Machine Learning Applications for Physical Activity and Behaviour in Early Childhood: A Systematic Review
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 machin...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/11/6296 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850160980911194112 |
|---|---|
| author | Markel Rico-González Carlos D. Gómez-Carmona |
| author_facet | Markel Rico-González Carlos D. Gómez-Carmona |
| author_sort | Markel Rico-González |
| collection | DOAJ |
| description | 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 (<i>n</i> = 10) and sleep monitoring (<i>n</i> = 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. |
| format | Article |
| id | doaj-art-b9b85aeff6084a4cb76e4a35f45427c6 |
| institution | OA Journals |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-b9b85aeff6084a4cb76e4a35f45427c62025-08-20T02:23:00ZengMDPI AGApplied Sciences2076-34172025-06-011511629610.3390/app15116296Machine Learning Applications for Physical Activity and Behaviour in Early Childhood: A Systematic ReviewMarkel Rico-González0Carlos D. Gómez-Carmona1Department of Didactics of Music, Plastic and Corporal Expression, University of Basque Country (UPV-EHU), 48940 Leioa, SpainResearch Group in Training, Physical Activity and Sports Performance (ENFYRED), Department of Music, Plastic and Body Expression, University of Zaragoza, 44003 Teruel, SpainThis 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 (<i>n</i> = 10) and sleep monitoring (<i>n</i> = 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.https://www.mdpi.com/2076-3417/15/11/6296technologypreschoolpredictioncomputer scienceeducation |
| spellingShingle | Markel Rico-González Carlos D. Gómez-Carmona Machine Learning Applications for Physical Activity and Behaviour in Early Childhood: A Systematic Review Applied Sciences technology preschool prediction computer science education |
| title | Machine Learning Applications for Physical Activity and Behaviour in Early Childhood: A Systematic Review |
| title_full | Machine Learning Applications for Physical Activity and Behaviour in Early Childhood: A Systematic Review |
| title_fullStr | Machine Learning Applications for Physical Activity and Behaviour in Early Childhood: A Systematic Review |
| title_full_unstemmed | Machine Learning Applications for Physical Activity and Behaviour in Early Childhood: A Systematic Review |
| title_short | Machine Learning Applications for Physical Activity and Behaviour in Early Childhood: A Systematic Review |
| title_sort | machine learning applications for physical activity and behaviour in early childhood a systematic review |
| topic | technology preschool prediction computer science education |
| url | https://www.mdpi.com/2076-3417/15/11/6296 |
| work_keys_str_mv | AT markelricogonzalez machinelearningapplicationsforphysicalactivityandbehaviourinearlychildhoodasystematicreview AT carlosdgomezcarmona machinelearningapplicationsforphysicalactivityandbehaviourinearlychildhoodasystematicreview |