Predicting ACL Injury Using Machine Learning on Data From an Extensive Screening Test Battery of 880 Female Elite Athletes

Abstract

Background: Injury risk prediction is an emerging field in which more research is needed to recognize the best practices for accurate injury risk assessment. Important issues related to predictive machine learning need to be considered, for example, to avoid overinterpreting the observed prediction performance. Purpose: To carefully investigate the predictive potential of multiple predictive machine learning methods on a large set of risk factor data for anterior cruciate ligament (ACL) injury; the proposed approach takes into account the effect of chance and random variations in prediction performance. Study Design: Case-control study; Level of evidence, 3. Methods: The authors used 3-dimensional motion analysis and physical data collected from 791 female elite handball and soccer players. Four common classifiers were used to predict ACL injuries (n = 60). Area under the receiver operating characteristic curve (AUC-ROC) averaged across 100 cross-validation runs (mean AUC-ROC) was used as a performance metric. Results were confirmed with repeated permutation tests (paired Wilcoxon signed-rank-test; P < .05). Additionally, the effect of the most common class imbalance handling techniques was evaluated. Results: For the best classifier (linear support vector machine), the mean AUC-ROC was 0.63. Regardless of the classifier, the results were significantly better than chance, confirming the predictive ability of the data and methods used. AUC-ROC values varied substantially across repetitions and methods (0.51-0.69). Class imbalance handling did not improve the results. Conclusion: The authors’ approach and data showed statistically significant predictive ability, indicating that there exists information in this prospective data set that may be valuable for understanding injury causation. However, the predictive ability remained low from the perspective of clinical assessment, suggesting that included variables cannot be used for ACL prediction in practice.

Development of an algorithm-based approach using neuromuscular test results to indicate an increased risk for non-contact lower limb injuries in elite football players

“…Jauhiainen et al included an extensive screening protocol comprising neuromuscular and functional tests. Their results show that they could not predict ACL injuries in clinical practice 23…”

“…Nevertheless, screening can still highlight key risk factors for sports injuries 22. The current literature comprises similar proofs of concept in the NBA11 12 or applied to a specific injury—ACL injury 23. The study of Cohan et al predicted injury based on the injury mechanism, player’s characteristics and game statistics,11 while Lu et al focused mostly on injury history and past concussions 12.…”

Performance and healthcare analysis in elite sports teams using artificial intelligence: a scoping review

“…For instance, the GBRT model, known for its predictive accuracy in regression and classification problems, is assessed for its efficacy in predicting injury risk and performance outcomes ( 60 ). The AUC-ROC curve, a measure of the ability of a classifier to distinguish between classes, is used to evaluate the performance of predictive models in injury severity and return-to-play predictions ( 45 , 52 , 64 ).…”

Suggested improvements to the 11+ as identified by coaches, players, strength and conditioning staff and medical staff in New Zealand Football

“… 29 Unfortunately, while it may be possible to identify individual risk factors for injury, there is currently limited evidence to support the effectiveness of these individualised injury prevention strategies. 30 31 It is unlikely that this form of targeted approach would be viable at a population level, where access to S+C and coaching support is limited. There was some interest in developing targeted strategies for women and youth players; however, this was not supported by participants in the player group (although they would support this approach if there was a clear demonstrated need).…”