A preventive model for hamstring injuries in professional soccer: Learning algorithms

Ayala, Francisco, López-Valenciano, Alejandro, Jose, Antonio, De Ste Croix, Mark B ORCID: 0000-0001-9911-4355, Vera-García, Francisco, García-Vaquero, Maria, Ruiz-Pérez, Iñaki and Myer, Gregory (2019) A preventive model for hamstring injuries in professional soccer: Learning algorithms. International Journal of Sports Medicine, 40 (5). pp. 344-353. doi:10.1055/a-0826-1955

[img]
Preview
Text (Peer reviewed version)
De Ste Croix (2018) 6383 A preventive model for hamstring injuries in professional soccer.pdf - Accepted Version
Available under License All Rights Reserved.

Download (897kB) | Preview
[img]
Preview
Text (Supplemental Digital Content 1)
SDC 1.pdf - Accepted Version
Available under License All Rights Reserved.

Download (102kB) | Preview
[img]
Preview
Text (Supplemental Digital Content 2)
SDC 2.pdf - Accepted Version
Available under License All Rights Reserved.

Download (163kB) | Preview
[img]
Preview
Text (Supplemental Digital Content 3)
SDC 3.pdf - Accepted Version
Available under License All Rights Reserved.

Download (152kB) | Preview
[img]
Preview
Text (Supplemental Digital Content 4)
SDC 4.pdf - Accepted Version
Available under License All Rights Reserved.

Download (331kB) | Preview
[img]
Preview
Text (Supplemental Digital Content 5)
SDC 5.pdf - Accepted Version
Available under License All Rights Reserved.

Download (338kB) | Preview
[img]
Preview
Text (Supplemental Digital Content 6)
SDC 6.pdf - Accepted Version
Available under License All Rights Reserved.

Download (239kB) | Preview
[img]
Preview
Text (Supplemental Digital Content 7)
SDC 7.pdf - Accepted Version
Available under License All Rights Reserved.

Download (179kB) | Preview
[img]
Preview
Text (Supplemental Digital Content 8)
SDC 8.pdf - Accepted Version
Available under License All Rights Reserved.

Download (296kB) | Preview
[img]
Preview
Image (Supplemental Digital Content 9)
SDC 9. First classifier.jpg - Accepted Version
Available under License All Rights Reserved.

Download (669kB) | Preview
[img]
Preview
Image (Supplemental Digital Content 10)
SDC 10. Second classifier.jpg - Accepted Version
Available under License All Rights Reserved.

Download (618kB) | Preview
[img]
Preview
Image (Supplemental Digital Content 11)
SDC 11. Third classifier.jpg - Accepted Version
Available under License All Rights Reserved.

Download (679kB) | Preview
[img]
Preview
Image (Supplemental Digital Content 12)
SDC 12. Fourth classifier.jpg - Accepted Version
Available under License All Rights Reserved.

Download (655kB) | Preview
[img]
Preview
Image (Supplemental Digital Content 13)
SDC 13. Fifth classifier.jpg - Accepted Version
Available under License All Rights Reserved.

Download (605kB) | Preview
[img]
Preview
Image (Supplemental Digital Content 14)
SDC 14. Sixth classifier.jpg - Accepted Version
Available under License All Rights Reserved.

Download (607kB) | Preview
[img]
Preview
Image (Supplemental Digital Content 15)
SDC 15. Seventh classifier.jpg - Accepted Version
Available under License All Rights Reserved.

Download (661kB) | Preview
[img]
Preview
Image (Supplemental Digital Content 16)
SDC 16. Eighth classifier.jpg - Accepted Version
Available under License All Rights Reserved.

Download (622kB) | Preview
[img]
Preview
Image (Supplemental Digital Content 17)
SDC 17. Ninth classifier.jpg - Accepted Version
Available under License All Rights Reserved.

Download (675kB) | Preview
[img]
Preview
Image (Supplemental Digital Content 18)
SDC 18. Tenth classifier.jpg - Accepted Version
Available under License All Rights Reserved.

Download (622kB) | Preview

Abstract

Hamstring strain injury (HSI) is one of the most prevalent and severe injury in professional soccer. The purpose was to analyse and compare the predictive ability of a range of machine learning techniques to select the best performing injury risk factor model to identify professional soccer players at high risk of HSIs. A total of 96 male professional soccer players underwent a pre-season screening evaluation that included a large number of individual, psychological and neuromuscular measures. Injury surveillance was prospectively employed to capture all the HSI occurring in the 2013/2014 season. There were 18 HSIs. Injury distribution was 55.6% dominant leg and 44.4% non-dominant leg. The model generated by the SmooteBoostM1 technique with a cost-sensitive ADTree as the base classifier reported the best evaluation criteria (area under the receiver operating characteristic curve score=0.837, true positive rate=77.8%, true negative rate=83.8%) and hence was considered the best for predicting HSI. The prediction model showed moderate to high accuracy for identifying professional soccer players at risk of HSI during pre-season screenings. Therefore, the model developed might help coaches, physical trainers and medical practitioners in the decision-making process for injury prevention.

Item Type: Article
Article Type: Article
Uncontrolled Keywords: Injury Prevention; Injury Risk; Screening; Decision Making
Subjects: G Geography. Anthropology. Recreation > GV Recreation Leisure > GV557 Sports
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 Sport and Exercise
Research Priority Areas: Sport, Exercise, Health & Wellbeing
Depositing User: Kate Greenaway
Date Deposited: 10 Jan 2019 17:58
Last Modified: 30 Jul 2020 15:16
URI: http://eprints.glos.ac.uk/id/eprint/6383

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

University Of Gloucestershire

Bookmark and Share

Find Us On Social Media:

Social Media Icons Facebook Twitter Google+ YouTube Pinterest Linkedin

Other University Web Sites

University of Gloucestershire, The Park, Cheltenham, Gloucestershire, GL50 2RH. Telephone +44 (0)844 8010001.