Journal article 307 views 6 downloads
Development of a Head Acceleration Event Classification Algorithm for Female Rugby Union
Annals of Biomedical Engineering, Volume: 51, Issue: 6, Pages: 1322 - 1330
PDF | Version of Record
Copyright: 2023 The Author(s). Distributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4.0).Download (674.47KB)
Instrumented mouthguards have been used to detect head accelerations and record kinematic data in numerous sports. Each recording requires validation through time-consuming video verification. Classification algorithms have been posed to automatically categorise head acceleration events and spurious...
|Published in:||Annals of Biomedical Engineering|
Springer Science and Business Media LLC
Check full text
No Tags, Be the first to tag this record!
Instrumented mouthguards have been used to detect head accelerations and record kinematic data in numerous sports. Each recording requires validation through time-consuming video verification. Classification algorithms have been posed to automatically categorise head acceleration events and spurious events. However, classification algorithms must be designed and/or validated for each combination of sport, sex and mouthguard system. This study provides the first algorithm to classify head acceleration data from exclusively female rugby union players. Mouthguards instrumented with kinematic sensors were given to 25 participants for six competitive rugby union matches in an inter-university league. Across all instrumented players, 214 impacts were recorded from 460 match-minutes. Matches were video recorded to enable retrospective labelling of genuine and spurious events. Four machine learning algorithms were trained on five matches to predict these labels, then tested on the sixth match. Of the four classifiers, the support vector machine achieved the best results, with area under the receiver operator curve (AUROC) and area under the precision recall curve (AUPRC) scores of 0.92 and 0.85 respectively, on the test data. These findings represent an important development for head impact telemetry in female sport, contributing to the safer participation and improving the reliability of head impact data collection within female contact sport.
Machine learning, head impact telemetry, wearable sensors, concussion, mTBI
Faculty of Science and Engineering
The authors would like to thank participants and coaches for their engagement in the study. We would specifically like to thank the Zienkiewicz Centre for Computational Engineering for the scholarship of DP. Additionally, the authors would like to thank Prevent Biometrics for the technical support throughout this project. Funding Funding was provided by Economic and Social Research Council Wales Doctoral Training Partnership and Zienkiewicz Centre for Computational Engineering (ZCCE) Doctoral Scholarship, Faculty of Science and Engineering, Swansea University, Swansea, UK.