Exploring the Application of Pattern Recognition and Machine Learning for Identifying Movement Phenotypes During Deep Squat and Hurdle Step Movements.

Sarah M Remedios,Daniel P Armstrong,Ryan B Graham,Steven L Fischer

doi:10.3389/fbioe.2020.00364

Sarah M Remedios, Daniel P Armstrong + Show 2 more

Open Access

https://doi.org/10.3389/fbioe.2020.00364

Copy DOI

Abstract

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.

Highlights

Movement screens are commonly used to assess an individual’s quality of movement as a method to highlight poor movement patterns (McCunn et al, 2016)
While the FMSTM protocol includes a battery of 7 distinct movements, we focus on the Deep Squat (DS) and right and lift hurdle step (RHS; left hurdle step (LHS)) movements
The principal component analysis (PCA) models revealed that 4, 6, and 6 Principal component (PC) each explained at least 5% of the variance in the time-series trajectory data for the DS, RHS, and LHS, respectively

Summary

Introduction

Movement screens are commonly used to assess an individual’s quality of movement as a method to highlight poor movement patterns (McCunn et al, 2016). The quality of movement, termed movement competency, can be explained as an individual’s ability to adopt a movement pattern that achieves the task objective, while minimizing injury risk (Kritz et al, 2009; McGill et al, 2015). Visual assessment of body mechanics is the de facto method for measuring movement competency (Sinden et al, 2017), which increases the subjectivity of movement screens, relying on the appraisal and previous knowledge of the practitioner. 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

Methods

Results

Discussion

Conclusion