On-field player workload exposure and knee injury risk monitoring via deep learning

William R Johnson, Ajmal Mian, David G Lloyd, Jacqueline A Alderson

Research output: Contribution to journalArticle

Abstract

In sports analytics, an understanding of accurate on-field 3D knee joint moments (KJM) could provide an early warning system for athlete workload exposure and knee injury risk. Traditionally, this analysis has relied on captive laboratory force plates and associated downstream biomechanical modeling, and many researchers have approached the problem of portability by extrapolating models built on linear statistics. An alternative approach would be to capitalize on recent advances in deep learning. In this study, using the pre-trained CaffeNet convolutional neural network (CNN) model, multivariate regression of marker-based motion capture to 3D KJM for three sports-related movement types were compared. The strongest overall mean correlation to source modeling of 0.8895 was achieved over the initial 33% of stance phase for sidestepping. The accuracy of these mean predictions of the three critical KJM associated with anterior cruciate ligament (ACL) injury demonstrate the feasibility of on-field knee injury assessment using deep learning in lieu of laboratory embedded force plates. This multidisciplinary research approach significantly advances machine representation of real-world physical models with practical application for both community and professional level athletes.

Original languageEnglish
Pages (from-to)185-193
JournalJournal of Biomechanics
Volume93
DOIs
Publication statusPublished - 27 Aug 2019

Fingerprint

Knee Injuries
Knee Joint
Workload
Learning
Sports
Athletes
Monitoring
Neural Networks (Computer)
Ligaments
Alarm systems
Research Personnel
Statistics
Neural networks
Research
Deep learning

Cite this

@article{cff4e3b5df8941758945e8e252fa86fe,
title = "On-field player workload exposure and knee injury risk monitoring via deep learning",
abstract = "In sports analytics, an understanding of accurate on-field 3D knee joint moments (KJM) could provide an early warning system for athlete workload exposure and knee injury risk. Traditionally, this analysis has relied on captive laboratory force plates and associated downstream biomechanical modeling, and many researchers have approached the problem of portability by extrapolating models built on linear statistics. An alternative approach would be to capitalize on recent advances in deep learning. In this study, using the pre-trained CaffeNet convolutional neural network (CNN) model, multivariate regression of marker-based motion capture to 3D KJM for three sports-related movement types were compared. The strongest overall mean correlation to source modeling of 0.8895 was achieved over the initial 33{\%} of stance phase for sidestepping. The accuracy of these mean predictions of the three critical KJM associated with anterior cruciate ligament (ACL) injury demonstrate the feasibility of on-field knee injury assessment using deep learning in lieu of laboratory embedded force plates. This multidisciplinary research approach significantly advances machine representation of real-world physical models with practical application for both community and professional level athletes.",
author = "Johnson, {William R} and Ajmal Mian and Lloyd, {David G} and Alderson, {Jacqueline A}",
year = "2019",
month = "8",
day = "27",
doi = "10.1016/j.jbiomech.2019.07.002",
language = "English",
volume = "93",
pages = "185--193",
journal = "Journal of Biomechanics",
issn = "0021-9290",
publisher = "Elsevier",

}

On-field player workload exposure and knee injury risk monitoring via deep learning. / Johnson, William R; Mian, Ajmal; Lloyd, David G; Alderson, Jacqueline A.

In: Journal of Biomechanics, Vol. 93, 27.08.2019, p. 185-193.

Research output: Contribution to journalArticle

TY - JOUR

T1 - On-field player workload exposure and knee injury risk monitoring via deep learning

AU - Johnson, William R

AU - Mian, Ajmal

AU - Lloyd, David G

AU - Alderson, Jacqueline A

PY - 2019/8/27

Y1 - 2019/8/27

N2 - In sports analytics, an understanding of accurate on-field 3D knee joint moments (KJM) could provide an early warning system for athlete workload exposure and knee injury risk. Traditionally, this analysis has relied on captive laboratory force plates and associated downstream biomechanical modeling, and many researchers have approached the problem of portability by extrapolating models built on linear statistics. An alternative approach would be to capitalize on recent advances in deep learning. In this study, using the pre-trained CaffeNet convolutional neural network (CNN) model, multivariate regression of marker-based motion capture to 3D KJM for three sports-related movement types were compared. The strongest overall mean correlation to source modeling of 0.8895 was achieved over the initial 33% of stance phase for sidestepping. The accuracy of these mean predictions of the three critical KJM associated with anterior cruciate ligament (ACL) injury demonstrate the feasibility of on-field knee injury assessment using deep learning in lieu of laboratory embedded force plates. This multidisciplinary research approach significantly advances machine representation of real-world physical models with practical application for both community and professional level athletes.

AB - In sports analytics, an understanding of accurate on-field 3D knee joint moments (KJM) could provide an early warning system for athlete workload exposure and knee injury risk. Traditionally, this analysis has relied on captive laboratory force plates and associated downstream biomechanical modeling, and many researchers have approached the problem of portability by extrapolating models built on linear statistics. An alternative approach would be to capitalize on recent advances in deep learning. In this study, using the pre-trained CaffeNet convolutional neural network (CNN) model, multivariate regression of marker-based motion capture to 3D KJM for three sports-related movement types were compared. The strongest overall mean correlation to source modeling of 0.8895 was achieved over the initial 33% of stance phase for sidestepping. The accuracy of these mean predictions of the three critical KJM associated with anterior cruciate ligament (ACL) injury demonstrate the feasibility of on-field knee injury assessment using deep learning in lieu of laboratory embedded force plates. This multidisciplinary research approach significantly advances machine representation of real-world physical models with practical application for both community and professional level athletes.

U2 - 10.1016/j.jbiomech.2019.07.002

DO - 10.1016/j.jbiomech.2019.07.002

M3 - Article

VL - 93

SP - 185

EP - 193

JO - Journal of Biomechanics

JF - Journal of Biomechanics

SN - 0021-9290

ER -