Exploring the Application of Pattern Recognition and Machine Learning for Identifying Movement Phenotypes During Deep Squat and Hurdle Step Movements
BackgroundMovement screens are increasingly used in sport and rehabilitation to evaluate movement competency. However, common screens are often evaluated using subjective visual detection of a priori prescribed discrete movement features (e.g., spine angle at maximum squat depth) and may not account...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2020-04-01
|
Series: | Frontiers in Bioengineering and Biotechnology |
Subjects: | |
Online Access: | https://www.frontiersin.org/article/10.3389/fbioe.2020.00364/full |
_version_ | 1818578136757960704 |
---|---|
author | Sarah M. Remedios Daniel P. Armstrong Ryan B. Graham Steven L. Fischer |
author_facet | Sarah M. Remedios Daniel P. Armstrong Ryan B. Graham Steven L. Fischer |
author_sort | Sarah M. Remedios |
collection | DOAJ |
description | BackgroundMovement screens are increasingly used in sport and rehabilitation to evaluate movement competency. However, common screens are often evaluated using subjective visual detection of a priori prescribed discrete movement features (e.g., spine angle at maximum squat depth) and may not account for whole-body movement coordination, or associations between different discrete features.ObjectiveTo apply pattern recognition and machine learning techniques to identify whole-body movement pattern phenotypes during the performance of exemplar functional movement screening tasks; the deep squat and hurdle step. Additionally, we also aimed to compare how discrete kinematic measures, commonly used to score movement competency, differed between emergent groups identified via pattern recognition and machine learning.MethodsPrincipal component analysis (PCA) was applied to 3-dimensional (3D) trajectory data from participant’s deep squat (DS) and hurdle step performance, identifying emerging features that describe orthogonal modes of inter-trial variance in the data. A gaussian mixture model (GMM) was fit and used to cluster the principal component scores as an unsupervised machine learning approach to identify emergent movement phenotypes. Between group features were analyzed using a one-way ANOVA to determine if the objective classifications were significantly different from one another.ResultsThree clusters (i.e., phenotypes) emerged for the DS and right hurdle step (RHS) and 4 phenotypes emerged for the left hurdle step (LHS). Selected discrete points commonly used to score DS and hurdle step movements were different between emergent groups. In regard to the select discrete kinematic measures, 4 out of 5, 7 out of 7 and 4 out of 7, demonstrated a main effect (p < 0.05) between phenotypes for the DS, RHS, and LHS respectively.ConclusionFindings support that whole-body movement analysis, pattern recognition and machine learning techniques can objectively identify movement behavior phenotypes without the need to a priori prescribe movement features. However, we also highlight important considerations that can influence outcomes when using machine learning for this purpose. |
first_indexed | 2024-12-16T06:41:01Z |
format | Article |
id | doaj.art-2118b152a42d4f349944b2a3942459ca |
institution | Directory Open Access Journal |
issn | 2296-4185 |
language | English |
last_indexed | 2024-12-16T06:41:01Z |
publishDate | 2020-04-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Bioengineering and Biotechnology |
spelling | doaj.art-2118b152a42d4f349944b2a3942459ca2022-12-21T22:40:40ZengFrontiers Media S.A.Frontiers in Bioengineering and Biotechnology2296-41852020-04-01810.3389/fbioe.2020.00364520082Exploring the Application of Pattern Recognition and Machine Learning for Identifying Movement Phenotypes During Deep Squat and Hurdle Step MovementsSarah M. Remedios0Daniel P. Armstrong1Ryan B. Graham2Steven L. Fischer3Occupational Biomechanics and Ergonomics Laboratory, Department of Kinesiology, University of Waterloo, Waterloo, ON, CanadaOccupational Biomechanics and Ergonomics Laboratory, Department of Kinesiology, University of Waterloo, Waterloo, ON, CanadaSpine Biomechanics Laboratory, School of Human Kinetics, University of Ottawa, Ottawa, ON, CanadaOccupational Biomechanics and Ergonomics Laboratory, Department of Kinesiology, University of Waterloo, Waterloo, ON, CanadaBackgroundMovement screens are increasingly used in sport and rehabilitation to evaluate movement competency. However, common screens are often evaluated using subjective visual detection of a priori prescribed discrete movement features (e.g., spine angle at maximum squat depth) and may not account for whole-body movement coordination, or associations between different discrete features.ObjectiveTo apply pattern recognition and machine learning techniques to identify whole-body movement pattern phenotypes during the performance of exemplar functional movement screening tasks; the deep squat and hurdle step. Additionally, we also aimed to compare how discrete kinematic measures, commonly used to score movement competency, differed between emergent groups identified via pattern recognition and machine learning.MethodsPrincipal component analysis (PCA) was applied to 3-dimensional (3D) trajectory data from participant’s deep squat (DS) and hurdle step performance, identifying emerging features that describe orthogonal modes of inter-trial variance in the data. A gaussian mixture model (GMM) was fit and used to cluster the principal component scores as an unsupervised machine learning approach to identify emergent movement phenotypes. Between group features were analyzed using a one-way ANOVA to determine if the objective classifications were significantly different from one another.ResultsThree clusters (i.e., phenotypes) emerged for the DS and right hurdle step (RHS) and 4 phenotypes emerged for the left hurdle step (LHS). Selected discrete points commonly used to score DS and hurdle step movements were different between emergent groups. In regard to the select discrete kinematic measures, 4 out of 5, 7 out of 7 and 4 out of 7, demonstrated a main effect (p < 0.05) between phenotypes for the DS, RHS, and LHS respectively.ConclusionFindings support that whole-body movement analysis, pattern recognition and machine learning techniques can objectively identify movement behavior phenotypes without the need to a priori prescribe movement features. However, we also highlight important considerations that can influence outcomes when using machine learning for this purpose.https://www.frontiersin.org/article/10.3389/fbioe.2020.00364/fullprincipal component analysisclustergaussian mixture modelmovement phenotypesfunctional movement screen |
spellingShingle | Sarah M. Remedios Daniel P. Armstrong Ryan B. Graham Steven L. Fischer Exploring the Application of Pattern Recognition and Machine Learning for Identifying Movement Phenotypes During Deep Squat and Hurdle Step Movements Frontiers in Bioengineering and Biotechnology principal component analysis cluster gaussian mixture model movement phenotypes functional movement screen |
title | Exploring the Application of Pattern Recognition and Machine Learning for Identifying Movement Phenotypes During Deep Squat and Hurdle Step Movements |
title_full | Exploring the Application of Pattern Recognition and Machine Learning for Identifying Movement Phenotypes During Deep Squat and Hurdle Step Movements |
title_fullStr | Exploring the Application of Pattern Recognition and Machine Learning for Identifying Movement Phenotypes During Deep Squat and Hurdle Step Movements |
title_full_unstemmed | Exploring the Application of Pattern Recognition and Machine Learning for Identifying Movement Phenotypes During Deep Squat and Hurdle Step Movements |
title_short | Exploring the Application of Pattern Recognition and Machine Learning for Identifying Movement Phenotypes During Deep Squat and Hurdle Step Movements |
title_sort | exploring the application of pattern recognition and machine learning for identifying movement phenotypes during deep squat and hurdle step movements |
topic | principal component analysis cluster gaussian mixture model movement phenotypes functional movement screen |
url | https://www.frontiersin.org/article/10.3389/fbioe.2020.00364/full |
work_keys_str_mv | AT sarahmremedios exploringtheapplicationofpatternrecognitionandmachinelearningforidentifyingmovementphenotypesduringdeepsquatandhurdlestepmovements AT danielparmstrong exploringtheapplicationofpatternrecognitionandmachinelearningforidentifyingmovementphenotypesduringdeepsquatandhurdlestepmovements AT ryanbgraham exploringtheapplicationofpatternrecognitionandmachinelearningforidentifyingmovementphenotypesduringdeepsquatandhurdlestepmovements AT stevenlfischer exploringtheapplicationofpatternrecognitionandmachinelearningforidentifyingmovementphenotypesduringdeepsquatandhurdlestepmovements |