SleepVST: Sleep Staging from Near-Infrared Video Signals using Pre-Trained Transformers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Carter, Jonathan F., Jorge, João, Gibson, Oliver, Tarassenko, Lionel
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914741993078784
author Carter, Jonathan F.
Jorge, João
Gibson, Oliver
Tarassenko, Lionel
author_facet Carter, Jonathan F.
Jorge, João
Gibson, Oliver
Tarassenko, Lionel
contents Advances in camera-based physiological monitoring have enabled the robust, non-contact measurement of respiration and the cardiac pulse, which are known to be indicative of the sleep stage. This has led to research into camera-based sleep monitoring as a promising alternative to "gold-standard" polysomnography, which is cumbersome, expensive to administer, and hence unsuitable for longer-term clinical studies. In this paper, we introduce SleepVST, a transformer model which enables state-of-the-art performance in camera-based sleep stage classification (sleep staging). After pre-training on contact sensor data, SleepVST outperforms existing methods for cardio-respiratory sleep staging on the SHHS and MESA datasets, achieving total Cohen's kappa scores of 0.75 and 0.77 respectively. We then show that SleepVST can be successfully transferred to cardio-respiratory waveforms extracted from video, enabling fully contact-free sleep staging. Using a video dataset of 50 nights, we achieve a total accuracy of 78.8\% and a Cohen's $κ$ of 0.71 in four-class video-based sleep staging, setting a new state-of-the-art in the domain.
format Preprint
id arxiv_https___arxiv_org_abs_2404_03831
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SleepVST: Sleep Staging from Near-Infrared Video Signals using Pre-Trained Transformers
Carter, Jonathan F.
Jorge, João
Gibson, Oliver
Tarassenko, Lionel
Computer Vision and Pattern Recognition
Human-Computer Interaction
Neurons and Cognition
Advances in camera-based physiological monitoring have enabled the robust, non-contact measurement of respiration and the cardiac pulse, which are known to be indicative of the sleep stage. This has led to research into camera-based sleep monitoring as a promising alternative to "gold-standard" polysomnography, which is cumbersome, expensive to administer, and hence unsuitable for longer-term clinical studies. In this paper, we introduce SleepVST, a transformer model which enables state-of-the-art performance in camera-based sleep stage classification (sleep staging). After pre-training on contact sensor data, SleepVST outperforms existing methods for cardio-respiratory sleep staging on the SHHS and MESA datasets, achieving total Cohen's kappa scores of 0.75 and 0.77 respectively. We then show that SleepVST can be successfully transferred to cardio-respiratory waveforms extracted from video, enabling fully contact-free sleep staging. Using a video dataset of 50 nights, we achieve a total accuracy of 78.8\% and a Cohen's $κ$ of 0.71 in four-class video-based sleep staging, setting a new state-of-the-art in the domain.
title SleepVST: Sleep Staging from Near-Infrared Video Signals using Pre-Trained Transformers
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
Neurons and Cognition
url https://arxiv.org/abs/2404.03831