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

Marco Altini, Hannu Kinnunen, Marco Altini, Hannu Kinnunen

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.

Keywords: accelerometer; heart rate variability; machine learning; sleep staging; wearables.

Conflict of interest statement

H.K. is employed by Oura Health, M.A. is an advisor at Oura Health.

Figures

Figure 1
Figure 1
Technical illustration of the second generation Oura ring. The ring has a titanium cover, battery, power handling circuit, double core processor, memory, two LEDs, a photosensor, temperature sensors, 3-D accelerometer, and Bluetooth connectivity to a smartphone app.
Figure 2
Figure 2
Accelerometer and temperature data for one participant (Dataset 1: Singapore, 15 years old) and one night. Sleep stages annotated from PSG data are color-coded.
Figure 3
Figure 3
Heart rate and HRV (rMSSD) data for one participant (Dataset 1: Singapore, 15 years old) and one night. Sleep stages annotated from PSG data are color-coded.
Figure 4
Figure 4
Cosine, decay, and linear functions used to model sensor-independent circadian features.
Figure 5
Figure 5
Bland-Altman plots for total sleep time (TST), 2-stage classification, and the four models compared in this paper.
Figure 6
Figure 6
Epoch by epoch sensitivity for sleep and wake and the four models compared in this paper. Whiskers are computed as 1.5 times the interquartile range.
Figure 7
Figure 7
Bias and limits of agreement for TST, 4-stage classification, and the four models analyzed in this paper.
Figure 8
Figure 8
Bias and limits of agreement for time in light sleep, 4-stage classification, and the four models analyzed in this paper.
Figure 9
Figure 9
Bias and limits of agreement for time in deep sleep, 4-stage classification, and the four models analyzed in this paper.
Figure 10
Figure 10
Bias and limits of agreement for time in REM sleep, 4-stage classification, and the four models analyzed in this paper.
Figure 11
Figure 11
Epoch by epoch sensitivity for 4-stage classification and the four models compared in this paper. Whiskers are computed as 1.5 times the interquartile range.
Figure 12
Figure 12
Epoch by epoch specificity for 4-stage classification and the four models compared in this paper. Whiskers are computed as 1.5 times the interquartile range.
Figure 13
Figure 13
Example hypnogram for an average night (f1 = 0.78) for the model, including all features (ACC+T+HRV+C).

References

    1. Grandner M.A. Sleep, health, and society. Sleep Med. Clin. 2017;12:1–22. doi: 10.1016/j.jsmc.2016.10.012.
    1. Spiegel K., Tasali E., Leproult R., Van Cauter E. Effects of poor and short sleep on glucose metabolism and obesity risk. Nat. Rev. Endocrinol. 2009;5:253. doi: 10.1038/nrendo.2009.23.
    1. Peppard P.E., Young T., Palta M., Dempsey J., Skatrud J. Longitudinal study of moderate weight change and sleep-disordered breathing. JAMA. 2000;284:3015–3021. doi: 10.1001/jama.284.23.3015.
    1. Krause A.J., Simon E.B., Mander B.A., Greer S.M., Saletin J.M., Goldstein-Piekarski A.N., Walker M.P. The sleep-deprived human brain. Nat. Rev. Neurosci. 2017;18:404. doi: 10.1038/nrn.2017.55.
    1. Freeman D., Sheaves B., Goodwin G.M., Yu L.M., Nickless A., Harrison P.J., Emsley R., Luik A.I., Foster R.G., Wadekar V., et al. The effects of improving sleep on mental health (OASIS): A randomised controlled trial with mediation analysis. Lancet Psychiatry. 2017;4:749–758. doi: 10.1016/S2215-0366(17)30328-0.
    1. De Zambotti M., Cellini N., Goldstone A., Colrain I.M., Baker F.C. Wearable sleep technology in clinical and research settings. Med. Sci. Sport. Exerc. 2019;51:1538. doi: 10.1249/MSS.0000000000001947.
    1. Depner C.M., Cheng P.C., Devine J.K., Khosla S., de Zambotti M., Robillard R., Vakulin A., Drummond S.P. Wearable technologies for developing sleep and circadian biomarkers: A summary of workshop discussions. Sleep. 2020;43:zsz254. doi: 10.1093/sleep/zsz254.
    1. Shelgikar A.V., Anderson P.F., Stephens M.R. Sleep tracking, wearable technology, and opportunities for research and clinical care. Chest. 2016;150:732–743. doi: 10.1016/j.chest.2016.04.016.
    1. Berryhill S., Morton C.J., Dean A., Berryhill A., Provencio-Dean N., Patel S.I., Estep L., Combs D., Mashaqi S., Gerald L.B., et al. Effect of wearables on sleep in healthy individuals: A randomized crossover trial and validation study. J. Clin. Sleep Med. 2020;16:775–783. doi: 10.5664/jcsm.8356.
    1. Ameen M.S., Cheung L.M., Hauser T., Hahn M.A., Schabus M. About the accuracy and problems of consumer devices in the assessment of sleep. Sensors. 2019;19:4160. doi: 10.3390/s19194160.
    1. de Zambotti M., Rosas L., Colrain I.M., Baker F.C. The sleep of the ring: Comparison of the ŌURA sleep tracker against polysomnography. Behav. Sleep Med. 2019;17:124–136. doi: 10.1080/15402002.2017.1300587.
    1. Kuula L., Gradisar M., Martinmäki K., Richardson C., Bonnar D., Bartel K., Lang C., Leinonen L., Pesonen A. Using big data to explore worldwide trends in objective sleep in the transition to adulthood. Sleep Med. 2019;62:69–76. doi: 10.1016/j.sleep.2019.07.024.
    1. Khosla S., Deak M.C., Gault D., Goldstein C.A., Hwang D., Kwon Y., O’Hearn D., Schutte-Rodin S., Yurcheshen M., Rosen I.M., et al. Consumer sleep technology: An American Academy of Sleep Medicine position statement. J. Clin. Sleep Med. 2018;14:877–880. doi: 10.5664/jcsm.7128.
    1. Landolt H.P., Dijk D.J., Gaus S.E., Borbély A.A. Caffeine reduces low-frequency delta activity in the human sleep EEG. Neuropsychopharmacology. 1995;12:229–238. doi: 10.1016/0893-133X(94)00079-F.
    1. Mourtazaev M., Kemp B., Zwinderman A., Kamphuisen H. Age and gender affect different characteristics of slow waves in the sleep EEG. Sleep. 1995;18:557–564. doi: 10.1093/sleep/18.7.557.
    1. Rosenberg R.S., Van Hout S. The American Academy of Sleep Medicine inter-scorer reliability program: Sleep stage scoring. J. Clin. Sleep Med. 2013;9:81–87. doi: 10.5664/jcsm.2350.
    1. Van De Water A.T., Holmes A., Hurley D.A. Objective measurements of sleep for non-laboratory settings as alternatives to polysomnography—A systematic review. J. Sleep Res. 2011;20:183–200. doi: 10.1111/j.1365-2869.2009.00814.x.
    1. Scott H., Lack L., Lovato N. A systematic review of the accuracy of sleep wearable devices for estimating sleep onset. Sleep Med. Rev. 2020;49:101227. doi: 10.1016/j.smrv.2019.101227.
    1. Sundararajan K., Georgievska S., Te Lindert B.H., Gehrman P.R., Ramautar J., Mazzotti D.R., Sabia S., Weedon M.N., van Someren E.J., Ridder L., et al. Sleep classification from wrist-worn accelerometer data using random forests. Sci. Rep. 2021;11:1–10. doi: 10.1038/s41598-020-79217-x.
    1. Fonseca P., Weysen T., Goelema M.S., Møst E.I., Radha M., Lunsingh Scheurleer C., van den Heuvel L., Aarts R.M. Validation of photoplethysmography-based sleep staging compared with polysomnography in healthy middle-aged adults. Sleep. 2017;40:zsx097. doi: 10.1093/sleep/zsx097.
    1. de Zambotti M., Goldstone A., Claudatos S., Colrain I.M., Baker F.C. A validation study of Fitbit Charge 2™ compared with polysomnography in adults. Chronobiol. Int. 2018;35:465–476. doi: 10.1080/07420528.2017.1413578.
    1. Beattie Z., Pantelopoulos A., Ghoreyshi A., Oyang Y., Statan A., Heneghan C. 0068 estimation of sleep stages using cardiac and accelerometer data from a wrist-worn device. Sleep. 2017;40:A26. doi: 10.1093/sleepj/zsx050.067.
    1. Kortelainen J.M., Mendez M.O., Bianchi A.M., Matteucci M., Cerutti S. Sleep staging based on signals acquired through bed sensor. IEEE Trans. Inf. Technol. Biomed. 2010;14:776–785. doi: 10.1109/TITB.2010.2044797.
    1. Hedner J., White D.P., Malhotra A., Herscovici S., Pittman S.D., Zou D., Grote L., Pillar G. Sleep staging based on autonomic signals: A multi-center validation study. J. Clin. Sleep Med. 2011 doi: 10.5664/JCSM.1078.
    1. Long X. Sleep Wake. Technische Universiteit Eindhoven; Eindhoven, The Netherlands: 2015. On the analysis and classification of sleep stages from cardiorespiratory activity; pp. 1–232.
    1. Walch O., Huang Y., Forger D., Goldstein C. Sleep stage prediction with raw acceleration and photoplethysmography heart rate data derived from a consumer wearable device. Sleep. 2019;42:zsz180. doi: 10.1093/sleep/zsz180.
    1. Danzig R., Wang M., Shah A., Trotti L.M. The wrist is not the brain: Estimation of sleep by clinical and consumer wearable actigraphy devices is impacted by multiple patient-and device-specific factors. J. Sleep Res. 2020;29:e12926. doi: 10.1111/jsr.12926.
    1. Lee I., Park N., Lee H., Hwang C., Kim J.H., Park S. Systematic Review on Human Skin-Compatible Wearable Photoplethysmography Sensors. Appl. Sci. 2021;11:2313. doi: 10.3390/app11052313.
    1. Longmore S.K., Lui G.Y., Naik G., Breen P.P., Jalaludin B., Gargiulo G.D. A comparison of reflective photoplethysmography for detection of heart rate, blood oxygen saturation, and respiration rate at various anatomical locations. Sensors. 2019;19:1874. doi: 10.3390/s19081874.
    1. Menghini L., Cellini N., Goldstone A., Baker F.C., de Zambotti M. A standardized framework for testing the performance of sleep-tracking technology: Step-by-step guidelines and open-source code. Sleep. 2021;44:zsaa170. doi: 10.1093/sleep/zsaa170.
    1. Patanaik A., Ong J.L., Gooley J.J., Ancoli-Israel S., Chee M.W. An end-to-end framework for real-time automatic sleep stage classification. Sleep. 2018;41:zsy041. doi: 10.1093/sleep/zsy041.
    1. Chee N.I., Ghorbani S., Golkashani H.A., Leong R.L., Ong J.L., Chee M.W. Multi-night validation of a sleep tracking ring in adolescents compared with a research actigraph and polysomnography. Nat. Sci. Sleep. 2021;13:177. doi: 10.2147/NSS.S286070.
    1. te Lindert B.H., Van Someren E.J. Sleep estimates using microelectromechanical systems (MEMS) Sleep. 2013;36:781–789. doi: 10.5665/sleep.2648.
    1. Vähä-Ypyä H., Vasankari T., Husu P., Mänttäri A., Vuorimaa T., Suni J., Sievänen H. Validation of cut-points for evaluating the intensity of physical activity with accelerometry-based mean amplitude deviation (MAD) PLoS ONE. 2015;10:e0134813. doi: 10.1371/journal.pone.0134813.
    1. Van Hees V.T., Sabia S., Anderson K.N., Denton S.J., Oliver J., Catt M., Abell J.G., Kivimäki M., Trenell M.I., Singh-Manoux A. A novel, open access method to assess sleep duration using a wrist-worn accelerometer. PLoS ONE. 2015;10:e0142533. doi: 10.1371/journal.pone.0142533.
    1. Kinnunen H., Rantanen A., Kenttä T., Koskimäki H. Feasible assessment of recovery and cardiovascular health: Accuracy of nocturnal HR and HRV assessed via ring PPG in comparison to medical grade ECG. Physiol. Meas. 2020;41:04NT01. doi: 10.1088/1361-6579/ab840a.
    1. Xiao M., Yan H., Song J., Yang Y., Yang X. Sleep stages classification based on heart rate variability and random forest. Biomed. Signal Process. Control. 2013;8:624–633. doi: 10.1016/j.bspc.2013.06.001.
    1. Borbély A.A. A two process model of sleep regulation. Hum. Neurobiol. 1982;1:195–204.
    1. Borbély A.A., Daan S., Wirz-Justice A., Deboer T. The two-process model of sleep regulation: A reappraisal. J. Sleep Res. 2016;25:131–143. doi: 10.1111/jsr.12371.
    1. Huang Y., Mayer C., Cheng P., Siddula A., Burgess H.J., Drake C., Goldstein C., Walch O., Forger D.B. Predicting circadian phase across populations: A comparison of mathematical models and wearable devices. Sleep. 2019 doi: 10.1093/sleep/zsab126.
    1. Ke G., Meng Q., Finley T., Wang T., Chen W., Ma W., Ye Q., Liu T.Y. Lightgbm: A highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst. 2017;30:3146–3154.
    1. Vinayak R.K., Gilad-Bachrach R. Dart: Dropouts meet multiple additive regression trees. Artif. Intell. Stat. 2015;38:489–497.
    1. Imtiaz S.A. A Systematic Review of Sensing Technologies for Wearable Sleep Staging. Sensors. 2021;21:1562. doi: 10.3390/s21051562.
    1. Supratak A., Dong H., Wu C., Guo Y. DeepSleepNet: A model for automatic sleep stage scoring based on raw single-channel EEG. IEEE Trans. Neural Syst. Rehabil. Eng. 2017;25:1998–2008. doi: 10.1109/TNSRE.2017.2721116.
    1. Haghayegh S., Khoshnevis S., Smolensky M.H., Diller K.R., Castriotta R.J. Accuracy of wristband Fitbit models in assessing sleep: Systematic review and meta-analysis. J. Med. Internet Res. 2019;21:e16273. doi: 10.2196/16273.
    1. Stone J.D., Rentz L.E., Forsey J., Ramadan J., Markwald R.R., Finomore V.S. Evaluations of Commercial Sleep Technologies for Objective Monitoring During Routine Sleeping Conditions. Nat. Sci. Sleep. 2020;12:821. doi: 10.2147/NSS.S270705.
    1. Gradisar M., Lack L. Relationships between the circadian rhythms of finger temperature, core temperature, sleep latency, and subjective sleepiness. J. Biol. Rhythm. 2004;19:157–163. doi: 10.1177/0748730403261560.
    1. Harding E.C., Franks N.P., Wisden W. The temperature dependence of sleep. Front. Neurosci. 2019;13:336. doi: 10.3389/fnins.2019.00336.
    1. Campbell S.S., Broughton R.J. Rapid decline in body temperature before sleep: Fluffing the physiological pillow? Chronobiol. Int. 1994;11:126–131. doi: 10.3109/07420529409055899.
    1. Harding E.C., Franks N.P., Wisden W. Sleep and thermoregulation. Curr. Opin. Physiol. 2020;15:7–13. doi: 10.1016/j.cophys.2019.11.008.
    1. Altevogt B.M., Colten H.R. Sleep Disorders and Sleep Deprivation: An Unmet Public Health Problem. The National Academies Press, Institute of Medicine; Washington, DC, USA: 2006.
    1. Stein P.K., Pu Y. Heart rate variability, sleep and sleep disorders. Sleep Med. Rev. 2012;16:47–66. doi: 10.1016/j.smrv.2011.02.005.
    1. Carskadon M.A., Dement W.C. Normal human sleep: An overview. Princ. Pract. Sleep Med. 2005;4:13–23.
    1. Buysse D.J. Sleep health: Can we define it? Does it matter? Sleep. 2014;37:9–17. doi: 10.5665/sleep.3298.
    1. Tilley A.J., Wilkinson R.T. The effects of a restricted sleep regime on the composition of sleep and on performance. Psychophysiology. 1984;21:406–412. doi: 10.1111/j.1469-8986.1984.tb00217.x.
    1. Stone J.D., Ulman H.K., Tran K., Thompson A.G., Halter M.D., Ramadan J.H., Stephenson M., Finomore V.S., Jr., Galster S.M., Rezai A.R., et al. Assessing the Accuracy of Popular Commercial Technologies That Measure Resting Heart Rate and Heart Rate Variability. Front. Sport. Act. Living. 2021;3:37. doi: 10.3389/fspor.2021.585870.
    1. Parak J., Tarniceriu A., Renevey P., Bertschi M., Delgado-Gonzalo R., Korhonen I. Evaluation of the beat-to-beat detection accuracy of PulseOn wearable optical heart rate monitor; Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); Milan, Italy. 25–29 August 2015; pp. 8099–8102.
    1. Koskimäki H., Kinnunen H., Rönkä S., Smarr B. Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers. Association for Computing Machinery; New York, NY, USA: 2019. Following the heart: What does variation of resting heart rate tell about us as individuals and as a population; pp. 1178–1181.
    1. Phan H., Andreotti F., Cooray N., Chén O.Y., De Vos M. SeqSleepNet: End-to-end hierarchical recurrent neural network for sequence-to-sequence automatic sleep staging. IEEE Trans. Neural Syst. Rehabil. Eng. 2019;27:400–410. doi: 10.1109/TNSRE.2019.2896659.

Source: PubMed

Sponsorer og samarbeidspartnere

Medisinsk tilstand

Legemiddelintervensjoner

3
Abonnere