments from clinical pediatric polysomnograms (PSGs). Models were trained separately on three age groups (<6 months, 6-12 months, >1 year) using 9150 PSGs, with 2455 PSGs reserved for validation. Evaluation was conducted on 3804 held-out test recordings. Performance was compared with U-Sleep and the Complete Artificial Intelligence Sleep Report (CAISR), and stratified analyses were performed across ages, sexes, and seven ICD-10-based disease categories. External validation was conducted on two independent datasets, CHAT and PATS. Results pediatric SleepNet achieved robust performance across all age groups, with mean Cohen’s Kappa increasing from 0.49 (0–6 months) to 0.72 (>12 years). It significantly outperformed U-Sleep and CAISR across early developmental stages. Three-class staging yielded mean Cohen’s Kappa increasing from 0.66 (0–6 months) to 0.79 (>12 years). Sex-based differences were negligible. However, significant reductions in performance were observed in children with epilepsy, Down syndrome, hydrocephalus, and other neurodevelopmental conditions. External validation yielded Kappa values >0.69 comparable to the internal test set. Conclusions pediatric SleepNet demonstrates reliable sleep staging across pediatric development. Its robust performance across age, disease, and external datasets supports its potential for clinical and research use in pediatric sleep medicine.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Neurology, Beth Israel Deaconess Medical Center, Boston, MA, United States.
- Harvard Medical School, Boston, MA, United States.
- Harvard John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, United States.
- Emory University School of Medicine, Atlanta, GA, United States.
- Department of Epidemiology and Biostatistics, University of California, San Francisco, United States.
- California Pacific Medical Center Research, San Francisco, CA, United States.
ORCID-Profile: Ayush Tripathi, Arnav Gupta, Wolfgang Ganglberger, Haoqi Sun, Emmanuel Mignot, Matthew A Reyna, Lynn Marie Trotti, Kiran Maski, Robert J Thomas, M Brandon Westover
Förderung
- NCRR NIH HHS
- NINDS NIH HHS
- NIA NIH HHS
- NHLBI NIH HHS
- NIH
- NCATS NIH HHS
Zitieren
APA
Tripathi, A., Gupta, A., Ganglberger, W., Waters, S., Sun, H., Nasiri, S., Mitra, A., Stone, K. L., Mignot, E., Hwang, D., Reyna, M. A., Trotti, L. M., Clifford, G. D., Maski, K., Katwa, U., Thomas, R. J., & Westover, M. B. (2026). Pediatric SleepNet: a deep learning network for reliable pediatric sleep staging across developmental stages. SLEEP, 49(8). https://doi.org/10.1093/sleep/zsag064
Vancouver
Tripathi A, Gupta A, Ganglberger W, Waters S, Sun H, Nasiri S, et al. Pediatric SleepNet: a deep learning network for reliable pediatric sleep staging across developmental stages. SLEEP. 2026;49(8). doi:10.1093/sleep/zsag064
BibTeX
@article{Tripathi2026,
author = {Tripathi, Ayush and Gupta, Arnav and Ganglberger, Wolfgang and Waters, Samuel and Sun, Haoqi and Nasiri, Samaneh and Mitra, Ayan and Stone, Katie L and Mignot, Emmanuel and Hwang, Dennis and Reyna, Matthew A and Trotti, Lynn Marie and Clifford, Gari D and Maski, Kiran and Katwa, Umakanth and Thomas, Robert J and Westover, M Brandon},
title = {Pediatric SleepNet: a deep learning network for reliable pediatric sleep staging across developmental stages},
journal = {SLEEP},
year = {2026},
volume = {49},
number = {8},
doi = {10.1093/sleep/zsag064}
}
EUVIMED