Literature DB >> 31849551

Personalized Sleep Parameters Estimation from Actigraphy: A Machine Learning Approach.

Aria Khademi1,2,3, Yasser El-Manzalawy1,4, Lindsay Master5, Orfeu M Buxton5,6,7,8,9, Vasant G Honavar1,2,3,6,10,11.   

Abstract

BACKGROUND: The current gold standard for measuring sleep is polysomnography (PSG), but it can be obtrusive and costly. Actigraphy is a relatively low-cost and unobtrusive alternative to PSG. Of particular interest in measuring sleep from actigraphy is prediction of sleep-wake states. Current literature on prediction of sleep-wake states from actigraphy consists of methods that use population data, which we call generalized models. However, accounting for variability of sleep patterns across individuals calls for personalized models of sleep-wake states prediction that could be potentially better suited to individual-level data and yield more accurate estimation of sleep.
PURPOSE: To investigate the validity of developing personalized machine learning models, trained and tested on individual-level actigraphy data, for improved prediction of sleep-wake states and reliable estimation of nightly sleep parameters. PARTICIPANTS AND METHODS: We used a dataset including 54 participants and systematically trained and tested 5 different personalized machine learning models as well as their generalized counterparts. We evaluated model performance compared to concurrent PSG through extensive machine learning experiments and statistical analyses.
RESULTS: Our experiments show the superiority of personalized models over their generalized counterparts in estimating PSG-derived sleep parameters. Personalized models of regularized logistic regression, random forest, adaptive boosting, and extreme gradient boosting achieve estimates of total sleep time, wake after sleep onset, sleep efficiency, and number of awakenings that are closer to those obtained by PSG, in absolute difference, than the same estimates from their generalized counterparts. We further show that the difference between estimates of sleep parameters obtained by personalized models and those of PSG is statistically non-significant.
CONCLUSION: Personalized machine learning models of sleep-wake states outperform their generalized counterparts in terms of estimating sleep parameters and are indistinguishable from PSG labeled sleep-wake states. Personalized machine learning models can be used in actigraphy studies of sleep health and potentially screening for some sleep disorders.
© 2019 Khademi et al.

Entities:  

Keywords:  actigraphy; machine learning; personalized; polysomnography; sleep parameters

Year:  2019        PMID: 31849551      PMCID: PMC6912004          DOI: 10.2147/NSS.S220716

Source DB:  PubMed          Journal:  Nat Sci Sleep        ISSN: 1179-1608


  47 in total

1.  An evaluation of cardiorespiratory and movement features with respect to sleep-stage classification.

Authors:  T Willemen; D Van Deun; V Verhaert; M Vandekerckhove; V Exadaktylos; J Verbraecken; S Van Huffel; B Haex; J Vander Sloten
Journal:  IEEE J Biomed Health Inform       Date:  2014-03       Impact factor: 5.772

2.  Measuring sleep: accuracy, sensitivity, and specificity of wrist actigraphy compared to polysomnography.

Authors:  Miguel Marino; Yi Li; Michael N Rueschman; J W Winkelman; J M Ellenbogen; J M Solet; Hilary Dulin; Lisa F Berkman; Orfeu M Buxton
Journal:  Sleep       Date:  2013-11-01       Impact factor: 5.849

3.  Circadian misalignment increases cardiovascular disease risk factors in humans.

Authors:  Christopher J Morris; Taylor E Purvis; Kun Hu; Frank A J L Scheer
Journal:  Proc Natl Acad Sci U S A       Date:  2016-02-08       Impact factor: 11.205

4.  A novel adaptive wrist actigraphy algorithm for sleep-wake assessment in sleep apnea patients.

Authors:  Jan Hedner; Giora Pillar; Stephen D Pittman; Ding Zou; Ludger Grote; David P White
Journal:  Sleep       Date:  2004-12-15       Impact factor: 5.849

5.  Actigraph placement and sleep estimation in children.

Authors:  E Juulia Paavonen; Mika Fjällberg; Maija-Riikka Steenari; Eeva T Aronen
Journal:  Sleep       Date:  2002-03-15       Impact factor: 5.849

6.  Covert waking brain activity reveals instantaneous sleep depth.

Authors:  Scott M McKinney; Thien Thanh Dang-Vu; Orfeu M Buxton; Jo M Solet; Jeffrey M Ellenbogen
Journal:  PLoS One       Date:  2011-03-03       Impact factor: 3.240

Review 7.  Short- and long-term health consequences of sleep disruption.

Authors:  Goran Medic; Micheline Wille; Michiel Eh Hemels
Journal:  Nat Sci Sleep       Date:  2017-05-19

8.  Sleep estimates in children: parental versus actigraphic assessments.

Authors:  Ehab A Dayyat; Karen Spruyt; Dennis L Molfese; David Gozal
Journal:  Nat Sci Sleep       Date:  2011-10-28

9.  Sleep disturbance in mental health problems and neurodegenerative disease.

Authors:  Kirstie N Anderson; Andrew J Bradley
Journal:  Nat Sci Sleep       Date:  2013-05-31

10.  Sex-specific sleep patterns among university students in Lebanon: impact on depression and academic performance.

Authors:  Colette S Kabrita; Theresa A Hajjar-Muça
Journal:  Nat Sci Sleep       Date:  2016-06-17
View more
  6 in total

1.  Deep learning applied to polysomnography to predict blood pressure in obstructive sleep apnea and obesity hypoventilation: a proof-of-concept study.

Authors:  Bharati Prasad; Chirag Agarwal; Elan Schonfeld; Dan Schonfeld; Babak Mokhlesi
Journal:  J Clin Sleep Med       Date:  2020-10-15       Impact factor: 4.062

Review 2.  Data-Driven Modeling of Pregnancy-Related Complications.

Authors:  Camilo Espinosa; Martin Becker; Ivana Marić; Ronald J Wong; Gary M Shaw; Brice Gaudilliere; Nima Aghaeepour; David K Stevenson
Journal:  Trends Mol Med       Date:  2021-02-08       Impact factor: 15.272

3.  Efficient embedded sleep wake classification for open-source actigraphy.

Authors:  Tommaso Banfi; Nicolò Valigi; Marco di Galante; Paola d'Ascanio; Gastone Ciuti; Ugo Faraguna
Journal:  Sci Rep       Date:  2021-01-11       Impact factor: 4.379

4.  Rigorous performance evaluation (previously, "validation") for informed use of new technologies for sleep health measurement.

Authors:  Massimiliano de Zambotti; Luca Menghini; Michael A Grandner; Susan Redline; Ying Zhang; Meredith L Wallace; Orfeu M Buxton
Journal:  Sleep Health       Date:  2022-05-03

5.  Modeling Sleep Quality Depending on Objective Actigraphic Indicators Based on Machine Learning Methods.

Authors:  Olga Vl Bitkina; Jaehyun Park; Jungyoon Kim
Journal:  Int J Environ Res Public Health       Date:  2022-08-11       Impact factor: 4.614

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

Authors:  Jiaxing Liu; Yang Zhao; Boya Lai; Hailiang Wang; Kwok Leung Tsui
Journal:  JMIR Mhealth Uhealth       Date:  2020-08-05       Impact factor: 4.773

  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.