The Identification of Foot-Strike Patterns and Prediction of Running Related Injuries

Gore, Shane (2020) The Identification of Foot-Strike Patterns and Prediction of Running Related Injuries. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (8MB) | Preview
Preview	PDF (Configuration manual) Download (12MB) | Preview

Abstract

It is suggested that how the foot strikes the ground while running may be an important injury risk factor. Despite growing interest in foot-strike pattern and injury, only a limited number of studies have examined this relationship, with inconsistent findings. One source of this inconsistency may be how foot-strike pattern is defined. Indeed, current definitions are generally based on the arbitrary division of the foot into three equal parts. The aim of this project was twofold; 1) to identify foot-strike groupings using a clustering approach and to assess their relationship with injury and 2) to determine if any of the running biomechanics could predict injury classification. 3D biomechanical running data, collected prospectively, from 282 participants and 47,423 foot-strikes was explored along with injury occurrence. Six clustering algorithms were implemented and assessed with bootstrapped resamples of the Adjusted Rand Index (ARI). Mean ARI scores ranged from 0-0.007 indicating almost random assignment to the injury class. Six classification algorithms were then implemented and assessed with bootstrapped resamples of accuracy, sensitivity and specificity. The Random Forest model demonstrated the best performance (accuracy: 71%, specificity: 65%, sensitivity: 74%) and was significantly different than predicting the majority class (p<0.01). The final model contained ten features, of which, foot mechanics were not included. Collectively, these results suggest that foot-strike pattern is not important with respect to injury risk and the final features utilised by the Random Forest model likely represent the best targets for the prevention of running related injury.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	18 Jan 2021 14:10
Last Modified:	18 Jan 2021 14:10
URI:	https://norma.ncirl.ie/id/eprint/4367

Actions (login required)

View Item