Development of a Machine-Learning-Based Classifier for the Identification of Head and Body Impacts in Elite Level Australian Rules Football Players

被引:6
|
作者
Goodin, Peter [1 ,2 ]
Gardner, Andrew J. [3 ,4 ,5 ]
Dokani, Nasim [2 ]
Nizette, Ben [2 ]
Ahmadizadeh, Saeed [2 ]
Edwards, Suzi [3 ,6 ,7 ]
Iverson, Grant L. [8 ,9 ,10 ,11 ,12 ,13 ]
机构
[1] Univ Melbourne, Sch Med, Parkville, Vic, Australia
[2] HitIQ Ltd, S Melbourne, Vic, Australia
[3] Univ Newcastle, Sch Med & Publ Hlth, Prior Res Ctr Stroke & Brain Injury, Callaghan, NSW, Australia
[4] Calvary Mater Hosp, Hunter New England Local Hlth Dist Sports Concuss, Waratah, NSW, Australia
[5] Hunter Med Res Inst, New Lambton Hts, NSW, Australia
[6] Univ Newcastle, Sch Environm & Life Sci, Ourimbah, NSW, Australia
[7] Univ Newcastle, Prior Res Ctr Phys Act & Nutr, Callaghan, NSW, Australia
[8] Harvard Med Sch, Dept Phys Med & Rehabil, Boston, MA 02115 USA
[9] Spaulding Rehabil Hosp, Dept Phys Med & Rehabil, Charlestown, MA USA
[10] Spaulding Res Inst, Charlestown, MA USA
[11] MassGen Hosp Children, Sports Concuss Program, Boston, MA USA
[12] Home Base, Charlestown, MA USA
[13] Massachusetts Gen Hosp Program, Charlestown, MA USA
来源
关键词
Australian football; brain concussion; instrumented mouthguard; kinematics; impacts; machine learning; CHRONIC TRAUMATIC ENCEPHALOPATHY; VIDEO ANALYSIS; CONCUSSION; MAGNITUDE;
D O I
10.3389/fspor.2021.725245
中图分类号
G8 [体育];
学科分类号
04 ; 0403 ;
摘要
Background: Exposure to thousands of head and body impacts during a career in contact and collision sports may contribute to current or later life issues related to brain health. Wearable technology enables the measurement of impact exposure. The validation of impact detection is required for accurate exposure monitoring. In this study, we present a method of automatic identification (classification) of head and body impacts using an instrumented mouthguard, video-verified impacts, and machine-learning algorithms.Methods: Time series data were collected via the Nexus A9 mouthguard from 60 elite level men (mean age = 26.33; SD = 3.79) and four women (mean age = 25.50; SD = 5.91) from the Australian Rules Football players from eight clubs, participating in 119 games during the 2020 season. Ground truth data labeling on the captures used in this machine learning study was performed through the analysis of game footage by two expert video reviewers using SportCode and Catapult Vision. The visual labeling process occurred independently of the mouthguard time series data. True positive captures (captures where the reviewer directly observed contact between the mouthguard wearer and another player, the ball, or the ground) were defined as hits. Spectral and convolutional kernel based features were extracted from time series data. Performances of untuned classification algorithms from scikit-learn in addition to XGBoost were assessed to select the best performing baseline method for tuning.Results: Based on performance, XGBoost was selected as the classifier algorithm for tuning. A total of 13,712 video verified captures were collected and used to train and validate the classifier. True positive detection ranged from 94.67% in the Test set to 100% in the hold out set. True negatives ranged from 95.65 to 96.83% in the test and rest sets, respectively.Discussion and conclusion: This study suggests the potential for high performing impact classification models to be used for Australian Rules Football and highlights the importance of frequencies <150 Hz for the identification of these impacts.
引用
收藏
页数:10
相关论文
共 6 条
  • [1] Considerations in interpreting neuromuscular state in elite level Australian Rules football players
    Norris, Dean
    Joyce, David
    Siegler, Jason
    Cohen, Daniel
    Lovell, Ric
    [J]. JOURNAL OF SCIENCE AND MEDICINE IN SPORT, 2021, 24 (07) : 702 - 708
  • [2] Measurement of the head impacts in a sub-elite Australian Rules football team with an instrumented patch: An exploratory analysis
    King, D.
    Hecimovich, M.
    Clark, T.
    Gissane, C.
    [J]. INTERNATIONAL JOURNAL OF SPORTS SCIENCE & COACHING, 2017, 12 (03) : 359 - 370
  • [3] Visual search strategies and game knowledge in junior Australian rules football players: testing potential in talent identification and development
    Kassem, Lael
    Pang, Bonnie
    Dogramaci, Sera
    MacMahon, Clare
    Quinn, John
    Steel, Kylie A.
    [J]. FRONTIERS IN PSYCHOLOGY, 2024, 15
  • [4] Prevalence of head injury and medically diagnosed concussion in junior-level community-based Australian Rules Football
    Hecimovich, Mark D.
    King, Doug
    [J]. JOURNAL OF PAEDIATRICS AND CHILD HEALTH, 2017, 53 (03) : 246 - 251
  • [5] Pre-injury performance is most important for predicting the level of match participation after Achilles tendon ruptures in elite soccer players: a study using a machine learning classifier
    Diniz, Pedro
    Abreu, Mariana
    Lacerda, Diogo
    Martins, Antonio
    Pereira, Helder
    Ferreira, Frederico Castelo
    Kerkhoffs, Gino Mmj
    Fred, Ana
    [J]. KNEE SURGERY SPORTS TRAUMATOLOGY ARTHROSCOPY, 2022, 30 (12) : 4225 - 4237
  • [6] Pre-injury performance is most important for predicting the level of match participation after Achilles tendon ruptures in elite soccer players: a study using a machine learning classifier
    Pedro Diniz
    Mariana Abreu
    Diogo Lacerda
    António Martins
    Hélder Pereira
    Frederico Castelo Ferreira
    Gino MMJ Kerkhoffs
    Ana Fred
    [J]. Knee Surgery, Sports Traumatology, Arthroscopy, 2022, 30 : 4225 - 4237