A Machine Learning Approach to Assess Injury Risk in Elite Youth Football Players

Abstract

Purpose: To assess injury risk in elite-level youth football players based on anthropometric, motor coordination and physical performance measures with a machine learning approach.Methods: A total of 734 players in the U10 to U15 age categories (mean age: 11.7 +/-1.7 years) 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. An extreme gradient boosting algorithms (XGBoost) was 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. Conclusion: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

Home-Based Functional Electrical Stimulation of Human Permanent Denervated Muscles: A Narrative Review on Diagnostics, Managements, Results and Byproducts Revisited 2020

“…Machine learning (ML) algorithms, are becoming increasingly used in healthcare data applications. The increased availability of healthcare data and the continued development of big data analytics methods has driven the success of ML modelling in many quantitative fields, such as medical image processing or predictive system development, as well as other specialties such as neurology, cardiology, and oncology [ 58 , 59 , 60 , 61 , 62 ]. Mid-thigh computed tomography (CT) images from the Age, Gene/Environment Susceptibility (AGES) dataset have been used to quantitatively characterize subject-specific changes in soft tissue using a novel method known as non-linear trimodal regression analysis (NTRA) [ 63 ].…”

Using machine learning to improve our understanding of injury risk and prediction in elite male youth football players

“…Logistic regression does not manage imbalanced data sets well and tends to only consider the ability of one or a few variables to predict injury, yet it is acknowledged that injury is multifaceted and there will be interactions between and even within risks. 3,8 For example, body size, maturity and neuromuscular control may all interact to influence injury risk in young populations. Consequently, it has been argued that the complexity of injury means a broader statistical approach than logistic regression is needed to better understand relationships between risk factors and predictors of injury.…”

Machine Learning Outperforms Regression Analysis to Predict Next-Season Major League Baseball Player Injuries: Epidemiology and Validation of 13,982 Player-Years From Performance and Injury Profile Trends, 2000-2017

“…Several ML analyses are well-described (ie, LR and random forest) in the literature already and may assist the team physician in predicting injuries or identifying subclinical abnormalities. 5,16,17,23,27 Given the array of classic (ie, LR, random forest) and advanced modeling techniques, the results of this study demonstrate 3 important takeaway points to guide future orthopaedic and sports medicine research in this new frontier of injury modeling. First, a single predictive model is not necessarily ideally suited for all clinical questions posed.…”

“…Several ML analyses are well-described (ie, LR and random forest) in the literature already and may assist the team physician in predicting injuries or identifying subclinical abnormalities. 5 , 16 , 17 , 23 , 27 …”