Summary

The study's findings highlight the potential of machine learning as a valuable clinical tool for deci-sion-making on surgical intervention. Also, this study confirms knee hyperextension as an im-portant risk factor for ACL reconstruction failure.

Abstract

Background

Anterior Cruciate Ligament (ACL) reconstruction 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 developed prediction models to address this issue by identifying prognostic factors for treatment outcomes using classical statistical methods, their predictive efficacy is frequently suboptimal. The purpose of this study is to evaluate the predictive performance of different machine learning algorithms for the occurrence of failure in ACL reconstruction and to identify the most relevant predictors associated with this outcome.

Methods

680 patients submitted to ACL reconstruction between January 2012 and July 2021 were evaluated. The study outcome was ACL reconstruction failure, defined as a complete tear confirmed by MRI or arthroscopy or clinically ACL insufficiency. Routinely collected data were used to train 9 machine learning algorithms (k-nearest neighbors (KNN) classifier, decision tree classifier, random forest classifier, extra trees classifier, gradient boosting classifier, Light Gradient Boost-ing Machine (LightGBM), eXtreme Gradient Boosting (XGBoost), 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 AUC’s ranging from 0.71 to 0.84. The models with the best AUC metric were the CatBoost Classifier (0.85 [95% CI, 0.81 to 0.89]) and Random Forest Classifier (0.84 [ 95% CI, 0.77 to 0.90). Knee hyperextension consistently emerged as the primary predictor for ACL reconstruction failure across all models subjected to our analysis.

Conclusion

Machine learning algorithms demonstrated good performance to predict ACL reconstruction failure. Additionally, knee hyperextension consistently emerged as the primary predictor for failure across all models subjected to our analysis.