EUVIMEDDescoperă EUVIMED
QuerschnittstudieOpen access

Video-Based Gait Assessment Using Machine Learning to Classify Age and Sex in Low-Resource Settings: Cross-Sectional Study

Chanchanok Aramrat iD, Poppy Alice Carson Mallinson iD, Papangkorn Inkaew iD, Pusit Seepheung iD, Nutchar Wiwatkunupakarn iD, Nida Buawangpong iD, Nick Birk iD, Judith Lieber iD, Santhi Bhogadi iD, Hemant Mahajan iD, Santosh Kumar Banjara iD, Bharati Kulkarni iD and 2 more

JMIR Formative Research · 2026-03-30 · 10 · e76755

DOI: 10.2196/76755 ↗

At a glance

Querschnittstudie in JMIR Formative Research, published online on 2026-03-30. Written by Chanchanok Aramrat and 13 co-authors. Institution: Department of Family Medicine, Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand. Major MEDLINE topics: Machine Learning, Video Recording, Gait Analysis, Gait. Cited 1 times so far (Crossref); 40 references. The full text is freely available in PubMed Central. Funded by: Medical Research Council.

RezumatSubjectsDate bibliograficeCiteRelated studies

Abstract (original language)

Background

Gait assessment is an important tool for evaluating health risks in older adults but remains underused in low-resource settings. We explored the feasibility of using a low-cost, simple walking protocol with smartphone video capture to extract health-related gait signals by classifying sex and age. Sex and age are fundamental biological factors linked to most health- and aging-related outcomes. Establishing baseline classification performance provides justification for future exploration of more complex health-related conditions using this protocol.

Objective

This study aimed to assess whether pose parameters derived from smartphone-based gait videos can be used by machine learning models to classify age and sex.

Methods

A cross-sectional study was conducted with 155 participants (Thailand: n=59, 38.1%; India: n=96, 61.9%). Participants performed a simple walking protocol while being recorded using smartphones. Pose estimation was conducted using the MediaPipe algorithm to extract 109 features related to joint distances, angles, and walking speed. For feasibility assessment, we calculated the proportion of recordings for which pose estimation could be extracted. Elastic-net logistic regression and histogram-based gradient boosting classifiers were used for analysis. Model performance was evaluated using 5-fold cross-validation. Outcomes were sex (male vs female) and age group (aged

Subjects

MeSH terms (MEDLINE)

Machine LearningVideo RecordingGait AnalysisGaitHumansCross-Sectional StudiesFemaleMaleAgedIndiaSmartphoneAge FactorsClassification AlgorithmsSex Factors

Author keywords

age and sex classificationgait assessmentlow-resource settingmachine learningsmartphone video recording

Authors and institutions

  • Department of Family Medicine, Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand.
  • Global Health and Chronic Conditions Research Group, Chiang Mai University, Chiang Mai, Thailand.
  • Department of Non-Communicable Disease Epidemiology, Faculty of Epidemiology and Population Health, London School of Hygiene & Tropical Medicine, London, United Kingdom.
  • Department of Computer Science, Faculty of Science, Chiang Mai University, Chiang Mai, Thailand.
  • Harvard TH Chan, School of Public Health, Harvard University, Cambridge, MA, United States.
  • Department of Medical Statistics, Faculty of Epidemiology and Population Health, London School of Hygiene & Tropical Medicine, London, United Kingdom.

ORCID profiles: Chanchanok Aramrat, Poppy Alice Carson Mallinson, Papangkorn Inkaew, Pusit Seepheung, Nutchar Wiwatkunupakarn, Nida Buawangpong, Nick Birk, Judith Lieber, Santhi Bhogadi, Hemant Mahajan, Santosh Kumar Banjara, Bharati Kulkarni, Sanjay Kinra, Chaisiri Angkurawaranon

Funding

  • Medical Research Council

Cite

APA

Aramrat, C., Mallinson, P. A. C., Inkaew, P., Seepheung, P., Wiwatkunupakarn, N., Buawangpong, N., Birk, N., Lieber, J., Bhogadi, S., Mahajan, H., Banjara, S. K., Kulkarni, B., Kinra, S., & Angkurawaranon, C. (2026). Video-Based Gait Assessment Using Machine Learning to Classify Age and Sex in Low-Resource Settings: Cross-Sectional Study. JMIR Formative Research, 10, e76755. https://doi.org/10.2196/76755

Vancouver

Aramrat C, Mallinson PAC, Inkaew P, Seepheung P, Wiwatkunupakarn N, Buawangpong N, et al. Video-Based Gait Assessment Using Machine Learning to Classify Age and Sex in Low-Resource Settings: Cross-Sectional Study. JMIR Formative Research. 2026;10:e76755. doi:10.2196/76755

BibTeX
@article{Aramrat2026,
  author = {Aramrat, Chanchanok and Mallinson, Poppy Alice Carson and Inkaew, Papangkorn and Seepheung, Pusit and Wiwatkunupakarn, Nutchar and Buawangpong, Nida and Birk, Nick and Lieber, Judith and Bhogadi, Santhi and Mahajan, Hemant and Banjara, Santosh Kumar and Kulkarni, Bharati and Kinra, Sanjay and Angkurawaranon, Chaisiri},
  title = {Video-Based Gait Assessment Using Machine Learning to Classify Age and Sex in Low-Resource Settings: Cross-Sectional Study},
  journal = {JMIR Formative Research},
  year = {2026},
  volume = {10},
  pages = {e76755},
  doi = {10.2196/76755}
}
Start for free →