ChatPPG.
Join free

Paperdoi:10.3390/s21134302

The Promise of Sleep: A Multi-Sensor Approach for Accurate Sleep Stage Detection Using the Oura Ring

Unconfirmed2021Added Nov 4, 2026

  • MA
  • HH

Authors: Marco Altini, Hannu Kinnunen (Oura Health)

Publisher (opens in a new tab) Cite

TL;DR

LightGBM on ring accelerometer, temperature, HRV (PPG-derived) and circadian features; 106 participants, 440 nights, 3,444 h of PSG, 5-fold CV. 4-class (W/L/D/R) accuracy: ACC-only 57% (F1 0.68), +temp 60%, +HRV 76%, +circadian 79% (F1 0.78). 2-class 94% → 96%.

  • Form factor: ring

Abstract

Consumer-grade sleep trackers represent a promising tool for large scale studies and health management. However, the potential and limitations of these devices remain less well quantified. Addressing this issue, we aim at providing a comprehensive analysis of the impact of accelerometer, autonomic nervous system (ANS)-mediated peripheral signals, and circadian features for sleep stage detection on a large dataset. Four hundred and forty nights from 106 individuals, for a total of 3444 h of combined polysomnography (PSG) and physiological data from a wearable ring, were acquired. Features were extracted to investigate the relative impact of different data streams on 2-stage (sleep and wake) and 4-stage classification accuracy (light NREM sleep, deep NREM sleep, REM sleep, and wake). Machine learning models were evaluated using a 5-fold cross-validation and a standardized framework for sleep stage classification assessment. Accuracy for 2-stage detection (sleep, wake) was 94% for a simple accelerometer-based model and 96% for a full model that included ANS-derived and circadian features. Accuracy for 4-stage detection was 57% for the accelerometer-based model and 79% when including ANS-derived and circadian features. Combining the compact form factor of a finger ring, multidimensional biometric sensory streams, and machine learning, high accuracy wake-sleep detection and sleep staging can be accomplished.

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

Results on ChatPPG leaderboards · 1

All leaderboards
LeaderboardMethodResultRank
oura-2021 accuracy (4class)Sleep stagingOura Gen2 research ring, LightGBM ACC+temp+HRV+circadian79% (F1 0.78; ACC-only 57%)accuracy, lower is betterUnranked

1 row is credited to this paper. Ranks apply within each leaderboard only, as reported by the source.

Tasks & signals

Tasks

Sleep staging

Signals

PPGIMUTemp

Keywords

SleepStagingOuraRing

How it works

How Method works: Setup → Method → TargetSetup: Signals (PPG, ACC, temperature); Form factor (ring). Method: Method. Target: Sleep staging.SetupSignals: PPG, ACC, temperatureSignalsPPG, ACC, temperatureForm factor: ringForm factorringMethodMethodTargetSleep stagingSleep staging

Cite this paper

Cite this paper with the fields recorded here. Check it against the publisher before submitting.

Altini, M., & Kinnunen, H. (2021). The Promise of Sleep: A Multi-Sensor Approach for Accurate Sleep Stage Detection Using the Oura Ring. https://doi.org/10.3390/s21134302
Altini, Marco and Hannu Kinnunen. 2021. "The Promise of Sleep: A Multi-Sensor Approach for Accurate Sleep Stage Detection Using the Oura Ring." https://doi.org/10.3390/s21134302.
Altini, M. and Kinnunen, H. (2021) 'The Promise of Sleep: A Multi-Sensor Approach for Accurate Sleep Stage Detection Using the Oura Ring'. doi: 10.3390/s21134302.
Altini, Marco, and Hannu Kinnunen "The Promise of Sleep: A Multi-Sensor Approach for Accurate Sleep Stage Detection Using the Oura Ring." 2021. https://doi.org/10.3390/s21134302.
M. Altini and H. Kinnunen, "The Promise of Sleep: A Multi-Sensor Approach for Accurate Sleep Stage Detection Using the Oura Ring," 2021, doi: 10.3390/s21134302.
@misc{altini2021promise,
  title         = {{The Promise of Sleep: A Multi-Sensor Approach for Accurate Sleep Stage Detection Using the Oura Ring}},
  author        = {Altini, Marco and Kinnunen, Hannu},
  year          = {2021},
  doi           = {10.3390/s21134302}
}

Added to the ChatPPG research hub