{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T13:29:54Z","timestamp":1790688594804,"version":"4.1.0"},"reference-count":41,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T00:00:00Z","timestamp":1746489600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Accelerometers are frequently used to assess physical activity in large epidemiological studies. They can monitor movement patterns and cycles over several days under free-living conditions and are usually either worn on the wrist or the hip. While wrist-worn accelerometers have been frequently used to additionally assess sleep and time in bed behavior, hip-worn accelerometers have been widely neglected for this task due to their primary focus on physical activity. Here, we present a new method with the objective to identify the time in bed to enable further analysis options for large-scale studies using hip-placement like time in bed or sedentary time analyses. We introduced new and accelerometer-specific data augmentation methods, such as mimicking a wrongly worn accelerometer, additional noise, and random croping, to improve training and generalization performance. Subsequently, we trained a neural network model on a sample from the population-based Troms\u00f8 Study and evaluated it on two additional datasets. Our algorithm achieved an accuracy of 94% on the training data, 92% on unseen data from the same population and comparable results to consumer-wearable data obtained from a demographically different population. Generalization performance was overall good, however, we found that on a few particular days or participants, the trained model fundamentally over- or underestimated time in bed (e.g., predicted all or nothing as time in bed). Despite these limitations, we anticipate our approach to be a starting point for more sophisticated methods to identify time in bed or at some point even sleep from hip-worn acceleration signals. This can enable the re-use of already collected data, for example, for longitudinal analyses where sleep-related research questions only recently got into focus or sedentary time needs to be estimated in 24\u2009h wear protocols.<\/jats:p>","DOI":"10.1371\/journal.pone.0321558","type":"journal-article","created":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T13:58:24Z","timestamp":1746539904000},"page":"e0321558","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":4,"title":["Automatic time in bed detection from hip-worn accelerometers for large epidemiological studies: The Troms\u00f8 Study"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8225-833X","authenticated-orcid":true,"given":"Marc","family":"Weitz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaheen","family":"Syed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0072-7421","authenticated-orcid":true,"given":"Laila A.","family":"Hopstock","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bente","family":"Morseth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0918-7444","authenticated-orcid":true,"given":"Andr\u00e9","family":"Henriksen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Horsch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,5,6]]},"reference":[{"issue":"2","key":"pone.0321558.ref001","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0169649","article-title":"Large Scale Population Assessment of Physical Activity Using Wrist Worn Accelerometers: The UK Biobank Study","volume":"12","author":"A Doherty","year":"2017","journal-title":"PLoS One"},{"issue":"1","key":"pone.0321558.ref002","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1249\/mss.0b013e31815a51b3","article-title":"Physical activity in the United States measured by accelerometer","volume":"40","author":"RP Troiano","year":"2008","journal-title":"Med Sci Sports Exerc"},{"issue":"7","key":"pone.0321558.ref003","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1177\/14034948221092294","article-title":"The seventh survey of the Troms\u00f8 Study (Troms\u00f87) 2015-2016: study design, data collection, attendance, and prevalence of risk factors and disease in a multipurpose population-based health survey","volume":"50","author":"LA Hopstock","year":"2022","journal-title":"Scand J Public Health"},{"issue":"1","key":"pone.0321558.ref004","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1186\/s40814-021-00921-0","article-title":"Complex lifestyle intervention among inactive older adults with elevated cardiovascular disease risk and obesity: a mixed-method, single-arm feasibility study for RESTART-a randomized controlled trial","volume":"7","author":"TS Deraas","year":"2021","journal-title":"Pilot Feasibility Stud"},{"issue":"2","key":"pone.0321558.ref005","doi-asserted-by":"crossref","first-page":"39","DOI":"10.5195\/ijt.2016.6200","article-title":"Are Physical activity and Benefits Maintained After Long-Term Telerehabilitation in COPD?","volume":"8","author":"H Hoaas","year":"2016","journal-title":"Int J Telerehabil"},{"issue":"4","key":"pone.0321558.ref006","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.smrv.2010.10.001","article-title":"The role and validity of actigraphy in sleep medicine: an update","volume":"15","author":"A Sadeh","year":"2011","journal-title":"Sleep Med Rev"},{"issue":"7","key":"pone.0321558.ref007","doi-asserted-by":"crossref","first-page":"1209","DOI":"10.5664\/jcsm.7228","article-title":"Use of Actigraphy for the Evaluation of Sleep Disorders and Circadian Rhythm Sleep-Wake Disorders: An American Academy of Sleep Medicine Systematic Review, Meta-Analysis, and GRADE Assessment","volume":"14","author":"MT Smith","year":"2018","journal-title":"J Clin Sleep Med"},{"issue":"6","key":"pone.0321558.ref008","doi-asserted-by":"crossref","first-page":"1514","DOI":"10.1378\/chest.10-1872","article-title":"Wrist actigraphy","volume":"139","author":"JL Martin","year":"2011","journal-title":"Chest"},{"issue":"5","key":"pone.0321558.ref009","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1093\/sleep\/15.5.461","article-title":"Automatic sleep\/wake identification from wrist activity","volume":"15","author":"RJ Cole","year":"1992","journal-title":"Sleep"},{"issue":"3","key":"pone.0321558.ref010","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1093\/sleep\/17.3.201","article-title":"Activity-based sleep-wake identification: an empirical test of methodological issues","volume":"17","author":"A Sadeh","year":"1994","journal-title":"Sleep"},{"issue":"1","key":"pone.0321558.ref011","doi-asserted-by":"crossref","first-page":"11958","DOI":"10.1038\/s41598-022-16003-x","article-title":"Quantification of acceleration as activity counts in ActiGraph wearable","volume":"12","author":"A Neishabouri","year":"2022","journal-title":"Sci Rep"},{"key":"pone.0321558.ref012","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1038\/s41746-019-0126-9","article-title":"Benchmark on a large cohort for sleep-wake classification with machine learning techniques","volume":"2","author":"J Palotti","year":"2019","journal-title":"NPJ Digit Med"},{"issue":"6","key":"pone.0321558.ref013","first-page":"877","article-title":"Racial\/Ethnic Differences in Sleep Disturbances: The Multi-Ethnic Study of Atherosclerosis (MESA)","volume":"38","author":"X Chen","year":"2015","journal-title":"Sleep"},{"issue":"10","key":"pone.0321558.ref014","doi-asserted-by":"crossref","first-page":"1351","DOI":"10.1093\/jamia\/ocy064","article-title":"The National Sleep Research Resource: towards a sleep data commons","volume":"25","author":"G-Q Zhang","year":"2018","journal-title":"J Am Med Inform Assoc"},{"issue":"8","key":"pone.0321558.ref015","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"S Hochreiter","year":"1997","journal-title":"Neural Comput"},{"issue":"6","key":"pone.0321558.ref016","doi-asserted-by":"crossref","first-page":"525","DOI":"10.3414\/ME15-05-0013","article-title":"Challenges and opportunities for harmonizing research methodology: raw accelerometry","volume":"55","author":"VT Van Hees","year":"2016","journal-title":"Methods Inf Med"},{"issue":"11","key":"pone.0321558.ref017","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0142533","article-title":"A Novel, Open Access Method to Assess Sleep Duration Using a Wrist-Worn Accelerometer","volume":"10","author":"VT van Hees","year":"2015","journal-title":"PLoS One"},{"issue":"1","key":"pone.0321558.ref018","doi-asserted-by":"crossref","first-page":"12975","DOI":"10.1038\/s41598-018-31266-z","article-title":"Estimating sleep parameters using an accelerometer without sleep diary","volume":"8","author":"VT van Hees","year":"2018","journal-title":"Sci Rep"},{"key":"pone.0321558.ref019","article-title":"Newcastle polysomnography and accelerometer data;","author":"V van Hees","year":"2018","journal-title":"Available from"},{"issue":"1","key":"pone.0321558.ref020","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1038\/s41598-020-79217-x","article-title":"Sleep classification from wrist-worn accelerometer data using random forests","volume":"11","author":"K Sundararajan","year":"2021","journal-title":"Sci Rep"},{"issue":"9","key":"pone.0321558.ref021","doi-asserted-by":"crossref","first-page":"1821","DOI":"10.1007\/s40279-017-0716-0","article-title":"Accelerometer Data Collection and Processing Criteria to Assess Physical Activity and Other Outcomes: A Systematic Review and Practical Considerations","volume":"47","author":"JH Migueles","year":"2017","journal-title":"Sports Med"},{"issue":"4","key":"pone.0321558.ref022","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1111\/j.1479-8425.2012.00578.x","article-title":"Measure of sleep and physical activity by a single accelerometer: Can a waist-worn Actigraph adequately measure sleep in children?","volume":"10","author":"MF Hjorth","year":"2012","journal-title":"Sleep and Biological Rhythms"},{"issue":"12","key":"pone.0321558.ref023","doi-asserted-by":"crossref","first-page":"1101","DOI":"10.1016\/j.jsams.2017.04.017","article-title":"Comparability and feasibility of wrist- and hip-worn accelerometers in free-living adolescents","volume":"20","author":"JJ Scott","year":"2017","journal-title":"J Sci Med Sport"},{"key":"pone.0321558.ref024","doi-asserted-by":"crossref","DOI":"10.1249\/01.mss.0000185657.86065.98","article-title":"Conducting accelerometer-based activity assessments in field-based research","volume":"37","author":"SG Trost","year":"2005","journal-title":"Med Sci Sports Exerc"},{"key":"pone.0321558.ref025","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/s12966-015-0172-x","article-title":"Improving wear time compliance with a 24-hour waist-worn accelerometer protocol in the International Study of Childhood Obesity, Lifestyle and the Environment (ISCOLE)","volume":"12","author":"C Tudor-Locke","year":"2015","journal-title":"Int J Behav Nutr Phys Act"},{"issue":"5","key":"pone.0321558.ref026","doi-asserted-by":"crossref","DOI":"10.2196\/27248","article-title":"Polar Vantage and Oura Physical Activity and Sleep Trackers: Validation and Comparison Study","volume":"6","author":"A Henriksen","year":"2022","journal-title":"JMIR Form Res"},{"issue":"12","key":"pone.0321558.ref027","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0225670","article-title":"Physical activity levels in adults and elderly from triaxial and uniaxial accelerometry. The Troms\u00f8 Study","volume":"14","author":"EH Sagelv","year":"2019","journal-title":"PLoS One"},{"key":"pone.0321558.ref028","author":"A Henriksen","year":"2024"},{"key":"pone.0321558.ref029","volume-title":"Paat: physical activity analysis toolbox","author":"M Weitz","year":"2024"},{"issue":"3","key":"pone.0321558.ref030","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1123\/jmpb.2018-0063","article-title":"GGIR: A Research Community\u2013Driven Open Source R Package for Generating Physical Activity and Sleep Outcomes From Multi-Day Raw Accelerometer Data","volume":"2","author":"JH Migueles","year":"2019","journal-title":"Journal for the Measurement of Physical Behaviour"},{"issue":"7","key":"pone.0321558.ref031","doi-asserted-by":"crossref","first-page":"738","DOI":"10.1152\/japplphysiol.00421.2014","article-title":"Autocalibration of accelerometer data for free-living physical activity assessment using local gravity and temperature: an evaluation on four continents","volume":"117","author":"VT van Hees","year":"2014","journal-title":"J Appl Physiol (1985)"},{"issue":"1","key":"pone.0321558.ref032","doi-asserted-by":"crossref","DOI":"10.1123\/jmpb.2023-0019","article-title":"Influence of Accelerometer Calibration on the Estimation of Objectively Measured Physical Activity: The Troms\u00f8 Study","volume":"7","author":"M Weitz","year":"2024","journal-title":"Journal for the Measurement of Physical Behaviour"},{"issue":"7","key":"pone.0321558.ref033","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0022922","article-title":"Estimation of daily energy expenditure in pregnant and non-pregnant women using a wrist-worn tri-axial accelerometer","volume":"6","author":"VT van Hees","year":"2011","journal-title":"PLoS One"},{"issue":"4","key":"pone.0321558.ref034","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0061691","article-title":"Separating movement and gravity components in an acceleration signal and implications for the assessment of human daily physical activity","volume":"8","author":"VT van Hees","year":"2013","journal-title":"PLoS One"},{"issue":"4","key":"pone.0321558.ref035","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0231581","article-title":"Time trends in physical activity in the Troms\u00f8 study: An update","volume":"15","author":"B Morseth","year":"2020","journal-title":"PLoS One"},{"issue":"1","key":"pone.0321558.ref036","doi-asserted-by":"crossref","first-page":"7927","DOI":"10.1038\/s41598-024-58461-5","article-title":"Large-scale assessment of physical activity in a population using high-resolution hip-worn accelerometry: the German National Cohort (NAKO)","volume":"14","author":"A Weber","year":"2024","journal-title":"Sci Rep"},{"issue":"24","key":"pone.0321558.ref037","doi-asserted-by":"crossref","first-page":"8442","DOI":"10.3390\/s21248442","article-title":"Manual annotation of time in bed using free-living recordings of accelerometry data","volume":"21","author":"EL Skovgaard","year":"2021","journal-title":"Sensors (Basel)"},{"issue":"1","key":"pone.0321558.ref038","doi-asserted-by":"crossref","first-page":"2496","DOI":"10.1038\/s41598-023-29666-x","article-title":"Generalizability and performance of methods to detect non-wear with free-living accelerometer recordings","volume":"13","author":"EL Skovgaard","year":"2023","journal-title":"Sci Rep"},{"issue":"6","key":"pone.0321558.ref039","doi-asserted-by":"crossref","first-page":"68002","DOI":"10.1209\/0295-5075\/103\/68002","article-title":"Transitions in effective scaling behavior of accelerometric time series across sleep and wake","volume":"103","author":"P Wohlfahrt","year":"2013","journal-title":"EPL"},{"issue":"1","key":"pone.0321558.ref040","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1123\/jmpb.2021-0012","article-title":"Should We Use Activity Tracker Data From Smartphones and Wearables to Understand Population Physical Activity Patterns?","volume":"5","author":"JL Mair","year":"2022","journal-title":"Journal for the Measurement of Physical Behaviour"},{"issue":"4","key":"pone.0321558.ref041","doi-asserted-by":"crossref","DOI":"10.2196\/23806","article-title":"Consumer-Based Activity Trackers as a Tool for Physical Activity Monitoring in Epidemiological Studies During the COVID-19 Pandemic: Development and Usability Study","volume":"7","author":"A Henriksen","year":"2021","journal-title":"JMIR Public Health Surveill"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0321558","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T13:58:39Z","timestamp":1746539919000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0321558"}},"subtitle":[],"editor":[{"given":"Julio Alejandro Henriques Castro","family":"da Costa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,5,6]]},"references-count":41,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5,6]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0321558","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2022.03.07.22270992","asserted-by":"object"}]},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,6]]}}}