Predicting ACL Reconstruction Failure with Machine Learning: Development of Machine Learning Prediction Models.

Abstract

Background: Anterior cruciate ligament reconstruction (ACLR) is the predominant and widely accepted treatment modality for ACL injury. However, recurrence of ACL rupture or failure of the reconstruction remains a significant challenge. Despite several studies in the literature that have developed prediction models to address this issue by identifying prognostic factors for treatment outcomes using classical statistical methods, the predictive efficacy of these models is frequently suboptimal.

Purpose: To (1) evaluate the predictive performance of different machine learning algorithms for the occurrence of failure in ACLR and (2) identify the most relevant predictors associated with this outcome.

Study design: Cohort study; Level of evidence, 3.

Methods: A total of 680 patients who underwent ACLR between January 2012 and July 2021 were evaluated. The study outcome was ACLR failure-defined as a complete tear confirmed by magnetic resonance imaging, arthroscopy, or clinical ACL insufficiency-evaluated at a minimum 2-year follow-up. Routinely collected data were used to train 9 machine learning algorithms-including k-nearest neighbors classifier, decision tree classifier, random forest classifier, extra trees classifier, gradient boosting classifier, eXtreme Gradient Boosting, CatBoost classifier, and logistic regression. A random sample of 70% of patients was used to train the algorithms, and 30% were left for performance assessment, simulating new data. The performance of the models was evaluated with the area under the receiver operating characteristic curve (AUC).

Results: The predictive performance of most models was good, with AUCs ranging from 0.71 to 0.85. The models with the best AUC metric were the CatBoost classifier (0.85 [95% CI, 0.81-0.89]) and the random forest classifier (0.84 [95% CI, 0.77-0.90). Knee hyperextension consistently emerged as the primary predictor for ACLR failure across all models subjected to our analysis.

Conclusion: Machine learning algorithms demonstrated good performance in predicting ACLR failure. Moreover, knee hyperextension consistently emerged as the primary predictor for failure across all models subjected to our analysis.

Clinical relevance: The findings of this study highlight the potential of machine learning as a valuable clinical tool for decision-making on surgical intervention. By offering nuanced insights, these algorithms may contribute to the evolving landscape of orthopaedic practice. Also, this study confirms knee hyperextension as an important risk factor for ACLR failure.