A preventive model for muscle injuries: a novel approach based on learning algorithms

López-Valenciano, Alejandro, Ayala, Francisco ORCID: 0000-0003-2210-7389, Puerta, José Miguel, De Ste Croix, Mark B ORCID: 0000-0001-9911-4355, Vera-García, Francisco J, Hernándes-Sánchez, Sergio, Ruiz-Pérez, Iñaki and Myer, Gregory D (2018) A preventive model for muscle injuries: a novel approach based on learning algorithms. Medicine and Science in Sports and Exercise, 50 (5). pp. 915-927. doi:10.1249/MSS.0000000000001535

Preview

Text (Peer reviewed version) 5280 De Ste Croix (2017) A preventive model for muscle injuries accepted manuscript.pdf - Accepted Version Available under License All Rights Reserved. Download (1MB) | Preview

Abstract

Introduction: The application of contemporary statistical approaches coming from Machine Learning and Data Mining environments to build more robust predictive models to identify athletes at high risk of injury might support injury prevention strategies of the future. Purpose: The purpose was to analyse and compare the behaviour of numerous machine learning methods in order to select the best performing injury risk factor model to identify athlete at risk of lower extremity muscle injuries (MUSINJ). Study Design: Prospective Cohort study. Methods: A total of 132 male professional soccer and handball players underwent a pre-season screening evaluation which included personal, psychological and neuromuscular measures. Furthermore, injury surveillance was employed to capture all the MUSINJ occurring in the 2013/2014 seasons. The predictive ability of several models built by applying a range of learning techniques were analysed and compared. Results: There were 32 MUSINJ over the follow up period, 21 (65.6%) of which corresponded to the hamstrings, three to the quadriceps (9.3%), four to the adductors (12.5%) and four to the triceps surae (12.5%). A total of 13 injures occurred during training and 19 during competition. Three players were injured twice during the observation period so the first injury was used leaving 29 MUSINJ that were used to develop the predictive models. The model generated by the SmooteBoost technique with a cost-sensitive ADTree as the base classifier reported the best evaluation criteria (area under the receiver operating characteristic curve score = 0.747, true positive rate = 65.9%, true negative rate = 79.1) and hence was considered the best for predicting MUSINJ. Conclusions: The prediction model showed moderate accuracy for identifying professional soccer and handball players at risk of MUSINJ. Therefore, the model developed might help in the decision-making process for injury prevention.

Item Type:	Article
Article Type:	Article
Uncontrolled Keywords:	Injury prevention; Machine learning techniques; Modelling; Screening; Soccer; REF2021
Subjects:	G Geography. Anthropology. Recreation > GV Recreation Leisure > GV557 Sports > GV861 Ball games: Baseball, football, golf, etc. R Medicine > RC Internal medicine > RC1200 Sports Medicine
Divisions:	Schools and Research Institutes > School of Education and Science
Research Priority Areas:	Health, Life Sciences, Sport and Wellbeing
Depositing User:	Susan Turner
Date Deposited:	11 Jan 2018 13:08
Last Modified:	31 Aug 2023 09:08
URI:	https://eprints.glos.ac.uk/id/eprint/5280

University Staff: Request a correction | Repository Editors: Update this record