A1 Journal article (refereed)
New Machine Learning Approach for Detection of Injury Risk Factors in Young Team Sport Athletes (2021)
Jauhiainen, S., Kauppi, J.-P., Leppänen, M., Pasanen, K., Parkkari, J., Vasankari, T., Kannus, P., & Äyrämö, S. (2021). New Machine Learning Approach for Detection of Injury Risk Factors in Young Team Sport Athletes. International Journal of Sports Medicine, 42(02), 175-182. https://doi.org/10.1055/a-1231-5304
JYU authors or editors
Publication details
All authors or editors: Jauhiainen, Susanne; Kauppi, Jukka-Pekka; Leppänen, Mari; Pasanen, Kati; Parkkari, Jari; Vasankari, Tommi; Kannus, Pekka; Äyrämö, Sami
Journal or series: International Journal of Sports Medicine
ISSN: 0172-4622
eISSN: 1439-3964
Publication year: 2021
Publication date: 13/09/2020
Volume: 42
Issue number: 02
Pages range: 175-182
Publisher: Georg Thieme Verlag KG
Publication country: Germany
Publication language: English
DOI: https://doi.org/10.1055/a-1231-5304
Publication open access: Not open
Publication channel open access:
Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/88829
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.
Keywords: sports medicine; machine learning; forecasts; risk factors; sports injuries; becoming injured; knees; ankles; basketball; floorball; junior sports
Free keywords: sports medicine; predictive methods; machine learning; knee injuries; ankle injuries; basketball and floorball
Contributing organizations
Related projects
- Neuroscientifically motivated novel decoding methods for multichannel electromyographic and magnetoencephalographic signals
- Kauppi, Jukka-Pekka
- Research Council of Finland
Ministry reporting: Yes
Reporting Year: 2021
JUFO rating: 1