[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119404-en":3,"doc-seo-119404-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119404,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Machine Learning Applications for Physical Activity and Behaviour in Early Childhood - A Systematic Review","This systematic review evaluates how machine learning models analyze preschool physical activity and behaviour from accelerometer data. Using PRISMA-guided searches across PubMed, FECYT, and ProQuest Central, fourteen eligible studies were selected and appraised with the MINORS scale. Evidence clusters into physical activity analysis and sleep monitoring, with ActiGraph GT3X+ as the predominant device. Random Forest achieved the highest reported performance, while results varied by sampling frequency and epoch length. Small samples and inconsistent methods constrain generalizability, indicating a need for larger cohorts, sensor integration, and standardized protocols.","Systematic Review  \nMachine Learning Applications for Physical Activity and Behaviour in Early Childhood: A Systematic Review  \nMarkel Rico-González 1, * and Carlos D. Gómez-Carmona 2,3,4, *  \nAcademic Editors: Gaspar Rogério da Silva Chiappa, Alberto Souza Sá Filho and Rodrigo Lopes-Martins  \nReceived: 19 April 2025  \nRevised: 3 May 2025  \nAccepted: 8 May 2025  \nPublished: 3 June 2025  \nCitation: Rico-González, M.; Gómez-Carmona, C.D. Machine Learning Applications for Physical Activity and Behaviour in Early Childhood: A Systematic Review.  \nAppl. Sci. 2025, 15, 6296. [https://](https://)[ ](https://)[doi.org/10.3390/app15116296](doi.org/10.3390/app15116296)  \n[Copyright:](Copyright:) © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by/4.0/](licenses/by/4.0/)) .  \n1 Department of Didactics of Music, Plastic and Corporal Expression, University of Basque Country (UPV-EHU), 48940 Leioa, Spain  \n2 Research Group in Training, Physical Activity and Sports Performance (ENFYRED), Department of Music, Plastic and Body Expression, University of Zaragoza, 44003 Teruel, Spain  \n3 Research Group in Optimization of Training and Sports Performance (GOERD), University of Extremadura, 10071 Caceres, Spain  \n4 BioVetMed & SportSci Research Group, University of Murcia, 30001 Murcia, Spain  \n* [Correspondence: markel.rico@ehu.eus](Correspondence: markel.rico@ehu.eus) (M.R.-G.); [carlosdavid.gomez@unizar.es](carlosdavid.gomez@unizar.es) (C.D.G.-C.)  \nFeatured Application: Machine learning algorithms applied to accelerometer data can enhance physical activity and sleep pattern assessment in preschool children, enabling more accurate and automated monitoring for educational and health interventions.  \nAbstract: This systematic review evaluated machine learning applications for analysing physical activity and behaviour in preschool children using accelerometer data. Following the PRISMA guidelines, we systematically searched PubMed, FECYT, and ProQuest Central databases. Fourteen studies implementing machine learning approaches for preschool accelerometry data were identified and assessed using the MINORS scale. Studies focused on two primary domains: physical activity analysis (n = 10) and sleep monitoring (n = 4) . The ActiGraph GT3X+ was predominantly used, with placement varying between the hip and wrist. Random Forest algorithms proved most effective, achieving accuracy rates up to 86.4% in activity classification and 96.2% in sleep prediction. Sampling frequencies (0.25–100 Hz) and epoch lengths (1–60 s) varied considerably across studies. Machine learning applications show promising results for preschool physical activity assessment. However, small sample sizes and methodological inconsistencies limit generalizability. Future research should prioritise larger cohorts, explore multiple sensor integrations, and develop standardised protocols to enhance practical applications.  \nKeywords: technology; preschool; prediction; computer science; education  \n1. Introduction  \nThe early childhood years represent a critical period for establishing healthy physical activity patterns that can influence lifelong health outcomes. Physical activity is crucial forchildren’s health and development, affecting their physical growth, cognitive development, and social skills [1] . Furthermore, research has identified physical activity as a significant protective factor against mental health challenges, including depressive symptoms and suicidal behaviour in later developmental stages [2] . Understanding their activity level can provide valuable information for designing public health interventions, school physical activity programmes, and disease prevention strategies [3] . By improving the accuracy of these assessments, ","cbCairF2cdFMeevX","https://ap.wps.com/l/cbCairF2cdFMeevX","pdf",644444,1,15,"English","en",105,"# Introduction\n## Background and measurement approaches\n## Accelerometry and data-driven assessment\n## Machine learning and deep learning advantages\n# Methods\n## Search strategy and PRISMA process\n## Study selection and quality appraisal\n# Results\n## Physical activity analysis\n## Sleep monitoring\n## Model performance and sensor settings\n# Discussion\n## Strengths and limitations\n## Implications for practice\n# Future directions","[{\"question\":\"What data source do the reviewed studies use to assess preschool children’s activity and behaviour?\",\"answer\":\"The review focuses on accelerometer data collected in preschool settings, with ActiGraph GT3X+ used most often. Sensor placement varied across studies, including hip and wrist.\"},{\"question\":\"Which machine learning method performed best according to the included studies?\",\"answer\":\"Random Forest showed the most effective reported results, with accuracy up to 86.4% for activity classification and 96.2% for sleep prediction.\"},{\"question\":\"What limits the generalizability of the findings in this systematic review?\",\"answer\":\"Limitations include small sample sizes and methodological inconsistencies across studies, such as differences in sampling frequency and epoch length.\"}]","Machine Learning Applications for Physical Activity and Behaviour in Early Childhood - A Systematic Review | PDF",1785724119,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-applications-for-physical-activity-and-behaviour-in-early-childhood-a-systematic-review","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-applications-for-physical-activity-and-behaviour-in-early-childhood-a-systematic-review/119404/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What data source do the reviewed studies use to assess preschool children’s activity and behaviour?","Question",{"text":75,"@type":76},"The review focuses on accelerometer data collected in preschool settings, with ActiGraph GT3X+ used most often. Sensor placement varied across studies, including hip and wrist.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning method performed best according to the included studies?",{"text":80,"@type":76},"Random Forest showed the most effective reported results, with accuracy up to 86.4% for activity classification and 96.2% for sleep prediction.",{"name":82,"@type":73,"acceptedAnswer":83},"What limits the generalizability of the findings in this systematic review?",{"text":84,"@type":76},"Limitations include small sample sizes and methodological inconsistencies across studies, such as differences in sampling frequency and epoch length.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]