Revision Soft-Tissue Allograft Anterior Cruciate Ligament Reconstruction Is Associated With Lower Patient-Reported Outcomes Compared With Primary Anterior Cruciate Ligament Reconstruction in Patients Aged 40 and Older.

PURPOSE: To evaluate patient-reported outcomes (PROs) and graft failure rates in revision allograft anterior cruciate ligament reconstruction (ACLR) in patients aged 40 and older and compare them with primary ACLRs. METHODS: Patients aged 40 and older who underwent arthroscopic soft-tissue allograft ACLR between 2005 and 2016 with a minimum 2-year follow-up were retrospectively reviewed. Patients were grouped based on revision versus primary ACLR. The rate of achieving an International Knee Documentation Committee (IKDC) patient acceptable symptom state (PASS) score was recorded. Patient satisfaction, PROs, and graft failure were compared between groups using the χ2 test, Fisher exact test, and Mann-Whitney U test. RESULTS: We identified 32 patients who underwent revision ACLR and 201 patients who underwent primary ACLR aged 40 and older who met inclusion criteria with a mean follow-up of 6.2 and 6.9 years, respectively (P = .042). There was a lower rate of concomitant meniscal repair in the primary ACLR group (6% vs 21.9%, P = .007) There were no other differences in chondral injuries, mechanism of injury, or meniscal injuries between groups. The median IKDC score was greater in the primary ACLR group as compared with the revision ACLR group (83.9 vs 70.6, P < .001). Patients who underwent revision ACLR were less likely to achieve the IKDC PASS threshold (82.5% vs 56.3%, P = .001) and were less likely to report satisfaction as compared with patients who underwent primary ACLR (90.5% vs 78.1%, P =.038). No difference in graft failure rates was identified between groups (8% vs 15.6%, P = .180). CONCLUSIONS: Revision allograft ACLR in patients aged 40 and older was associated with lower PROs compared with primary ACLR. Patients who underwent revision ACLR failed to meet the IKDC PASS threshold more often and were dissatisfied with procedure results more than twice as often as patients that underwent primary ACLR. LEVEL OF EVIDENCE: III, retrospective cohort study.

High Levels of Satisfaction and Adequate Patient-Reported Outcomes After Operative Reconstruction of Multiligament Knee Injury With Allograft Among Patients Aged 40 Years and Older.

Purpose: To describe injury characteristics and patient-reported outcomes (PROs) among patients aged 40 years and older who underwent allograft reconstruction for multiligament knee injury (MLKI). Methods: Records of patients aged 40 years and older who underwent allograft multiligament knee reconstruction at a single institution between 2007 and 2017 with a minimum of 2 years of follow-up were retrospectively reviewed. Demographic information, concomitant injuries, patient satisfaction, and PROs including International Knee Documentation Committee and Marx activity scores were obtained. Results: Twelve patients were included with a minimum follow-up time of 2.3 years (mean, 6.1; range, 2.3-10.1 years) and a mean age at surgery of 49.8 years. Seven patients were male, and the most common mechanism of injury was sport-related. The most frequently reconstructed MLKIs were anterior cruciate ligament and medial collateral ligament (4), anterior cruciate ligament and posterolateral corner (2), and posterior cruciate ligament and posterolateral corner (2). The majority of patients reported satisfaction with their treatment (11). Median International Knee Documentation Committee and Marx scores were 73 (interquartile range, 45.5-88.0) and 3 (interquartile range 0-5), respectively. Conclusions: Patients aged 40 years and older can expect a high level of satisfaction and adequate PROs at 2-years follow-up after operative reconstruction for a MLKI with allograft. This demonstrates that allograft reconstruction for a MLKI in older patients may have clinical utility. Level of Evidence: IV, therapeutic case series.

Traditional Machine Learning Methods versus Deep Learning for Meningioma Classification, Grading, Outcome Prediction, and Segmentation: A Systematic Review and Meta-Analysis.

BACKGROUND: Meningiomas are common intracranial tumors. Machine learning (ML) algorithms are emerging to improve accuracy in 4 primary domains: classification, grading, outcome prediction, and segmentation. Such algorithms include both traditional approaches that rely on hand-crafted features and deep learning (DL) techniques that utilize automatic feature extraction. The aim of this study was to evaluate the performance of published traditional ML versus DL algorithms in classification, grading, outcome prediction, and segmentation of meningiomas. METHODS: A systematic review and meta-analysis were conducted. Major databases were searched through September 2021 for publications evaluating traditional ML versus DL models on meningioma management. Performance measures including pooled sensitivity, specificity, F1-score, area under the receiver-operating characteristic curve, positive and negative likelihood ratios (LR+, LR-) along with their respective 95% confidence intervals (95% CIs) were derived using random-effects models. RESULTS: Five hundred thirty-four records were screened, and 43 articles were included, regarding classification (3 articles), grading (29), outcome prediction (7), and segmentation (6) of meningiomas. Of the 29 studies that reported on grading, 10 could be meta-analyzed with 2 DL models (sensitivity 0.89, 95% CI: 0.74-0.96; specificity 0.91, 95% CI: 0.45-0.99; LR+ 10.1, 95% CI: 1.33-137; LR- 0.12, 95% CI: 0.04-0.59) and 8 traditional ML (sensitivity 0.74, 95% CI: 0.62-0.83; specificity 0.93, 95% CI: 0.79-0.98; LR+ 10.5, 95% CI: 2.91-39.5; and LR- 0.28, 95% CI: 0.17-0.49). The insufficient performance metrics reported precluded further statistical analysis of other performance metrics. CONCLUSIONS: ML on meningiomas is mostly carried out with traditional methods. For meningioma grading, traditional ML methods generally had a higher LR+, while DL models a lower LR-.