Rxivist logo

Detecting sleep in free-living conditions without sleep-diaries: a device-agnostic, wearable heart rate sensing approach

By Ignacio Perez-Pozuelo, Marius Posa, Dimitris Spathis, Kate Westgate, Nicholas J. Wareham, Cecilia Mascolo, Soren Brage, Joao Palotti

Posted 08 Sep 2020
medRxiv DOI: 10.1101/2020.09.05.20188367

Study Objectives: The rise of multisensor wearable devices offers a unique opportunity for the objective inference of sleep outside laboratories, enabling longitudinal monitoring in large populations. To enhance objectivity and facilitate cross-cohort comparisons, sleep detection algorithms in free-living conditions should rely on personalized but device-agnostic features, which can be applied without laborious human annotations or sleep diaries. We developed and validated a heart rate-based algorithm that captures inter- and intra-individual sleep differences, does not require human input and can be applied in free-living conditions. Methods: The algorithm was evaluated across four study cohorts using different research- and consumer-grade devices for over 2,000 nights. Recording periods included both 24-hour free-living and conventional lab-based night-only data. Our method was systematically optimized and validated against polysomnography and sleep diaries and compared to sleep periods produced by accelerometry-based angular change algorithms. Results: We evaluated our approach in four cohorts comprising two free-living studies with detailed sleep diaries and two PSG studies. In the free-living studies, the algorithm yielded a mean squared error (MSE) of 0.06 to 0.07 and a total sleep time deviation of -0.60 to -14.08 minutes. In the laboratory studies, the MSE ranged between 0.06 and 0.10 yielding a time deviation between -23.23 and -33.15 minutes. Conclusions: Our results suggest that our heart rate-based algorithm can reliably and objectively infer sleep under longitudinal, free-living conditions, independent of the wearable device used. This represents the first open-source algorithm to leverage heart rate data for inferring sleep without requiring sleep diaries or annotations.

Download data

  • Downloaded 309 times
  • Download rankings, all-time:
    • Site-wide: 78,361
    • In health informatics: 256
  • Year to date:
    • Site-wide: 19,650
  • Since beginning of last month:
    • Site-wide: 19,650

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide


Sign up for the Rxivist weekly newsletter! (Click here for more details.)