Citations

Background: Several factors are associated with an increased risk of anterior cruciate ligament (ACL) reconstruction revision. However, the ability to accurately translate these factors into a quantifiable risk of revision at a patient-specific level has remained elusive. We sought to determine if machine learning analysis of the Norwegian Knee Ligament Register (NKLR) can identify the most important risk factors associated with subsequent revision of primary ACL reconstruction and develop a clinically meaningful calculator for predicting revision of primary ACL reconstruction. Methods: Machine learning analysis was performed on the NKLR data set. The primary outcome was the probability of revision ACL reconstruction within 1, 2, and/or 5 years. Data were split randomly into training sets (75%) and test sets (25%). Four machine learning models were tested: Cox Lasso, survival random forest, generalized additive model, and gradient boosted regression. Concordance and calibration were calculated for all 4 models. Results: The data set included 24,935 patients, and 4.9% underwent a revision surgical procedure during a mean follow-up (and standard deviation) of 8.1 ± 4.1 years. All 4 models were well-calibrated, with moderate concordance (0.67 to 0.69). The Cox Lasso model required only 5 variables for outcome prediction. The other models either used more variables without an appreciable improvement in accuracy or had slightly lower accuracy overall. An in-clinic calculator was developed that can estimate the risk of ACL revision (Revision Risk Calculator). This calculator can quantify risk at a patient-specific level, with a plausible range from near 0% for low-risk patients to 20% for high-risk patients at 5 years. Conclusions: Machine learning analysis of a national knee ligament registry can predict the risk of ACL reconstruction revision with moderate accuracy. This algorithm supports the creation of an in-clinic calculator for point-of-care risk stratification based on the input of only 5 variables. Similar analysis using a larger or more comprehensive data set may improve the accuracy of risk prediction, and future studies incorporating patients who have experienced failure of ACL reconstruction but have not undergone subsequent revision may better predict the true risk of ACL reconstruction failure. Level of Evidence: Prognostic Level III . See Instructions for Authors for a complete description of levels of evidence.

Background: Increased lateral posterior tibial slope (LPTS) is associated with increased rates of anterior cruciate ligament (ACL) injury and failure of ACL reconstruction. It is unknown if ACL deficiency influences the developing proximal tibial physis and slope in skeletally immature patients through anterior tibial subluxation and abnormal force transmission. Purpose: To assess the natural history of LPTS in skeletally immature patients with an ACL-injured knee. Study Design: Case series; Level of evidence, 4. Methods: A total of 38 participants from a previous study on nonoperative management of ACL injury in skeletally immature patients were included. During the initial study, bilateral knee magnetic resonance imaging (MRI) was performed within 1 year of enrollment and again at final follow-up. All patients were younger than 13 years at the time of enrollment, and final follow-up occurred a mean 10 years after the injury. MRI scans were retrospectively reviewed by 2 reviewers to determine bilateral LPTS for each patient and each time point. Linear mixed models were used to assess LPTS differences between knees, change over time, and association with operational status. Subgroup analyses were performed for patients who remained nonoperated throughout the study. Results: A total of 22 patients had ACL reconstruction before final follow-up and 16 remained nonoperated. In the entire study population, the mean LPTS was higher in the injured knee than in the contralateral knee at final follow-up by 2.0° ( P < .001; 95% CI, 1.3°–2.6°). The mean LPTS increased significantly in the injured knee by 0.9° ( P = .042; 95% CI, 0.03°–1.7°), while the mean LPTS decreased in the contralateral knee by 0.4° ( P = .363; 95% CI, –0.8° to 0.4°). A significant difference in LPTS was also observed in the nonoperated subgroup. No significant association was observed between LPTS and operational status. Conclusion: Lateral posterior tibial slope increased more in the ACL-injured knee than in the contralateral uninjured knee in a group of skeletally immature patients. Lateral posterior tibial slope at baseline was not associated with the need for surgical reconstruction over the study period.