Paperdoi:10.1088/1361-6579/ae0119
Learning individual autonomic representations of sleep stages to improve photoplethysmography based sleep monitoring
Physiological Measurement 46(9):095012 (IOP), published online 2025-09-30
Licence: CC BY 4.0
TL;DR
59 people with sleep disorders wore a wrist PPG device and a wearable EEG at home for up to 7 nights. A general PPG sleep-staging model was personalised by fine-tuning (partial retraining) on each subject's own PPG, using the wearable-EEG stage classifications as labels. The EEG model acts as the teacher at the label level.
- Form factor: wrist
Abstract
Objective. Wrist-worn photoplethysmography (PPG) enables scalable, long-term unobtrusive sleep monitoring through the expression of sympathetic and parasympathetic activity in heart rate variability. However, interindividual differences in the sympatho-vagal balance may inherently limited general PPG-based sleep staging models. This study investigates whether learning individual autonomic representations through model personalization can improve PPG-based automated sleep staging performance. Approach. Concurrent wrist-worn PPG and wearable electroencephalography (EEG) were collected during home monitoring for up to seven nights in a heterogeneous sleep-disordered population (n = 59). Personalization was performed through finetuning (i.e. partial retraining) a general PPG-based model by coupling the subject-specific PPG data with the wearable EEG stage classifications. Performance of the general and personalized models were compared on PPG acquired during a gold-standard clinical polysomnography, testing their agreement on 4-stage classification (W/N1+N2/N3/REM) with the manual scoring. Main result. Overall performance increased in 82.5% of the subjects, with significantly improved performance reached when personalizing the model on three or more training nights. Performance increased with personalization on additional training nights for each stage: wake (β= .005, p β = .003, p β = .004, p β = .005, p β = .009, p β = .011, p Significance. Personalization can overcome one-size-fits-all limitations of a general model and should be considered for PPG-based sleep staging when an altered autonomic modulation is expected that deviates from the general model’s global representation.
Verbatim from the publisher's DOI record (opens in a new tab) · Publisher licence: https://creativecommons.org/licenses/by/4.0/
Results on ChatPPG leaderboards
All leaderboardsNo results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.
Tasks & signals
Tasks
Signals
Keywords
How it works
Cite this paper
APA
van der Aar, J. F., van Gilst, M. M., van den Ende, D. A., Overeem, S., Peri, E., & Fonseca, P. (2025). Learning individual autonomic representations of sleep stages to improve photoplethysmography based sleep monitoring. Physiological Measurement. https://doi.org/10.1088/1361-6579/ae0119
BibTeX
@article{aar2025learning,
title = {{Learning individual autonomic representations of sleep stages to improve photoplethysmography based sleep monitoring}},
author = {van der Aar, Jaap F. and van Gilst, Merel M. and van den Ende, Daan A. and Overeem, Sebastiaan and Peri, Elisabetta and Fonseca, Pedro},
year = {2025},
journal = {Physiological Measurement},
doi = {10.1088/1361-6579/ae0119}
}Built from the hub record. Check it against the publisher before submitting.
Added to the ChatPPG research hub
