TY - JOUR
T1 - A Machine Learning Approach to Assess Injury Risk in Elite Youth Football Players
AU - Rommers, Nikki
AU - Rössler, Roland
AU - Verhagen, Evert
AU - Vandecasteele, Florian
AU - Verstockt, Steven
AU - Vaeyens, Roel
AU - Lenoir, Matthieu
AU - D'Hondt, Eva
AU - Witvrouw, Erik
N1 - Funding Information: Conflicts of Interest and Source of Funding: The Research Foundation – Flanders kindly supported this study through a PhD research grant awarded to Nikki Rommers (grant number 1116517N). The funding source had no involvement in the conduct and reporting of the study. None of the authors declares a conflict of interest. Publisher Copyright: © 2020 Lippincott Williams & Wilkins. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/8/1
Y1 - 2020/8/1
N2 - PURPOSE: To assess injury risk in elite-level youth football (soccer) players based on anthropometric, motor coordination and physical performance measures with a machine learning model. METHODS: A total of 734 players in the U10 to U15 age categories (mean age, 11.7 ± 1.7 yr) from seven Belgian youth academies were prospectively followed during one season. Football exposure and occurring injuries were monitored continuously by the academies' coaching and medical staff, respectively. Preseason anthropometric measurements (height, weight, and sitting height) were taken and test batteries to assess motor coordination and physical fitness (strength, flexibility, speed, agility, and endurance) were performed. Extreme gradient boosting algorithms (XGBoost) were used to predict injury based on the preseason test results. Subsequently, the same approach was used to classify injuries as either overuse or acute. RESULTS: During the season, half of the players (n = 368) sustained at least one injury. Of the first occurring injuries, 173 were identified as overuse and 195 as acute injuries. The machine learning algorithm was able to identify the injured players in the hold-out test sample with 85% precision, 85% recall (sensitivity) and 85% accuracy (f1 score). Furthermore, injuries could be classified as overuse or acute with 78% precision, 78% recall, and 78% accuracy. CONCLUSIONS: Our machine learning algorithm was able to predict injury and to distinguish overuse from acute injuries with reasonably high accuracy based on preseason measures. Hence, it is a promising approach to assess injury risk among elite-level youth football players. This new knowledge could be applied in the development and improvement of injury risk management strategies to identify youth players with the highest injury risk.
AB - PURPOSE: To assess injury risk in elite-level youth football (soccer) players based on anthropometric, motor coordination and physical performance measures with a machine learning model. METHODS: A total of 734 players in the U10 to U15 age categories (mean age, 11.7 ± 1.7 yr) from seven Belgian youth academies were prospectively followed during one season. Football exposure and occurring injuries were monitored continuously by the academies' coaching and medical staff, respectively. Preseason anthropometric measurements (height, weight, and sitting height) were taken and test batteries to assess motor coordination and physical fitness (strength, flexibility, speed, agility, and endurance) were performed. Extreme gradient boosting algorithms (XGBoost) were used to predict injury based on the preseason test results. Subsequently, the same approach was used to classify injuries as either overuse or acute. RESULTS: During the season, half of the players (n = 368) sustained at least one injury. Of the first occurring injuries, 173 were identified as overuse and 195 as acute injuries. The machine learning algorithm was able to identify the injured players in the hold-out test sample with 85% precision, 85% recall (sensitivity) and 85% accuracy (f1 score). Furthermore, injuries could be classified as overuse or acute with 78% precision, 78% recall, and 78% accuracy. CONCLUSIONS: Our machine learning algorithm was able to predict injury and to distinguish overuse from acute injuries with reasonably high accuracy based on preseason measures. Hence, it is a promising approach to assess injury risk among elite-level youth football players. This new knowledge could be applied in the development and improvement of injury risk management strategies to identify youth players with the highest injury risk.
KW - Injury prevention
KW - adolescent
KW - child
KW - soccer
UR - http://www.scopus.com/inward/record.url?scp=85085642874&partnerID=8YFLogxK
U2 - https://doi.org/10.1249/MSS.0000000000002305
DO - https://doi.org/10.1249/MSS.0000000000002305
M3 - Article
C2 - 32079917
SN - 0195-9131
VL - 52
SP - 1745
EP - 1751
JO - Medicine and science in sports and exercise
JF - Medicine and science in sports and exercise
IS - 8
ER -