Int J Sports Med
DOI: 10.1055/a-1231-5304
Orthopedics & Biomechanics
© Georg Thieme Verlag KG Stuttgart · New York

New Machine Learning Approach for Detection of Injury Risk Factors in Young Team Sport Athletes

1  Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland
,
Jukka-Pekka Kauppi
1  Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland
,
Mari Leppänen
2  Tampere Research Centre of Sports Medicine, UKK Institute, Tampere, Finland
,
Kati Pasanen
2  Tampere Research Centre of Sports Medicine, UKK Institute, Tampere, Finland
3  Sport Injury Prevention Research Centre, Faculty of Kinesiology, University of Calgary, Calgary, Alberta, Canada
4  Alberta Children’s Hospital Research Institute, University of Calgary, Calgary, Alberta, Canada
5  McCaig Institute for Bone and Joint Health, University of Calgary, Calgary, Alberta, Canada
,
Jari Parkkari
2  Tampere Research Centre of Sports Medicine, UKK Institute, Tampere, Finland
6  Tampere University Hospital, Tampere, Finland
,
Tommi Vasankari
2  Tampere Research Centre of Sports Medicine, UKK Institute, Tampere, Finland
,
Pekka Kannus
2  Tampere Research Centre of Sports Medicine, UKK Institute, Tampere, Finland
6  Tampere University Hospital, Tampere, Finland
,
Sami Äyrämö
1  Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland
› Author Affiliations
Funding: This study was supported by the Finnish Ministry of Education and Culture, and Competitive State Research Financing of the Expert Responsibility area of Tampere University Hospital (grants 9S047, 9T046, 9U044, 9N053). This work has been carried out in two projects ”Value from health data with cognitive computing” and ”Watson Health Cloud”, funded by Business Finland. Susanne Jauhiainen was funded by the Jenny and Antti Wihuri Foundation (grant 00180121). Jukka-Pekka Kauppi was funded by the Academy of Finland Postdoctoral Researcher program (Research Council for Natural Sciences and Engineering; grant 286019).
Further Information

Publication History



accepted Published online: 202020 July 2020

Publication Date:
13 September 2020 (online)

Abstract

The purpose of this article is to present how predictive machine learning methods can be utilized for detecting sport injury risk factors in a data-driven manner. The approach can be used for finding new hypotheses for risk factors and confirming the predictive power of previously recognized ones. We used three-dimensional motion analysis and physical data from 314 young basketball and floorball players (48.4% males, 15.72±1.79 yr, 173.34±9.14 cm, 64.65±10.4 kg). Both linear (L1-regularized logistic regression) and non-linear methods (random forest) were used to predict moderate and severe knee and ankle injuries (N=57) during three-year follow-up. Results were confirmed with permutation tests and predictive risk factors detected with Wilcoxon signed-rank-test (p<0.01). Random forest suggested twelve consistent injury predictors and logistic regression twenty. Ten of these were suggested in both models; sex, body mass index, hamstring flexibility, knee joint laxity, medial knee displacement, height, ankle plantar flexion at initial contact, leg press one-repetition max, and knee valgus at initial contact. Cross-validated areas under receiver operating characteristic curve were 0.65 (logistic regression) and 0.63 (random forest). The results highlight the difficulty of predicting future injuries, but also show that even with models having relatively low predictive power, certain predictive injury risk factors can be consistently detected.

Supplementary Material