Cargando…

Development and validation of FootNet; a new kinematic algorithm to improve foot-strike and toe-off detection in treadmill running

The accurate detection of foot-strike and toe-off is often critical in the assessment of running biomechanics. The gold standard method for step event detection requires force data which are not always available. Although kinematics-based algorithms can also be used, their accuracy and generalisabil...

Descripción completa

Detalles Bibliográficos
Autores principales: Rivadulla, Adrian, Chen, Xi, Weir, Gillian, Cazzola, Dario, Trewartha, Grant, Hamill, Joseph, Preatoni, Ezio
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8351929/
https://www.ncbi.nlm.nih.gov/pubmed/34370747
http://dx.doi.org/10.1371/journal.pone.0248608
_version_ 1783736071895384064
author Rivadulla, Adrian
Chen, Xi
Weir, Gillian
Cazzola, Dario
Trewartha, Grant
Hamill, Joseph
Preatoni, Ezio
author_facet Rivadulla, Adrian
Chen, Xi
Weir, Gillian
Cazzola, Dario
Trewartha, Grant
Hamill, Joseph
Preatoni, Ezio
author_sort Rivadulla, Adrian
collection PubMed
description The accurate detection of foot-strike and toe-off is often critical in the assessment of running biomechanics. The gold standard method for step event detection requires force data which are not always available. Although kinematics-based algorithms can also be used, their accuracy and generalisability are limited, often requiring corrections for speed or foot-strike pattern. The purpose of this study was to develop FootNet, a novel kinematics and deep learning-based algorithm for the detection of step events in treadmill running. Five treadmill running datasets were gathered and processed to obtain segment and joint kinematics, and to identify the contact phase within each gait cycle using force data. The proposed algorithm is based on a long short-term memory recurrent neural network and takes the distal tibia anteroposterior velocity, ankle dorsiflexion/plantar flexion angle and the anteroposterior and vertical velocities of the foot centre of mass as input features to predict the contact phase within a given gait cycle. The chosen model architecture underwent 5-fold cross-validation and the final model was tested in a subset of participants from each dataset (30%). Non-parametric Bland-Altman analyses (bias and [95% limits of agreement]) and root mean squared error (RMSE) were used to compare FootNet against the force data step event detection method. The association between detection errors and running speed, foot-strike angle and incline were also investigated. FootNet outperformed previously published algorithms (foot-strike bias = 0 [–10, 7] ms, RMSE = 5 ms; toe-off bias = 0 [–10, 10] ms, RMSE = 6 ms; and contact time bias = 0 [–15, 15] ms, RMSE = 8 ms) and proved robust to different running speeds, foot-strike angles and inclines. We have made FootNet’s source code publicly available for step event detection in treadmill running when force data are not available.
format Online
Article
Text
id pubmed-8351929
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-83519292021-08-10 Development and validation of FootNet; a new kinematic algorithm to improve foot-strike and toe-off detection in treadmill running Rivadulla, Adrian Chen, Xi Weir, Gillian Cazzola, Dario Trewartha, Grant Hamill, Joseph Preatoni, Ezio PLoS One Research Article The accurate detection of foot-strike and toe-off is often critical in the assessment of running biomechanics. The gold standard method for step event detection requires force data which are not always available. Although kinematics-based algorithms can also be used, their accuracy and generalisability are limited, often requiring corrections for speed or foot-strike pattern. The purpose of this study was to develop FootNet, a novel kinematics and deep learning-based algorithm for the detection of step events in treadmill running. Five treadmill running datasets were gathered and processed to obtain segment and joint kinematics, and to identify the contact phase within each gait cycle using force data. The proposed algorithm is based on a long short-term memory recurrent neural network and takes the distal tibia anteroposterior velocity, ankle dorsiflexion/plantar flexion angle and the anteroposterior and vertical velocities of the foot centre of mass as input features to predict the contact phase within a given gait cycle. The chosen model architecture underwent 5-fold cross-validation and the final model was tested in a subset of participants from each dataset (30%). Non-parametric Bland-Altman analyses (bias and [95% limits of agreement]) and root mean squared error (RMSE) were used to compare FootNet against the force data step event detection method. The association between detection errors and running speed, foot-strike angle and incline were also investigated. FootNet outperformed previously published algorithms (foot-strike bias = 0 [–10, 7] ms, RMSE = 5 ms; toe-off bias = 0 [–10, 10] ms, RMSE = 6 ms; and contact time bias = 0 [–15, 15] ms, RMSE = 8 ms) and proved robust to different running speeds, foot-strike angles and inclines. We have made FootNet’s source code publicly available for step event detection in treadmill running when force data are not available. Public Library of Science 2021-08-09 /pmc/articles/PMC8351929/ /pubmed/34370747 http://dx.doi.org/10.1371/journal.pone.0248608 Text en © 2021 Rivadulla et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Rivadulla, Adrian
Chen, Xi
Weir, Gillian
Cazzola, Dario
Trewartha, Grant
Hamill, Joseph
Preatoni, Ezio
Development and validation of FootNet; a new kinematic algorithm to improve foot-strike and toe-off detection in treadmill running
title Development and validation of FootNet; a new kinematic algorithm to improve foot-strike and toe-off detection in treadmill running
title_full Development and validation of FootNet; a new kinematic algorithm to improve foot-strike and toe-off detection in treadmill running
title_fullStr Development and validation of FootNet; a new kinematic algorithm to improve foot-strike and toe-off detection in treadmill running
title_full_unstemmed Development and validation of FootNet; a new kinematic algorithm to improve foot-strike and toe-off detection in treadmill running
title_short Development and validation of FootNet; a new kinematic algorithm to improve foot-strike and toe-off detection in treadmill running
title_sort development and validation of footnet; a new kinematic algorithm to improve foot-strike and toe-off detection in treadmill running
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8351929/
https://www.ncbi.nlm.nih.gov/pubmed/34370747
http://dx.doi.org/10.1371/journal.pone.0248608
work_keys_str_mv AT rivadullaadrian developmentandvalidationoffootnetanewkinematicalgorithmtoimprovefootstrikeandtoeoffdetectionintreadmillrunning
AT chenxi developmentandvalidationoffootnetanewkinematicalgorithmtoimprovefootstrikeandtoeoffdetectionintreadmillrunning
AT weirgillian developmentandvalidationoffootnetanewkinematicalgorithmtoimprovefootstrikeandtoeoffdetectionintreadmillrunning
AT cazzoladario developmentandvalidationoffootnetanewkinematicalgorithmtoimprovefootstrikeandtoeoffdetectionintreadmillrunning
AT trewarthagrant developmentandvalidationoffootnetanewkinematicalgorithmtoimprovefootstrikeandtoeoffdetectionintreadmillrunning
AT hamilljoseph developmentandvalidationoffootnetanewkinematicalgorithmtoimprovefootstrikeandtoeoffdetectionintreadmillrunning
AT preatoniezio developmentandvalidationoffootnetanewkinematicalgorithmtoimprovefootstrikeandtoeoffdetectionintreadmillrunning