Paperdoi:10.1038/s41598-023-36444-2
A computationally efficient algorithm for wearable sleep staging in clinical populations
Scientific Reports
TL;DR
Neural net 4-class staging (wake / N1+N2 / N3 / REM) from reflective PPG interbeat intervals + instantaneous HR and accelerometer gross body movements, 30 s epochs, validated vs PSG in clinical sleep-pathology populations. Median epoch κ 0.638, accuracy 77.8%, matching prior HRV-feature approach with ~50× faster execution — practical for on-device/wearable deployment.
- Form factor: wrist
Abstract
This study describes a computationally efficient algorithm for 4-class sleep staging based on cardiac activity and body movements. Using an accelerometer to calculate gross body movements and a reflective photoplethysmographic (PPG) sensor to determine interbeat intervals and a corresponding instantaneous heart rate signal, a neural network was trained to classify between wake, combined N1 and N2, N3 and REM sleep in epochs of 30 s. The classifier was validated on a hold-out set by comparing the output against manually scored sleep stages based on polysomnography (PSG). In addition, the execution time was compared with that of a previously developed heart rate variability (HRV) feature-based sleep staging algorithm. With a median epoch-per-epoch κ of 0.638 and accuracy of 77.8% the algorithm achieved an equivalent performance when compared to the previously developed HRV-based approach, but with a 50-times faster execution time. This shows how a neural network, without leveraging any a priori knowledge of the domain, can automatically “discover” a suitable mapping between cardiac activity and body movements, and sleep stages, even in patients with different sleep pathologies. In addition to the high performance, the reduced complexity of the algorithm makes practical implementation feasible, opening up new avenues in sleep diagnostics.
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
Fonseca, P., Ross, M., Cerny, A., Anderer, P., van Meulen, F., Janssen, H., Pijpers, A., Dujardin, S., van Hirtum, P., van Gilst, M., & Overeem, S. (2023). A computationally efficient algorithm for wearable sleep staging in clinical populations. Scientific Reports. https://doi.org/10.1038/s41598-023-36444-2
BibTeX
@article{fonseca2023computationally,
title = {{A computationally efficient algorithm for wearable sleep staging in clinical populations}},
author = {Fonseca, Pedro and Ross, Marco and Cerny, Andreas and Anderer, Peter and van Meulen, Fokke and Janssen, Hennie and Pijpers, Angelique and Dujardin, Sylvie and van Hirtum, Pauline and van Gilst, Merel and Overeem, Sebastiaan},
year = {2023},
journal = {Scientific Reports},
doi = {10.1038/s41598-023-36444-2}
}Built from the hub record. Check it against the publisher before submitting.
Added to the ChatPPG research hub
