Abstract

Actigraphy offers a low-cost alternative to conventional polysomnography (PSG) for screening of sleep-wake patterns. Effective use of actigraphy signals requires reliable methods for detecting sleep-wake states from actigraphy measurements. Hence, there is a growing interest in machine learning methods for training predictive models of sleep-wake states from actigraphy data. Existing work has focused on training a single predictive model for the entire population. However, accounting for individual differences, such as age, biological factors, or lifestyle-related variations, calls for personalized models for reliable identification of sleep-wake states from actigraphy data. This study investigates whether personalized models, trained on individual data, can match the performance of generalized models trained on population data. Using a dataset of 54 individuals, we systematically trained and tested personalized and generalized sleep-wake detectors developed using five commonly used machine learning algorithms. Results of our experiments show that personalized sleep-wake predictors are competitive, in terms of their predictive performance, with their generalized counterparts. Our work demonstrates the feasibility of developing reliable personalized sleep-wake states predictors from actigraphy data. This study lays the groundwork for developing personalized models for sleep-wake states detection that are better equipped to handle individual differences.

Original languageEnglish (US)
Title of host publication2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages414-417
Number of pages4
Volume2018-January
ISBN (Electronic)9781538624050
DOIs
StatePublished - Apr 6 2018
Event2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018 - Las Vegas, United States
Duration: Mar 4 2018Mar 7 2018

Other

Other2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018
CountryUnited States
CityLas Vegas
Period3/4/183/7/18

Fingerprint

Actigraphy
Sleep
Individuality
Learning systems
Polysomnography
Age Factors
Biological Factors
Learning algorithms
Population
Life Style
Identification (control systems)
Screening
Detectors
Costs and Cost Analysis

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Biomedical Engineering
  • Health Informatics

Cite this

Khademi, A., Elmanzalawi, Y., Buxton, O. M., & Honavar, V. G. (2018). Toward personalized sleep-wake prediction from actigraphy. In 2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018 (Vol. 2018-January, pp. 414-417). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BHI.2018.8333456
Khademi, Aria ; Elmanzalawi, Yasser ; Buxton, Orfeu M. ; Honavar, Vasant Gajanan. / Toward personalized sleep-wake prediction from actigraphy. 2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 414-417
@inproceedings{7204b897149b4a089a033e5cda6328ee,
title = "Toward personalized sleep-wake prediction from actigraphy",
abstract = "Actigraphy offers a low-cost alternative to conventional polysomnography (PSG) for screening of sleep-wake patterns. Effective use of actigraphy signals requires reliable methods for detecting sleep-wake states from actigraphy measurements. Hence, there is a growing interest in machine learning methods for training predictive models of sleep-wake states from actigraphy data. Existing work has focused on training a single predictive model for the entire population. However, accounting for individual differences, such as age, biological factors, or lifestyle-related variations, calls for personalized models for reliable identification of sleep-wake states from actigraphy data. This study investigates whether personalized models, trained on individual data, can match the performance of generalized models trained on population data. Using a dataset of 54 individuals, we systematically trained and tested personalized and generalized sleep-wake detectors developed using five commonly used machine learning algorithms. Results of our experiments show that personalized sleep-wake predictors are competitive, in terms of their predictive performance, with their generalized counterparts. Our work demonstrates the feasibility of developing reliable personalized sleep-wake states predictors from actigraphy data. This study lays the groundwork for developing personalized models for sleep-wake states detection that are better equipped to handle individual differences.",
author = "Aria Khademi and Yasser Elmanzalawi and Buxton, {Orfeu M.} and Honavar, {Vasant Gajanan}",
year = "2018",
month = "4",
day = "6",
doi = "10.1109/BHI.2018.8333456",
language = "English (US)",
volume = "2018-January",
pages = "414--417",
booktitle = "2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Khademi, A, Elmanzalawi, Y, Buxton, OM & Honavar, VG 2018, Toward personalized sleep-wake prediction from actigraphy. in 2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 414-417, 2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018, Las Vegas, United States, 3/4/18. https://doi.org/10.1109/BHI.2018.8333456

Toward personalized sleep-wake prediction from actigraphy. / Khademi, Aria; Elmanzalawi, Yasser; Buxton, Orfeu M.; Honavar, Vasant Gajanan.

2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 414-417.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Toward personalized sleep-wake prediction from actigraphy

AU - Khademi, Aria

AU - Elmanzalawi, Yasser

AU - Buxton, Orfeu M.

AU - Honavar, Vasant Gajanan

PY - 2018/4/6

Y1 - 2018/4/6

N2 - Actigraphy offers a low-cost alternative to conventional polysomnography (PSG) for screening of sleep-wake patterns. Effective use of actigraphy signals requires reliable methods for detecting sleep-wake states from actigraphy measurements. Hence, there is a growing interest in machine learning methods for training predictive models of sleep-wake states from actigraphy data. Existing work has focused on training a single predictive model for the entire population. However, accounting for individual differences, such as age, biological factors, or lifestyle-related variations, calls for personalized models for reliable identification of sleep-wake states from actigraphy data. This study investigates whether personalized models, trained on individual data, can match the performance of generalized models trained on population data. Using a dataset of 54 individuals, we systematically trained and tested personalized and generalized sleep-wake detectors developed using five commonly used machine learning algorithms. Results of our experiments show that personalized sleep-wake predictors are competitive, in terms of their predictive performance, with their generalized counterparts. Our work demonstrates the feasibility of developing reliable personalized sleep-wake states predictors from actigraphy data. This study lays the groundwork for developing personalized models for sleep-wake states detection that are better equipped to handle individual differences.

AB - Actigraphy offers a low-cost alternative to conventional polysomnography (PSG) for screening of sleep-wake patterns. Effective use of actigraphy signals requires reliable methods for detecting sleep-wake states from actigraphy measurements. Hence, there is a growing interest in machine learning methods for training predictive models of sleep-wake states from actigraphy data. Existing work has focused on training a single predictive model for the entire population. However, accounting for individual differences, such as age, biological factors, or lifestyle-related variations, calls for personalized models for reliable identification of sleep-wake states from actigraphy data. This study investigates whether personalized models, trained on individual data, can match the performance of generalized models trained on population data. Using a dataset of 54 individuals, we systematically trained and tested personalized and generalized sleep-wake detectors developed using five commonly used machine learning algorithms. Results of our experiments show that personalized sleep-wake predictors are competitive, in terms of their predictive performance, with their generalized counterparts. Our work demonstrates the feasibility of developing reliable personalized sleep-wake states predictors from actigraphy data. This study lays the groundwork for developing personalized models for sleep-wake states detection that are better equipped to handle individual differences.

UR - http://www.scopus.com/inward/record.url?scp=85050849838&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050849838&partnerID=8YFLogxK

U2 - 10.1109/BHI.2018.8333456

DO - 10.1109/BHI.2018.8333456

M3 - Conference contribution

AN - SCOPUS:85050849838

VL - 2018-January

SP - 414

EP - 417

BT - 2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Khademi A, Elmanzalawi Y, Buxton OM, Honavar VG. Toward personalized sleep-wake prediction from actigraphy. In 2018 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 414-417 https://doi.org/10.1109/BHI.2018.8333456