ChatPPG.
Paper

Statistical machine learning of sleep and physical activity phenotypes from sensor data in 96,220 UK Biobank participants

Matthew Willetts, Sven Hollowell, Louis Aslett, Chris Holmes, Aiden Doherty
Scientific Reports2018CC BY 4.0
Read paper Cite
Published articlePublication date: May 21, 2018Added to atlas: Oct 15, 2026Source
Citations241Crossref referencesChecked Oct 16, 2026
GitHub stars—Not available
HF downloads—Not available

Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.

Willetts and colleagues developed a machine-learning model combining balanced random forests with hidden Markov models to detect activity and sleep modes from simple wrist-worn activity monitors. The model classified free-living behaviours with 87% accuracy across 159,504 recorded minutes from 132 adults. Applied to 96,220 UK Biobank participants, it showed, for example, that men spend more time in low- and high-intensity behaviours while women spend more time in mixed behaviours.

  • Result: The authors show that physical activity and sleep behaviours can be classified with 87% accuracy in 159,504 minutes of recorded free-living behaviours from 132 adults.
At a glance
Venue
Scientific Reports
Published
2018
DOI
10.1038/s41598-018-26174-1 (opens in a new tab)
arXiv
Not reported
PMID
Not reported
Licence
CC BY 4.0 (opens in a new tab)
Signals
Not reported
Form factor
Not reported
Devices
Datasets
Subjects
132 adults
Code
Not reported
Added
Oct 15, 2026

Abstract

Current public health guidelines on physical activity and sleep duration are limited by a reliance on subjective self-reported evidence. Using data from simple wrist-worn activity monitors, we developed a tailored machine learning model, using balanced random forests with Hidden Markov Models, to reliably detect a number of activity modes. We show that physical activity and sleep behaviours can be classified with 87% accuracy in 159,504 minutes of recorded free-living behaviours from 132 adults. These trained models can be used to infer fine resolution activity patterns at the population scale in 96,220 participants. For example, we find that men spend more time in both low- and high- intensity behaviours, while women spend more time in mixed behaviours. Walking time is highest in spring and sleep time lowest during the summer. This work opens the possibility of future public health guidelines informed by the health consequences associated with specific, objectively measured, physical activity and sleep behaviours.

Verbatim fromthe publisher's DOI record· Publisher licence: https://creativecommons.org/licenses/by/4.0

Statistical machine learning of sleep and physical activity phenotypes from sensor data in 96,220 UK Biobank participants: ChatPPG research summary card

Key results

159
accuracy
The model classified free-living behaviours with 87% accuracy across 159,504 recorded minutes from 132 adults

How it works

How Method works: Setup → Method → ResultSetup: Cohort (132 adults). Method: Method. Result: Result (The authors show that physical activity and sleep behaviours can be classified with 87% accuracy in 159,504 minutes of recorded free-living behaviours from 132 adults.).SetupCohort: 132 adultsCohort132 adultsMethodMethodResultResult: The authors show that physical activity and sleep behaviours can be classified with 87% accuracy in 159,504 minutes of recorded free-living behaviours from 132 adults.ResultThe authors show that physical activity…
Cohort
132 adults

Devices· 1

Axivity AX3
Axivity · Wrist
IMU

Illustrations by form factor; product photos are added as licences clear.

Datasets used· 1

Dataset
UK Biobank wrist accelerometer (Axivity AX3 / field 90001)
103,568 subjects · uk-biobank
IMU

Cite

@article{willettsukbsleepactivity2018,
  title = {{Statistical machine learning of sleep and physical activity phenotypes from sensor data in 96,220 UK Biobank participants}},
  author = {Matthew Willetts and Sven Hollowell and Louis Aslett and Chris Holmes and Aiden Doherty},
  year = {2018},
  journal = {Scientific Reports},
  doi = {10.1038/s41598-018-26174-1}
}

History

  1. Added to the ChatPPG research hub

More on ChatPPG