[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127510-en":3,"doc-seo-127510-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},127510,13056712833777,"Logic","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Using unsupervised machine learning to quantify physical activity from accelerometry in a diverse and rapidly changing population","Accelerometers widely quantify physical activity, but conventional cut-point processing depends on calibration studies that link acceleration magnitude to energy expenditure. Those mappings often fail to generalize across diverse populations, forcing costly re-parameterisation by subgroup and limiting longitudinal comparisons. An unsupervised alternative can let intensity states emerge from the data without external parameters. A hidden semi-Markov model was applied to waist-worn ActiGraph GT3X+ data from 279 children, and its activity time estimates were benchmarked against literature cut points. The unsupervised estimates showed stronger correlations with multiple PEDI-CAT mobility and daily functioning domains, supporting a more sensitive, appropriate, and cost-effective approach for inclusive research.","Edinburgh Research Explorer  \nUsing unsupervised machine learning to quantify physical activity from accelerometry in a diverse and rapidly changing population  \nCitation for published version:  \nThornton, C, Kolehmainen, N & Nazarpour, K 2023, 'Using unsupervised machine learning to quantify physical activity from accelerometry in a diverse and rapidly changing population', PLOS Digital Health, vol.  \n2, no. 4, e0000220, pp. 1-13. [https://doi.org/10.1371/journal.pdig.0000220](https://doi.org/10.1371/journal.pdig.0000220)  \nDigital Object Identifier (DOI):  \n10.1371/journal.pdig.0000220  \nLink:  \nLink to publication record in Edinburgh Research Explorer  \nDocument Version:  \nPublisher's PDF, also known as Version of record  \nPublished In:  \nPLOS Digital Health  \nGeneral rights  \nCopyright for the publications made accessible via the Edinburgh Research Explorer is retained by the author(s) and / or other copyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights.  \nTake down policy  \nThe University of Edinburgh has made every reasonable effort to ensure that Edinburgh Research Explorer content complies with UK legislation. If you believe that the public display of this file breaches copyright please [contact openaccess@ed.ac.uk](contact openaccess@ed.ac.uk) providing details, and we will remove access to the work immediately and investigate your claim.  \nDownload date: 08. Jan. 2026  \nPLOS DIGITAL HEALTH  \nOPEN ACCESS  \nCitation: Thornton CB, Kolehmainen N, Nazarpour K (2023) Using unsupervised machine learning to quantify physical activity from accelerometry in a diverse and rapidly changing population. PLOS Digit Health 2(4): e0000220 . [https://doi.org/](https://doi.org/)[ ](https://doi.org/)[10.1371/journal.pdig.0000220](10.1371/journal.pdig.0000220)  \nEditor: Ryan S. McGinnis, University of Vermont, UNITED STATES  \nReceived: October 18, 2022  \nAccepted: February 23, 2023  \nPublished: April 5, 2023  \nPeer Review History: PLOS recognizes the benefits of transparency in the peer review process; therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. The editorial history of this article is available here:  \n[https://doi.org/10.1371/journal.pdig.0000220](https://doi.org/10.1371/journal.pdig.0000220)  \n[Copyright:](Copyright:) © [2023 Thornton](2023 Thornton) et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.  \nData Availability Statement: All data underlying the results presented in this paper is available on the data.ncl repository. Physical activity data and the fitted HSMM model [is available at](is available at doi.org/10)[ ](is available at doi.org/10)[doi.org/10](is available at doi.org/10) .  \nRESEARCH ARTICLE  \nUsing unsupervised machine learning to quantify physical activity from accelerometry in a diverse and rapidly changing population  \nChristopher B. Thornton1 *, Niina Kolehmainen1,2, Kianoush Nazarpour3  \n1 Population Health Sciences Institute, Faculty of Medical Sciences, Newcastle University, United Kingdom, 2 Great North Children’s Hospital, Newcastle upon Tyne NHS Hospitals Trust, Unite Kingdom, 3 Institute for Adaptive and Neural Computation, School of Informatics, The University of Edinburgh, United Kingdom  \n* [chris.thornton@newcastle.ac.uk](chris.thornton@newcastle.ac.uk)  \nAbstract  \nAccelerometers are widely used to measure physical activity behaviour, including in children. The traditional method for processing acceleration data uses cut points to define physical activity intensity, relying on calibration studies that relate the magnitude of acceleration to energy expenditure. However, these relationships do not generalise across diverse pop","cbCaifKFCotgeami","https://ap.wps.com/l/cbCaifKFCotgeami","pdf",1575995,3,1,14,"English","en",105,"# Abstract\n## Problem and motivation\n## Method and data\n## Benchmarking and results\n## Implications","[{\"question\":\"Why do traditional cut points for accelerometry struggle in diverse populations?\",\"answer\":\"They rely on calibration relationships between acceleration magnitude and energy expenditure that may not generalize across different groups. This often requires subgroup-specific re-parameterisation, which is costly and complicates longitudinal or multi-population studies.\"},{\"question\":\"What unsupervised model was used to process the accelerometer data?\",\"answer\":\"The study used a hidden semi-Markov model to segment and cluster raw accelerometry data and derive physical activity intensity states directly from the signal.\"},{\"question\":\"How did the unsupervised approach perform versus the cut-point method?\",\"answer\":\"Time spent active from the unsupervised approach correlated more strongly with several PEDI-CAT domains, including mobility, social-cognitive capacity, responsibility, daily activity, and age, compared with the cut-point approach.\"}]","Using unsupervised machine learning to quantify physical activity from accelerometry in a diverse and rapidly changing population | PDF",1785939573,35,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"using-unsupervised-machine-learning-to-quantify-physical-activity-from-accelerometry-in-a-diverse-and-rapidly-changing-population","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":20},"https://docshare.wps.com/document/research-report/",{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/using-unsupervised-machine-learning-to-quantify-physical-activity-from-accelerometry-in-a-diverse-and-rapidly-changing-population/127510/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why do traditional cut points for accelerometry struggle in diverse populations?","Question",{"text":76,"@type":77},"They rely on calibration relationships between acceleration magnitude and energy expenditure that may not generalize across different groups. This often requires subgroup-specific re-parameterisation, which is costly and complicates longitudinal or multi-population studies.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What unsupervised model was used to process the accelerometer data?",{"text":81,"@type":77},"The study used a hidden semi-Markov model to segment and cluster raw accelerometry data and derive physical activity intensity states directly from the signal.",{"name":83,"@type":74,"acceptedAnswer":84},"How did the unsupervised approach perform versus the cut-point method?",{"text":85,"@type":77},"Time spent active from the unsupervised approach correlated more strongly with several PEDI-CAT domains, including mobility, social-cognitive capacity, responsibility, daily activity, and age, compared with the cut-point approach.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]