Vasavada, Kinjal

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: The use of telerehabilitation after sports medicine procedures such as an arthroscopic rotator cuff repair (ARCR) and anterior cruciate ligament reconstruction (ACLR) has rapidly increased in recent years; however, the functional outcomes and patient satisfaction with telerehabilitation compared to in-person rehabilitation remain unclear. The purpose of this study was to compare the functional outcomes and patient satisfaction with telerehabilitation to in-person rehabilitation in a randomized controlled trial after two common sports procedures, ARCR and ACLR. Methods: Two randomized controlled trials were conducted involving patients scheduled to undergo ARCR or ACLR by one of six fellowship-trained sports medicine surgeons between October 2020 and November 2021. Each trial had an enrollment goal of 60 patients. Subjects were randomized 1:1 to receive telerehabilitation or in-person rehabilitation postoperatively. Functional outcome and satisfaction metrics were collected at baseline and at post-operative visits and compared between groups. Results: In total, 16 ACLR patients were enrolled, of whom 10 (62.5%) were assigned to in-person rehabilitation and 6 (37.5%) to telerehabilitation. Additionally, 32 ARCR patients were enrolled, of whom 20 (62.5%) were assigned in-person rehabilitation and 12 (37.5%) were assigned telerehabilitation. In total, of the 30 patients assigned to in-person rehabilitation, none reported a crossover to telerehabilitation. Of the 18 patients initially assigned to telerehabilitation, 12 (67%) completed the final follow-up survey, of which 11 (92%) reported a crossover; 9 patients completed in-person rehabilitation and 2 patients completed hybrid in-person and telerehabilitation. Conclusions: Patients preferred in-person rehabilitation compared to telerehabilitation after ACLR and ARCR, as evidenced by the nearly ubiquitous crossover from telerehabilitation to in-person rehabilitation in both studies. Our findings suggest that telerehabilitation protocols still need to be perfected, and that there may be a role for a hybrid in-person and tele-rehab model.