Wearable Device Heart Rate and Activity Data in an Unsupervised Approach to Personalized Sleep Monitoring: Algorithm Validation

Background The proliferation of wearable devices that collect activity and heart rate data has facilitated new ways to measure sleeping and waking durations unobtrusively and longitudinally. Most existing sleep/wake identification algorithms are based on activity only and are trained on expensive and laboriously annotated polysomnography (PSG). Heart rate can also be reflective of sleep/wake transitions, which has motivated its investigation herein in an unsupervised algorithm. Moreover, it is necessary to develop a personalized approach to deal with interindividual variance in sleep/wake patterns. Objective We aimed to develop an unsupervised personalized sleep/wake identification algorithm using multifaceted data to explore the benefits of incorporating both heart rate and activity level in these types of algorithms and to compare this approach’s output with that of an existing commercial wearable device’s algorithms. Methods In this study, a total of 14 community-dwelling older adults wore wearable devices (Fitbit Alta; Fitbit Inc) 24 hours a day and 7 days a week over period of 3 months during which their heart rate and activity data were collected. After preprocessing the data, a model was developed to distinguish sleep/wake states based on each individual’s data. We proposed the use of hidden Markov models and compared different modeling schemes. With the best model selected, sleep/wake patterns were characterized by estimated parameters in hidden Markov models, and sleep/wake states were identified. Results When applying our proposed algorithm on a daily basis, we found there were significant differences in estimated parameters between weekday models and weekend models for some participants. Conclusions Our unsupervised approach can be effectively implemented based on an individual’s multifaceted sleep-related data from a commercial wearable device. A personalized model is shown to be necessary given the interindividual variability in estimated parameters.

[1]  James F. Jones,et al.  Higher heart rate and reduced heart rate variability persist during sleep in chronic fatigue syndrome: A population-based study , 2007, Autonomic Neuroscience.

[2]  Mark G. Davis,et al.  Associations between multiple indicators of objectively-measured and self-reported sedentary behaviour and cardiometabolic risk in older adults. , 2012, Preventive medicine.

[3]  Daniel J Buysse,et al.  Joint Consensus Statement of the American Academy of Sleep Medicine and Sleep Research Society on the Recommended Amount of Sleep for a Healthy Adult: Methodology and Discussion. , 2015, Sleep.

[4]  Iain L. MacDonald,et al.  Hidden Markov Models for Time Series: An Introduction Using R, Second Edition , 2016 .

[5]  Dario Floreano,et al.  Adaptive Sleep–Wake Discrimination for Wearable Devices , 2011, IEEE Transactions on Biomedical Engineering.

[6]  Luis Fernandez-Luque,et al.  Benchmark on a large cohort for sleep-wake classification with machine learning techniques , 2019, npj Digital Medicine.

[7]  H. Montgomery-Downs,et al.  Movement toward a novel activity monitoring device , 2012, Sleep and Breathing.

[8]  Martin J Shipley,et al.  Change in sleep duration and cognitive function: findings from the Whitehall II Study. , 2011, Sleep.

[9]  M. Speekenbrink,et al.  depmixS4: An R Package for Hidden Markov Models , 2010 .

[10]  Sonia Ancoli-Israel,et al.  Comparison of sleep parameters from actigraphy and polysomnography in older women: the SOF study. , 2008, Sleep.

[11]  M. Irwin,et al.  Why sleep is important for health: a psychoneuroimmunology perspective. , 2015, Annual review of psychology.

[12]  Claude Bouchard,et al.  Short Sleep Duration is Associated with Reduced Leptin Levels and Increased Adiposity: Results from the Québec Family Study , 2007, Obesity.

[13]  M. Kothare,et al.  Algorithms for sleep–wake identification using actigraphy: a comparative study and new results , 2009, Journal of sleep research.

[14]  M. Marmot,et al.  A prospective study of change in sleep duration: associations with mortality in the Whitehall II cohort. , 2007, Sleep.

[15]  Vasant Honavar,et al.  Sleep/wake state prediction and sleep parameter estimation using unsupervised classification via clustering , 2017, 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[16]  A. Sadeh,et al.  Activity-based sleep-wake identification: an empirical test of methodological issues. , 1994, Sleep.

[17]  Daniel J Buysse,et al.  The Pittsburgh sleep quality index: A new instrument for psychiatric practice and research , 1989, Psychiatry Research.

[18]  Matt T Bianchi,et al.  Sleep devices: wearables and nearables, informational and interventional, consumer and clinical. , 2017, Metabolism: clinical and experimental.

[19]  Dario Floreano,et al.  Improving actigraph sleep/wake classification with cardio-respiratory signals , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[20]  Bingfeng Ge,et al.  Automatic sleep and wake classifier with heart rate and pulse oximetry: Derived dynamic time warping features and logistic model , 2016, 2016 Annual IEEE Systems Conference (SysCon).

[21]  Qi Huang,et al.  Hidden Markov models for monitoring circadian rhythmicity in telemetric activity data , 2018, Journal of The Royal Society Interface.

[22]  Shing-Tai Pan,et al.  A transition-constrained discrete hidden Markov model for automatic sleep staging , 2012, Biomedical engineering online.

[23]  Xi Long,et al.  Effects of Between- and Within-Subject Variability on Autonomic Cardiorespiratory Activity during Sleep and Their Limitations on Sleep Staging: A Multilevel Analysis , 2015, Comput. Intell. Neurosci..

[24]  D. J. Mullaney,et al.  An activity-based sleep monitor system for ambulatory use. , 1982, Sleep.

[25]  N. Watanabe,et al.  Short sleep duration and health outcomes: a systematic review, meta-analysis, and meta-regression. , 2017, Sleep medicine.

[26]  D. J. Mullaney,et al.  Automatic sleep/wake identification from wrist activity. , 1992, Sleep.

[27]  A. Malliani,et al.  Continuous 24-hour assessment of the neural regulation of systemic arterial pressure and RR variabilities in ambulant subjects. , 1990, Circulation.

[28]  Roland Langrock,et al.  Combining hidden Markov models for comparing the dynamics of multiple sleep electroencephalograms , 2013, Statistics in medicine.

[29]  Peter Achermann,et al.  Interindividual differences in the dynamics of the homeostatic process are trait‐like and distinct for sleep versus wakefulness , 2017, Journal of sleep research.

[30]  A. Chesson,et al.  The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology, and Techinical Specifications , 2007 .

[31]  Vasant G Honavar,et al.  Personalized Sleep Parameters Estimation from Actigraphy: A Machine Learning Approach , 2019, Nature and science of sleep.

[32]  Raquel Faubel,et al.  Sleep duration and health-related quality of life among older adults: a population-based cohort in Spain. , 2009, Sleep.

[33]  Hongyu Zhao,et al.  A novel machine learning unsupervised algorithm for sleep/wake identification using actigraphy , 2020, Chronobiology international.

[34]  Sabine Van Huffel,et al.  An Evaluation of Cardiorespiratory and Movement Features With Respect to Sleep-Stage Classification , 2014, IEEE Journal of Biomedical and Health Informatics.

[35]  Deepak Shrivastava,et al.  How to interpret the results of a sleep study , 2014, Journal of community hospital internal medicine perspectives.

[36]  A. Goldstone,et al.  A validation study of Fitbit Charge 2™ compared with polysomnography in adults , 2018, Chronobiology international.

[37]  C. Bouchard,et al.  Short sleep duration as a risk factor for the development of the metabolic syndrome in adults. , 2013, Preventive medicine.

[38]  W. J. Hadden,et al.  A Comparison of , 1971 .

[39]  D. Kripke,et al.  The role of actigraphy in the evaluation of sleep disorders. , 1995, Sleep.

[40]  Deepak L. Bhatt,et al.  Sleep Duration and Quality: Impact on Lifestyle Behaviors and Cardiometabolic Health: A Scientific Statement From the American Heart Association. , 2016, Circulation.

[41]  Nicholas B Allen,et al.  Accuracy of Consumer Wearable Heart Rate Measurement During an Ecologically Valid 24-Hour Period: Intraindividual Validation Study , 2019, JMIR mHealth and uHealth.

[42]  Stephen W. Wilson,et al.  Early Stages of Zebrafish Eye Formation Require the Coordinated Activity of Wnt11, Fz5, and the Wnt/β-Catenin Pathway , 2005, Neuron.

[43]  Deliang L. Chen,et al.  Empirical-Statistical Downscaling , 2008 .

[44]  Pasquale Strazzullo,et al.  Sleep duration predicts cardiovascular outcomes: a systematic review and meta-analysis of prospective studies. , 2011, European heart journal.