Krych, Aaron J

Purpose To (1) review definitions and concepts necessary to interpret applications of deep learning (DL; a domain of artificial intelligence that leverages neural networks to make predictions on media inputs such as images) and (2) identify knowledge and translational gaps in the literature to provide insight into specific areas for improvement as adoption of this technology continues. Methods A comprehensive search of the literature was performed in December 2023 for articles regarding the use of DL in sports medicine. For each study, information regarding the joint of focus, specific anatomic structure/pathology to which DL was applied, imaging modality utilized, source of images used for model training and testing, data set size, model performance, and whether the DL model was externally validated was recorded. A numerical scale was used to rate each DL model’s clinical impact, with 1 corresponding to proof‐of‐concept studies with little to no direct clinical impact and 5 corresponding to practice‐changing clinical impact and ready for clinical deployment. Results Fifty‐five studies were identified, all of which were published within the past 5 years, while 82% were published within the past 3 years. Of the DL models identified, 84% were developed for classification tasks, 9% for automated measurements, and 7% for segmentation. A total of 62% of studies utilized magnetic resonance imaging as the imaging modality, 25% radiographs, and 7% ultrasound, while 1 study each used computed tomography, arthroscopic images, or arthroscopic video. Sixty‐five percent of studies focused on the detection of tears (anterior cruciate ligament [ACL], rotator cuff [RC], and meniscus). The diagnostic performance of ACL tears, as determined by the area under the receiver operator curve (AUROC), ranged from 0.81 to 0.99 for ACL tears (excellent to near perfect), 0.83 to 0.94 for RC tears (excellent), and from 0.75 to 0.96 for meniscus tears (acceptable to excellent). In addition, 3 studies focused on detection of cartilage lesions had AUROC ranging from 0.90 to 0.92 (excellent performance). However, only 4 (7%) studies externally validated their models, suggesting that they may not be generalizable or may not perform well when applied to populations other than that used to develop the model. Finally, the mean clinical impact score was 2 (range, 1‐3) on scale of 1 to 5, corresponding to limited clinical applicability. Conclusions DL models in orthopaedic sports medicine show generally excellent performance (high internal validity) but require external validation to facilitate clinical deployment. In addition, current models have low clinical applicability and fail to advance the field due to a focus on routine tasks and a narrow conceptual framework. Level of Evidence Level IV, scoping review of Level I to IV studies.

Background: Matrix-induced autologous chondrocyte implantation (MACI) is an established cell-based therapy for the treatment of chondral defects of the knee. As long-term outcomes are now being reported in the literature, it is important to systematically review available evidence to better inform clinical practice. Purpose: To report (1) subjective patient-reported outcomes (PROs) and (2) the rate of graft failure, reoperation, and progression to total knee arthroplasty (TKA) after undergoing MACI of the knee at a minimum 10-year follow-up. Study Design: Systematic review; Level of evidence, 4. Methods: A comprehensive search of Ovid MEDLINE and Epub Ahead of Print, In-Process & Other Non-Indexed Citations and Daily; Ovid Embase; Ovid Cochrane Central Register of Controlled Trials; Ovid Cochrane Database of Systematic Reviews; and Scopus from 2008 to September 15, 2022, was conducted in the English language. Study eligibility criteria included (1) full-text articles in the English language, (2) patients undergoing a MACI within the knee, (3) clinical outcomes reported, and (4) a minimum 10-year follow-up. Results: In total, 168 patients (99 male, 69 female; mean age, 37 years [range, 15-63 years]; mean body mass index, 26.2 [range, 18.6-39.4]) representing 188 treated chondral defects at a minimum 10-year follow-up after MACI were included in this review. Significant and durable long-term improvements were observed across multiple PRO measures. Follow-up magnetic resonance imaging (MRI), when performed, also demonstrated satisfactory defect fill and an intact graft in the majority of patients. The all-cause reoperation rate was 9.0%, with an overall 7.4% rate of progression to TKA at 10 to 17 years of follow-up. Conclusion: At a minimum 10-year follow-up, patients undergoing MACI for knee chondral defects demonstrated significant and durable improvements in PROs, satisfactory defect fill on MRI-based assessment, and low rates of reoperation and TKA. These data support the use of MACI as a long-term treatment of focal cartilage defects of the knee.

Background: Wrestling is a physically demanding sport with young athletes prone to traumatic shoulder instability and a paucity of data evaluating the results of shoulder instability surgery (SIS). Purpose: To assess reoperation rates, patient-reported outcomes, and return to wrestling (RTW) after SIS in a cohort of competitive wrestlers. Study Design: Case series; Level of evidence, 3. Methods: All competitive wrestlers with a history of shoulder instability and subsequent surgery at a single institution between 1996 and 2020 were identified. All directions of shoulder instability (anterior shoulder instability [ASI], posterior shoulder instability [PSI], and traumatic multidirectional shoulder instability [TMDI]) were analyzed. Exclusions included revision SIS and <2 years of follow-up. Athletes were contacted for determination of complications, RTW, and Western Ontario Shoulder Instability Index scores. Results: Ultimately, 104 wrestlers were included with a mean age at initial instability of 16.9 years (range, 12.0-22.7 years), mean age at surgery of 18.9 years (range, 14.0-29.0 years), and a mean follow-up of 5.2 years (range, 2.0-22.0 years). A total of 58 (55.8%) wrestlers were evaluated after a single shoulder instability event, while 46 (44.2%) sustained multiple events before evaluation. ASI was the most common direction (n = 79; 76.0%), followed by PSI (n = 14; 13.5%) and TMDI (n = 11; 10.6%). Surgical treatment was most commonly an arthroscopic soft tissue stabilization (n = 88; 84.6%), with open soft tissue repair (n = 13; 12.5%) and open bony augmentation (n = 3; 2.9%) performed less frequently. RTW occurred in 57.3% of wrestlers at a mean of 9.8 months. Recurrent instability was the most common complication, occurring in 18 (17.3%) wrestlers. Revision SIS was performed in 15 (14.4%) wrestlers. Across the entire cohort, survivorship rates free from recurrent instability and revision surgery were 90.4% and 92.5% at 2 years, 71.9% and 70.7% at 5 years, and 71.9% and 66.5% at 10 years, respectively. Preoperative recurrent instability was an independent risk factor for postoperative recurrent instability (hazard ratio, 3.8; 95% CI, 1.33-11.03; P = .012). Conclusion: Competitive wrestlers with multiple dislocations before initial clinical evaluation were 3.8 times more likely to experience postoperative recurrent instability. Patients should be counseled that despite SIS, only 57.3% returned to wrestling after surgery.

Background: Fresh-frozen allografts are the current standard in meniscal allograft transplant (MAT) surgery, due to their availability, ease of preservation, and affordability. However, fresh-frozen grafts are associated with several clinical challenges such as graft shrinkage and extrusion, among many others. Purpose: To present the current knowledge on the use of fresh meniscal allografts, presenting whether benefits associated with fresh grafts provide sufficient evidence to support their use in clinical practice. Study Design: Systematic review; Level of evidence, 5. Methods: A comprehensive search was conducted with keywords listed below. After an initial screening on title and abstract, full-text articles were assessed with the inclusion criteria. Results: A total of 78 studies matched the inclusion criteria. Literature and preclinical studies indicated that fresh meniscal allografts are beneficial for maintaining mechanical properties, graft ultrastructure, and matrix metabolism due to the presence of viable cells. Therefore, fresh allografts may address common complications associated with fresh-frozen MAT. To overcome challenges associated with both fresh-frozen and fresh allografts, a group has studied treating fresh-frozen allografts with a cell-based injection therapy. Conclusion: Fresh meniscal allografts pose several challenges including limited availability, demanding preservation procedures, and high costs. Although the role of viable cells within meniscal allografts remains controversial, these cells may be vital for maintaining tissue properties.

Case: A 29-year-old man sustained a bilateral acute patellar tendon rupture (PTR) while jumping on a trampoline. He was initially treated with bilateral transosseous patellar tendon repairs. Bilateral rerupture occurred during a fall 10 weeks after. He subsequently underwent staged bilateral patellar tendon reconstructions using an Achilles tendon allograft. At 3-year follow-up, he has maintained full range of motion and leg strength without rerupture or other complications. Conclusion: The use of Achilles tendon allograft in the presence of inadequate and poor-quality tendon tissue for reconstruction of the patellar tendon in the revision setting is a viable and effective treatment option.

Background: Meniscal allograft transplantation (MAT) is an accepted and effective treatment option in the context of unsalvageable menisci, particularly in young and active patients. It has been shown to reduce pain and improve knee function in previously symptomatic patients. However, there is still limited knowledge about the long-term survival rates of allografts, the durability of clinical results, and the influence of patient-specific parameters, such as leg alignment, tibial slope, and preoperative International Cartilage Regeneration & Joint Preservation Society (ICRS) grade. Purpose: To determine (1) the long-term clinical success rate after MAT with bony fixation in a large, single-center cohort of consecutive patients, and (2) if patient-specific and procedural variables influence the clinical, anatomic, and subjective outcomes and risk of failure. Study Design: Case-control study; Level of evidence, 3. Methods: Data on 185 consecutive knees undergoing MAT in a single institution were prospectively collected and screened for inclusion in this study. The minimum follow-up time was 2 years. Radiographic variables (ICRS grade and Kellgren-Lawrence grade) were assessed preoperatively and at follow-up. Subjective patient-reported outcome measures (PROMs) (Lysholm score, Knee injury and Osteoarthritis Outcome Score [KOOS] including subscores, International Knee Documentation Committee [IKDC] score, and visual analog scale [VAS] score) were collected preoperatively and at follow-up. Clinical failure was defined as revision surgery due to graft failure or conversion to total knee arthroplasty. Anatomic failure was considered a tear covering >20% of the allograft, any peripheral tear, and unstable peripheral fixation leading to dislocation of the graft. Subjective failure was defined as Lysholm score ≤65. Preoperative tibial slope and leg alignment were assessed. Survival analyses were performed using the Kaplan-Meier estimate. Univariate and multivariate analyses were performed to determine risk factors for clinical and anatomic failure. Results: A total of 157 knees met inclusion criteria. After a mean follow-up time of 7 ± 3.5 years, 127 (80.9%) knees were free of clinical, anatomic, and subjective failure. Fourteen (8.9%) knees experienced clinical failure, 26 (16.6%) knees were identified as having experienced anatomic failure, and 13 (8.3%) patients experienced subjective failure with a reported Lysholm score of ≤65 at a mean follow-up of 7 years. Concurrent osteochondral allograft transplantation was identified as a predictor of both clinical (hazard ratio [HR], 4.55; 95% CI, 1.46-14.17; P = .009) and anatomic (HR, 3.05; 95% CI, 1.34-6.92; P = .008) failure. Cartilage damage of ICRS grade 3 or 4 of the index compartment conveyed an increased risk for clinical (HR, 3.41; 95% CI, 1.05-11.01; P = .04) and anatomic (HR, 3.04; 95% CI, 1.31-7.11; P = .01) failure. High-grade cartilage damage preoperatively (HR, 10.67; 95% CI, 1.037-109.768; P = .046), patient age >25 years (HR, 5.44; 95% CI, 0.120-246.070; P = .384), and a body mass index >30 (HR, 2.24; 95% CI, 0.748-6.705; P = .149) were associated with subjective failure. PROMs including KOOS and IKDC were significantly improved at final follow-up compared with preoperative scores across all measurements ( P < .005). Conclusion: MAT showed good to excellent clinical results at a mean follow-up of 7 years. Low ICRS lesion grade was associated with a higher clinical and anatomic survival rate. Patients with concurrent OCA transplantation are at a higher risk of clinical and anatomic failure, but still report significantly improved PROMs. These results suggest that MAT has a lasting beneficial effect both in isolation and in complex cases with ≥1 concurrent procedures.

Abstract Capsular management in hip arthroscopy has recently become a popular topic in the literature. Various approaches have been developed around the critical balance between safe and satisfactory exposure while maintaining hip joint stability and the restoration of capsular integrity at the conclusion of the case. Advocates for capsular closure recognize the role of the capsule in providing hip joint stability and aim to reestablish normal hip biomechanics through capsule preservation. Several recent studies have also shown capsular management strategies to influence both clinical outcomes and risk of revision surgery. We present an effective method for capsular management in hip arthroscopy that consistently allows excellent exposure and working space while allowing for facile, anatomic closure. Technique Video video See video under supplementary data.

Purpose To compare the cost‐effectiveness of an initial trial of nonoperative treatment to that of early arthroscopic debridement for stable osteochondritis dissecans (OCD) lesions of the capitellum. Methods A Markov Chain Monte Carlo probabilistic model was developed to evaluate the outcomes and costs of 1,000 simulated patients undergoing nonoperative management versus early arthroscopic debridement for stable OCD lesions of the capitellum. Health utility values, treatment success rates, and transition probabilities were derived from the published literature. Costs were determined on the basis of the typical patient undergoing each treatment strategy at our institution. Outcome measures included costs, quality‐adjusted life‐years (QALYs), and the incremental cost‐effectiveness ratio (ICER). Results Mean total costs resulting from nonoperative management and early arthroscopic debridement were $5,330 and $21,672, respectively. On average, early arthroscopic debridement produced an additional 0.64 QALYS, resulting in an ICER of $25,245/QALY, which falls well below the widely accepted $50,000 willingness‐to‐pay (WTP) threshold. Overall, early arthroscopic debridement was determined to be the preferred cost‐effective strategy in 69% of patients included in the microsimulation model. Conclusions Results of the Monte Carlo microsimulation and probabilistic sensitivity analysis demonstrated early arthroscopic debridement to be a cost‐effective treatment strategy for the majority of stable OCD lesions of the capitellum. Although early arthroscopic debridement was associated with higher total costs, the increase in QALYS that resulted from early surgery was enough to justify the cost difference based on an ICER substantially below the $50,000 WTP threshold. Level of Evidence Level III, economic computer simulation model.

Purpose To perform a systematic review of the literature to evaluate (1) activity level and knee function, (2) reoperation and failure rates, and (3) risk factors for reoperation and failure of autologous osteochondral transfer (AOT) at long‐term follow‐up. Methods A comprehensive review of the long‐term outcomes of AOT was performed. Studies reported on activity‐based outcomes (Tegner Activity Scale) and clinical outcomes (Lysholm score and International Knee Documentation Committee score). Reoperation and failure rates as defined by the publishing authors were recorded for each study. Modified Coleman Methodology Scores were calculated to assess study methodological quality. Results Twelve studies with a total of 495 patients and an average age of 32.5 years at the time of surgery and a mean follow‐up of 15.1 years (range, 10.4‐18.0 years) were included. The mean defect size was 3.2 cm 2 (range, 1.9‐6.9 cm 2 ). The mean duration of symptoms before surgery was 5.1 years. Return to sport rates ranged from 86% to 100%. Conversion to arthroplasty rates ranged from 0% to 16%. The average preoperative International Knee Documentation Committee scores ranged from 32.9 to 36.8, and the average postoperative International Knee Documentation Committee scores at final follow‐up ranged from 66.3 to 77.3. The average preoperative Lysholm scores ranged from 44.5 to 56.0 and the average postoperative Lysholm scores ranged from 70.0 to 96.5. The average preoperative Tegner scores ranged from 2.5 to 3.0, and the average postoperative scores ranged from 4.1 to 7.0. Conclusions AOT of the knee resulted in high rates of return to sport with correspondingly low rates of conversion to arthroplasty at long‐term follow‐up. In addition, AOT demonstrated significant improvements in long‐term patient‐reported outcomes from baseline. Level of Evidence Level IV, systematic review of Level I‐IV studies.

Abstract Iliopsoas tendinitis following total hip arthroplasty has been linked to retroverted acetabular cup position with associated anterior overhang. For severely malpositioned components, preferred treatment is in the form of revision arthroplasty. However, for a substantial number of cases, iliopsoas tendinitis as well as associated pain and disability are observed in the presence of modest acetabular overhang. In such cases, patients may benefit substantially from arthroscopic iliopsoas fractional lengthening. Given altered postarthroplasty anatomy, we present an arthroscopic approach employing an iliopsoas air bursogram. In such a way, safe and predictable access can be provided for efficient tendon lengthening without capsular violation or inadvertent instrumentation of the nearby medial neurovascular bundle. Technique Video video See video under supplementary data.