Self-supervised learning of accelerometer data provides new insights for sleep and its association with mortality

Hang Yuan; Tatiana Plekhanova; Rosemary Walmsley; Amy C Reynolds; Kathleen J Maddison; Maja Bucan; Philip Gehrman; Alex Rowlands; David W Ray; Derrick Bennett; Joanne McVeigh; Leon Straker; Peter Eastwood; Simon D Kyle; Aiden Doherty

doi:10.1038/s41746-024-01065-0

Back

Self-supervised learning of accelerometer data provides new insights for sleep and its association with mortality

Journal article

Open access

Peer reviewed

Self-supervised learning of accelerometer data provides new insights for sleep and its association with mortality

Hang Yuan, Tatiana Plekhanova, Rosemary Walmsley, Amy C Reynolds, Kathleen J Maddison, Maja Bucan, Philip Gehrman, Alex Rowlands, David W Ray, Derrick Bennett, …

NPJ digital medicine, Vol.7, 86

2024

DOI: https://doi.org/10.1038/s41746-024-01065-0

PMID: 38769347

Files and links (1)

pdf

Published2.83 MBDownload View

CC BY V4.0, Open Access

Abstract

Sleep is essential to life. Accurate measurement and classification of sleep/wake and sleep stages is important in clinical studies for sleep disorder diagnoses and in the interpretation of data from consumer devices for monitoring physical and mental well-being. Existing non-polysomnography sleep classification techniques mainly rely on heuristic methods developed in relatively small cohorts. Thus, we aimed to establish the accuracy of wrist-worn accelerometers for sleep stage classification and subsequently describe the association between sleep duration and efficiency (proportion of total time asleep when in bed) with mortality outcomes. We developed a self-supervised deep neural network for sleep stage classification using concurrent laboratory-based polysomnography and accelerometry. After exclusion, 1448 participant nights of data were used for training. The difference between polysomnography and the model classifications on the external validation was 34.7 min (95% limits of agreement (LoA): -37.8-107.2 min) for total sleep duration, 2.6 min for REM duration (95% LoA: -68.4-73.4 min) and 32.1 min (95% LoA: -54.4-118.5 min) for NREM duration. The sleep classifier was deployed in the UK Biobank with 100,000 participants to study the association of sleep duration and sleep efficiency with all-cause mortality. Among 66,214 UK Biobank participants, 1642 mortality events were observed. Short sleepers (<6 h) had a higher risk of mortality compared to participants with normal sleep duration of 6-7.9 h, regardless of whether they had low sleep efficiency (Hazard ratios (HRs): 1.58; 95% confidence intervals (CIs): 1.19-2.11) or high sleep efficiency (HRs: 1.45; 95% CIs: 1.16-1.81). Deep-learning-based sleep classification using accelerometers has a fair to moderate agreement with polysomnography. Our findings suggest that having short overnight sleep confers mortality risk irrespective of sleep continuity.

Details

Title: Self-supervised learning of accelerometer data provides new insights for sleep and its association with mortality
Authors/Creators: Hang Yuan - University of Oxford
Tatiana Plekhanova - University of Leicester
Rosemary Walmsley - University of Oxford
Amy C Reynolds - Flinders University
Kathleen J Maddison - The University of Western Australia
Maja Bucan - University of Pennsylvania
Philip Gehrman - University of Pennsylvania
Alex Rowlands - University of Leicester
David W Ray - John Radcliffe Hospital
Derrick Bennett - University of Oxford
Joanne McVeigh - Curtin University
Leon Straker - Curtin University
Peter Eastwood - Murdoch University, Vice Chancellery
Simon D Kyle - Sir Jules Thorn Sleep & Circadian Neuroscience Institute, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK
Aiden Doherty - University of Oxford
Publication Details: NPJ digital medicine, Vol.7, 86
Publisher: Published in partnership with Seoul National University Bundang Hospital
Grant note: 227093/Z/23/Z / Wellcome Trust (Wellcome) R21 MH103963 / NIMH NIH HHS NIHR203316 / DH | National Institute for Health Research (NIHR) Wellcome Trust RE/18/3/34214 / British Heart Foundation (BHF) 223100/Z/21/Z / Wellcome Trust (Wellcome)
Identifiers: 991005666668507891
Copyright: © The Author(s) 2024
Murdoch Affiliation: Health Futures Institute; Vice Chancellery
Language: English
Resource Type: Journal article

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

Metrics

8 File views/ downloads

60 Record Views

20 Times Cited - Web of Science

See more details

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration; International collaboration
Citation topics: 1 Clinical & Life Sciences; 1.137 Sleep Science & Circadian Systems; 1.137.349 Insomnia
Web Of Science research areas: Health Care Sciences & Services; Medical Informatics
ESI research areas: Clinical Medicine