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

Yuan H, Plekhanova T, Walmsley R, Reynolds AC, Maddison KJ, Bucan M, Gehrman P, Rowlands A, Ray DW, Bennett D, McVeigh J, Straker L, Eastwood P, Kyle SD, Doherty A. 20 May 2024 Nature. doi: 10.1038/s41746-024-01065-0

Publication date: 20 May 2024

Keywords: accelerometer data, mortality, Self-supervised learning, sleep

What is already known about this subject:

  • 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.
  • This research 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.

What this study adds

  • 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.
View full publication

Areas of Interest