Machine learning methods in sport injury prediction and prevention: a systematic review

Abstract

Purpose Injuries are common in sports and can have significant physical, psychological and financial consequences. Machine learning (ML) methods could be used to improve injury prediction and allow proper approaches to injury prevention. The aim of our study was therefore to perform a systematic review of ML methods in sport injury prediction and prevention. Methods A search of the PubMed database was performed on March 24th 2020. Eligible articles included original studies investigating the role of ML for sport injury prediction and prevention. Two independent reviewers screened articles, assessed eligibility, risk of bias and extracted data. Methodological quality and risk of bias were determined by the Newcastle–Ottawa Scale. Study quality was evaluated using the GRADE working group methodology. Results Eleven out of 249 studies met inclusion/exclusion criteria. Different ML methods were used (tree-based ensemble methods (n = 9), Support Vector Machines (n = 4), Artificial Neural Networks (n = 2)). The classification methods were facilitated by preprocessing steps (n = 5) and optimized using over- and undersampling methods (n = 6), hyperparameter tuning (n = 4), feature selection (n = 3) and dimensionality reduction (n = 1). Injury predictive performance ranged from poor (Accuracy = 52%, AUC = 0.52) to strong (AUC = 0.87, f1-score = 85%). Conclusions Current ML methods can be used to identify athletes at high injury risk and be helpful to detect the most important injury risk factors. Methodological quality of the analyses was sufficient in general, but could be further improved. More effort should be put in the interpretation of the ML models.

A Narrative Review for a Machine Learning Application in Sports: An Example Based on Injury Forecasting in Soccer

“…Supervised machine learning models can learn a function that map an input (e.g., external workloads, internal workloads, and self-reported wellness) to an output (e.g., injury label). Van Eetvelde et al [ 74 ], in their review about injury forecasting by machine learning model, asserted that the results detected in the previous papers are promising in the sense that these models might help coaches, physical trainers, and medical practitioners in the decision-making process for injury prevention and prediction. The most common supervised machine learning models used for injury forecasting are decision trees [ 15 , 20 , 23 , 24 ], binary logistic regression [ 6 , 11 , 15 , 24 ], random forests [ 15 , 22 , 24 ], and supporting vector machines [ 22 , 24 ].…”

Managing the Training Process in Elite Sports: From Descriptive to Prescriptive Data Analytics

“…24,25 Again, given the complexity of the training process, advanced statistics and machine learning techniques such as regression and decision trees can be recommended for this purpose. 21,22,[25][26][27][28] To evaluate predictive accuracy, appropriate statistical measures such as sensitivity, specificity, and mean absolute error should be used. 14,22 Also, it is advised to distinguish the model's in-sample and out-of-sample performance when interpreting predictive accuracy.…”

“…[17][18][19][20]26 In addition, the amount of training process data that are collected in elite sports is relatively small compared with other "big data" domains, such as finance using the historical data of stock prices or social sciences using social media data. Therefore, we advise being careful in dealing with commercial assertions that claim accurate training process data predictions (for more examples on predictive analytics in elite sports, see Van Eetvelde et al 27 and Richter et al 26 ).…”

Predicting subjective failure of ACL reconstruction: a machine learning analysis of the Norwegian Knee Ligament Register and patient reported outcomes

“…Recently, there has been an increased focus on the use of artificial intelligence and machine learning to improve predictive capability within several fields of medicine, including orthopaedic surgery [5][6][7][8][9]. These advanced statistical techniques utilize computer algorithms to model complex interactions between variables and may lead to improved capacity to predict outcome.…”