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. 1. College of Information Sciences and Technology, The Pennsylvania State University, University Park, PA, USA. 2. Artificial Intelligence Research Laboratory, The Pennsylvania State University, University Park, PA, USA. 3. Center for Big Data Analytics and Discovery Informatics, The Pennsylvania State University, University Park, PA, USA. 4. Department of Imaging Science and Innovation, Geisinger Health System, Danville, PA, 17822, USA. 5. Department of Biobehavioral Health, The Pennsylvania State University, University Park, PA, USA. 6. Clinical and Translational Sciences Institute, The Pennsylvania State University, University Park, PA, USA. 7. Division of Sleep Medicine, Harvard University, Boston, MA, USA. 8. Department of Social and Behavioral Sciences, Harvard Chan School of Public Health, Boston, MA, USA. 9. Division of Sleep and Circadian Disorders, Departments of Medicine and Neurology, Brigham and Women's Hospital, Boston, MA, USA. 10. Institute for Computational and Data Sciences, The Pennsylvania State University, University Park, PA, USA. 11. Huck Institutes of the Life Sciences, The Pennsylvania State University, University Park, PA, USA.
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.
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.
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
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
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
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
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