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

SleepNet: a wrist-accelerometer sleep classifier (wake / NREM / REM, 30-s windows) built on a multi-task self-supervised feature extractor pretrained on ~700,000 person-days of unlabelled UK Biobank accelerometry, then fine-tuned with a deep recurrent network on lab PSG. Internal validation (subject-wise 5-fold CV) pooled 1113 PSG nights (Raine Gen1/Gen2 + Newcastle); external validation 53 nights (Leicester + Pennsylvania). Sleep/wake F1 0.75 ± 0.1 internal, 0.66 ± 0.12 external; 3-class F1 0.57 / 0.49 and epoch kappa 0.39 / 0.32.

• Form factor: wrist

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, 1113 participant nights of data were used for training. The difference between polysomnography and the model classifications on the external validation was 48.2 min (95% limits of agreement (LoA): −50.3 to 146.8 min) for total sleep duration, −17.1 min for REM duration (95% LoA: −56.7 to 91.0 min) and 31.1 min (95% LoA: −67.3 to 129.5 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 66,262 UK Biobank participants, 1644 mortality events were observed. Short sleepers (<6 h) had a higher risk of mortality compared to participants with normal sleep duration 6–7.9 h, regardless of whether they had low sleep efficiency (Hazard ratios (HRs): 1.36; 95% confidence intervals (CIs): 1.18 to 1.58) or high sleep efficiency (HRs: 1.29; 95% CIs: 1.04–1.61). 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.

Verbatim from the publisher's DOI record (opens in a new tab) · Publisher licence: https://creativecommons.org/licenses/by/4.0

4 rows are credited to this paper. Ranks apply within each leaderboard only, as reported by the source.

• Newcastle PSG + GENEActiv both wrists (sleep clinic, 2015)TrainingEvaluation28 subjects · IMU
• UK Biobank wrist accelerometer (Axivity AX3 / field 90001)Pretraining103,568 subjects · IMU