Gait stability prediction through synthetic time-series and vision-based data

IntroductionGait stability assessment in older adults is challenged by limited data availability and measurement complexity, particularly among vulnerable populations and in limited resource settings. We address three research questions: (1) can synthetic data accurately replicate the statistical pr...

Full description

Saved in:
Bibliographic Details
Main Authors: Mauricio C. Cordeiro, Ciaran O. Cathain, Vitor B. Nascimento, Thiago B. Rodrigues
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Sports and Active Living
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fspor.2025.1646146/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849763063358554112
author Mauricio C. Cordeiro
Ciaran O. Cathain
Ciaran O. Cathain
Ciaran O. Cathain
Vitor B. Nascimento
Thiago B. Rodrigues
author_facet Mauricio C. Cordeiro
Ciaran O. Cathain
Ciaran O. Cathain
Ciaran O. Cathain
Vitor B. Nascimento
Thiago B. Rodrigues
author_sort Mauricio C. Cordeiro
collection DOAJ
description IntroductionGait stability assessment in older adults is challenged by limited data availability and measurement complexity, particularly among vulnerable populations and in limited resource settings. We address three research questions: (1) can synthetic data accurately replicate the statistical properties of gait parameters in older adults? (2) how effectively do synthetic data-trained models predict the Margin of Stability (MoS) when tested on real-world data? and (3) what specific biomechanical features contribute most significantly to the MoS predictions in older adults? To address these challenges, the present study proposes a novel approach to gait stability prediction by integrating computer vision with a data-centric synthetic data generation (SDG) approach using accessible, low-cost technology.MethodsUsing a public dataset from 14 healthy older adults (86.7 ± 6.2 years), we implemented a constraint-based SDG methodology that preserved biomechanical relationships through SDG metadata configuration and rank correlation-based constraints. Gait analysis was performed through a smartphone (Motorola Moto G5 Play) and the open-source MediaPipe algorithm to extract body landmarks from frontal plane gait videos, making the approach suitable for resource-limited settings.ResultsOur approach achieved exceptional fidelity (97.09% overall) and maintained biomechanical variable relationships. The model trained exclusively on synthetic data (TSTR) outperformed the model trained on real data (TRTR), with error reductions (RMSE decreased by 56.3%, MAE by 58.2%, and MSE by 80.9%) and improved variance explanation (R2 increase of 31.2%). SHAP analysis revealed that the synthetic data approach enhanced feature attribution alignment with established principles, particularly for step width, BMI, and fall history.DiscussionTherefore, our results show that: (1) synthetic data accurately replicated gait parameters with high fidelity; (2) synthetic data-trained models outperformed real data-trained models in MoS prediction; and (3) step width, BMI, and fall history were the most significant predictors of MoS in older adults. These findings demonstrate the potential of synthetic biomechanical time series to overcome data scarcity, improve predictive modeling capabilities, and enhance clinical gait assessment through accessible, low-cost computer vision methods.
format Article
id doaj-art-774e7c88aaa040e8a680bc5c1bd765b5
institution DOAJ
issn 2624-9367
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Sports and Active Living
spelling doaj-art-774e7c88aaa040e8a680bc5c1bd765b52025-08-20T03:05:31ZengFrontiers Media S.A.Frontiers in Sports and Active Living2624-93672025-08-01710.3389/fspor.2025.16461461646146Gait stability prediction through synthetic time-series and vision-based dataMauricio C. Cordeiro0Ciaran O. Cathain1Ciaran O. Cathain2Ciaran O. Cathain3Vitor B. Nascimento4Thiago B. Rodrigues5Department of Engineering & Informatics, Technological University of the Shannon, Athlone, IrelandDepartment of Sport & Health Sciences, Technological University of the Shannon, Athlone, IrelandSHE Research Centre, Technological University of the Shannon, Athlone, IrelandDepartment of Sport Science and Nutrition, Faculty of Science and Engineering, Maynooth University, Maynooth, IrelandDepartment of Physical Education, Pontifícia Universidade Católica do Paraná, Curitiba, BrazilDepartment of Engineering & Informatics, Technological University of the Shannon, Athlone, IrelandIntroductionGait stability assessment in older adults is challenged by limited data availability and measurement complexity, particularly among vulnerable populations and in limited resource settings. We address three research questions: (1) can synthetic data accurately replicate the statistical properties of gait parameters in older adults? (2) how effectively do synthetic data-trained models predict the Margin of Stability (MoS) when tested on real-world data? and (3) what specific biomechanical features contribute most significantly to the MoS predictions in older adults? To address these challenges, the present study proposes a novel approach to gait stability prediction by integrating computer vision with a data-centric synthetic data generation (SDG) approach using accessible, low-cost technology.MethodsUsing a public dataset from 14 healthy older adults (86.7 ± 6.2 years), we implemented a constraint-based SDG methodology that preserved biomechanical relationships through SDG metadata configuration and rank correlation-based constraints. Gait analysis was performed through a smartphone (Motorola Moto G5 Play) and the open-source MediaPipe algorithm to extract body landmarks from frontal plane gait videos, making the approach suitable for resource-limited settings.ResultsOur approach achieved exceptional fidelity (97.09% overall) and maintained biomechanical variable relationships. The model trained exclusively on synthetic data (TSTR) outperformed the model trained on real data (TRTR), with error reductions (RMSE decreased by 56.3%, MAE by 58.2%, and MSE by 80.9%) and improved variance explanation (R2 increase of 31.2%). SHAP analysis revealed that the synthetic data approach enhanced feature attribution alignment with established principles, particularly for step width, BMI, and fall history.DiscussionTherefore, our results show that: (1) synthetic data accurately replicated gait parameters with high fidelity; (2) synthetic data-trained models outperformed real data-trained models in MoS prediction; and (3) step width, BMI, and fall history were the most significant predictors of MoS in older adults. These findings demonstrate the potential of synthetic biomechanical time series to overcome data scarcity, improve predictive modeling capabilities, and enhance clinical gait assessment through accessible, low-cost computer vision methods.https://www.frontiersin.org/articles/10.3389/fspor.2025.1646146/fullsynthetic datagait stabilitycomputer visionSHAP valuesMediaPipe pose estimation
spellingShingle Mauricio C. Cordeiro
Ciaran O. Cathain
Ciaran O. Cathain
Ciaran O. Cathain
Vitor B. Nascimento
Thiago B. Rodrigues
Gait stability prediction through synthetic time-series and vision-based data
Frontiers in Sports and Active Living
synthetic data
gait stability
computer vision
SHAP values
MediaPipe pose estimation
title Gait stability prediction through synthetic time-series and vision-based data
title_full Gait stability prediction through synthetic time-series and vision-based data
title_fullStr Gait stability prediction through synthetic time-series and vision-based data
title_full_unstemmed Gait stability prediction through synthetic time-series and vision-based data
title_short Gait stability prediction through synthetic time-series and vision-based data
title_sort gait stability prediction through synthetic time series and vision based data
topic synthetic data
gait stability
computer vision
SHAP values
MediaPipe pose estimation
url https://www.frontiersin.org/articles/10.3389/fspor.2025.1646146/full
work_keys_str_mv AT mauricioccordeiro gaitstabilitypredictionthroughsynthetictimeseriesandvisionbaseddata
AT ciaranocathain gaitstabilitypredictionthroughsynthetictimeseriesandvisionbaseddata
AT ciaranocathain gaitstabilitypredictionthroughsynthetictimeseriesandvisionbaseddata
AT ciaranocathain gaitstabilitypredictionthroughsynthetictimeseriesandvisionbaseddata
AT vitorbnascimento gaitstabilitypredictionthroughsynthetictimeseriesandvisionbaseddata
AT thiagobrodrigues gaitstabilitypredictionthroughsynthetictimeseriesandvisionbaseddata