Cooper, Jonathan M.

Background: As machine learning becomes increasingly utilized in orthopaedic clinical research, the application of machine learning methodology to cohort data from the Multicenter ACL Revision Study (MARS) presents a valuable opportunity to translate data into patient-specific insights. Purpose: To apply novel machine learning methodology to MARS cohort data to determine a predictive model of revision anterior cruciate ligament reconstruction (rACLR) graft failure and features most predictive of failure. Study Design: Cohort study; Level of evidence, 3. Methods: The authors prospectively recruited patients undergoing rACLR from the MARS cohort and obtained preoperative radiographs, surgeon-reported intraoperative findings, and 2- and 6-year follow-up data on patient-reported outcomes, additional surgeries, and graft failure. Machine learning models including logistic regression (LR), XGBoost, gradient boosting (GB), random forest (RF), and a validated ensemble algorithm (AutoPrognosis) were built to predict graft failure by 6 years postoperatively. Validated performance metrics and feature importance measures were used to evaluate model performance. Results: The cohort included 960 patients who completed 6-year follow-up, with 5.7% (n = 55) experiencing graft failure. AutoPrognosis demonstrated the highest discriminative power (model area under the receiver operating characteristic curve: AutoPrognosis, 0.703; RF, 0.618; GB, 0.660; XGBoost, 0.680; LR, 0.592), with well-calibrated scores (model Brier score: AutoPrognosis, 0.053; RF, 0.054; GB, 0.057; XGBoost, 0.058; LR, 0.111). The most important features for AutoPrognosis model performance were prior compromised femoral and tibial tunnels (placement and size) and allograft graft type used in current rACLR. Conclusion: The present study demonstrated the ability of the novel AutoPrognosis machine learning model to best predict the risk of graft failure in patients undergoing rACLR at 6 years postoperatively with moderate predictive ability. Femoral and tibial tunnel size and position in prior ACLR and allograft use in current rACLR were all risk factors for rACLR failure in the context of the AutoPrognosis model. This study describes a unique model that can be externally validated with larger data sets and contribute toward the creation of a robust rACLR bedside risk calculator in future studies. Registration: NCT00625885 (ClinicalTrials.gov identifier).

Background: Revision anterior cruciate ligament (ACL) reconstruction has been documented to have inferior outcomes compared with primary ACL reconstruction. The reasons why remain unknown. Purpose: To determine whether surgical factors performed at the time of revision ACL reconstruction can influence a patient’s outcome at 6-year follow-up. Study Design: Cohort study; Level of evidence, 2. Methods: Patients who underwent revision ACL reconstruction were identified and prospectively enrolled between 2006 and 2011. Data collected included baseline patient characteristics, surgical technique and pathology, and a series of validated patient-reported outcome instruments: Knee injury and Osteoarthritis Outcome Score (KOOS), International Knee Documentation Committee (IKDC) subjective form, Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), and Marx activity rating score. Patients were followed up for 6 years and asked to complete the identical set of outcome instruments. Regression analysis was used to control for baseline patient characteristics and surgical variables to assess the surgical risk factors for clinical outcomes 6 years after surgery. Results: A total of 1234 patients were enrolled (716 men, 58%; median age, 26 years), and 6-year follow-up was obtained on 79% of patients (980/1234). Using an interference screw for femoral fixation compared with a cross-pin resulted in significantly better outcomes in 6-year IKDC scores (odds ratio [OR], 2.2; 95% CI, 1.2-3.9; P = .008) and KOOS sports/recreation and quality of life subscale scores (OR range, 2.2-2.7; 95% CI, 1.2-4.8; P < .01). Use of an interference screw compared with a cross-pin resulted in a 2.6 times less likely chance of having a subsequent surgery within 6 years. Use of an interference screw for tibial fixation compared with any combination of tibial fixation techniques resulted in significantly improved scores for IKDC (OR, 1.96; 95% CI, 1.3-2.9; P = .001); KOOS pain, activities of daily living, and sports/recreation subscales (OR range, 1.5-1.6; 95% CI, 1.0-2.4; P < .05); and WOMAC pain and activities of daily living subscales (OR range, 1.5-1.8; 95% CI, 1.0-2.7; P < .05). Use of a transtibial surgical approach compared with an anteromedial portal approach resulted in significantly improved KOOS pain and quality of life subscale scores at 6 years (OR, 1.5; 95% CI, 1.02-2.2; P≤ .04). Conclusion: There are surgical variables at the time of ACL revision that can modify clinical outcomes at 6 years. Opting for a transtibial surgical approach and choosing an interference screw for femoral and tibial fixation improved patients’ odds of having a significantly better 6-year clinical outcome in this cohort.