Ranawat, Anil S.

Background: Adequate cam resection during hip arthroscopy for femoroacetabular impingement syndrome (FAIS) is necessary to restore femoral head-neck offset while avoiding under- or over-resection. The relationship between the extent of femoroplasty and postoperative patient-reported outcomes remains unclear. Purpose: We sought to answer the following questions: What is the association between the extent of cam femoroplasty resection and postoperative improvements? and is a 5% resection threshold associated with improved outcomes? Methods: We conducted a retrospective review of patients with adequate acetabular coverage who underwent primary hip arthroscopy with femoroplasty between January 2015 and December 2022 at our institution and had preoperative and 1- and/or 2-year postoperative modified Harris hip score (mHHS) and/or International Hip Outcome Tool (iHOT) scores. We included 400 patients (409 hips; ages 14–50 years). Outcomes included score changes and achievement of minimum clinically important difference (MCID) and substantial clinical benefit (SCB). Postoperative Dunn lateral radiographs quantified femoroplasty by resection depth percentage (resection depth/femoral head diameter), proximal resection angle, and postoperative α angle. Hips were classified as under-resection, neutral (0%–5%), or over-resection (>5%), and differences in outcomes were compared between resection groups. Multivariable regression analyses controlled for demographic, radiographic, and surgical variables. Results: Mean resection depth was 4.8%; mean proximal resection angle was 72.6°. No differences were observed in score improvements or MCID/SCB rates between groups with under-resection versus over-resection at 1 or 2 years. Greater resection depth was associated with larger 1-year mHHS and iHOT improvements and independently predicted 1-year iHOT MCID and SCB. Higher proximal resection angle predicted 2-year iHOT MCID. Conclusion: In this retrospective, single-institution cohort study, we found that in patients with FAIS, greater femoroplasty depth was associated with improved 1-year clinical outcomes. Level of Evidence: Level III, retrospective cohort study.

Background: Assessment of orthopaedic surgery trainees is traditionally based on subjective evaluation by faculty. The recent push for value-based health care has placed a premium on improving patient outcomes. As a result, surgical training evaluations for orthopaedic trainees are evolving to include more objective measures to evaluate competency. Purpose: To develop and subsequently demonstrate the efficacy of a novel surgical skills assessment for orthopaedic sports medicine fellows. Study Design: Case series; Level of evidence, 4. Methods: A team of 14 fellowship-trained orthopaedic sports medicine surgeons developed objective scoring rubrics for anterior cruciate ligament reconstruction (ACLR) and rotator cuff repair (RCR) using a modified Delphi process. Rubrics were designed based on 10 surgical steps with a grading scale (1-5) based on core competencies with a maximum summative score of 50. Fourteen orthopaedic fellows across a regionally diverse group of sports medicine–accredited fellowship programs were invited to complete both an ACLR and RCR in a surgical skills laboratory at the beginning and end of their fellowship year. Individual surgical steps, overall performance, and total procedure time were evaluated by a single sports medicine surgeon for both sessions. Results: Thirteen of 14 fellows completed both pre- and post-fellowship assessments. For the ACLR procedure, the pre-fellowship mean summative score was 25.4 (SD, 4.4) and the post-fellowship mean summative score was 38.6 (SD, 4.1), which was a statistically significant improvement ( P < .001). For the RCR procedure, the pre-fellowship mean summative score was 26.6 (SD, 5.4) and the post-fellowship mean summative score was 38.8 (SD, 4.3), which was also a statistically significant improvement ( P < .001). The mean time to completion for the ACLR procedure was 82.3 minutes (SD, 4.3 minutes) pre-fellowship, which improved to 69.7 minutes (SD, 11.6 minutes) post-fellowship ( P = .002). The mean time to completion for the RCR procedure was 85.5 minutes (SD, 5.0 minutes) pre-fellowship, which improved to 76.4 minutes (SD, 7.0 minutes) post-fellowship ( P < .001). Conclusion: This surgical skills program represents the first standardized and reproducible instrument for the evaluation of 2 arthroscopic sports medicine procedures in the United States. Orthopaedic sports medicine fellows improved significantly in aggregate over their fellowship year with regard to the ACLR and RCR. The described program has the potential to serve as both a training tool and formal orthopaedic sports medicine fellow assessment.

Purpose To develop a deep learning model for the detection of Segond fractures on anteroposterior (AP) knee radiographs and to compare model performance to that of trained human experts. Methods AP knee radiographs were retrieved from the Hospital for Special Surgery ACL Registry, which enrolled patients between 2009 and 2013. All images corresponded to patients who underwent anterior cruciate ligament reconstruction by 1 of 23 surgeons included in the registry data. Images were categorized into 1 of 2 classes based on radiographic evidence of a Segond fracture and manually annotated. Seventy percent of the images were used to populate the training set, while 20% and 10% were reserved for the validation and test sets, respectively. Images from the test set were used to compare model performance to that of expert human observers, including an orthopaedic surgery sports medicine fellow and a fellowship‐trained orthopaedic sports medicine surgeon with over 10 years of experience. Results A total of 324 AP knee radiographs were retrieved, of which 34 (10.4%) images demonstrated evidence of a Segond fracture. The overall mean average precision (mAP) was 0.985, and this was maintained on the Segond fracture class (mAP = 0.978, precision = 0.844, recall = 1). The model demonstrated 100% accuracy with perfect sensitivity and specificity when applied to the independent testing set and the ability to meet or exceed human sensitivity and specificity in all cases. Compared to an orthopaedic surgery sports medicine fellow, the model required 0.3% of the total time needed to evaluate and classify images in the independent test set. Conclusions A deep learning model was developed and internally validated for Segond fracture detection on AP radiographs and demonstrated perfect accuracy, sensitivity, and specificity on a small test set of radiographs with and without Segond fractures. The model demonstrated superior performance compared with expert human observers. Clinical Relevance Deep learning can be used for automated Segond fracture identification on radiographs, leading to improved diagnosis of easily missed concomitant injuries, including lateral meniscus tears. Automated identification of Segond fractures can also enable large‐scale studies on the incidence and clinical significance of these fractures, which may lead to improved management and outcomes for patients with knee injuries.

AbstractDeep learning is a subset of artificial intelligence (AI) with enormous potential to transform orthopaedic surgery. As has already become evident with the deployment of Large Language Models (LLMs) like ChatGPT (OpenAI Inc.), deep learning can rapidly enter clinical and surgical practices. As such, it is imperative that orthopaedic surgeons acquire a deeper understanding of the technical terminology, capabilities and limitations associated with deep learning models. The focus of this series thus far has been providing surgeons with an overview of the steps needed to implement a deep learning‐based pipeline, emphasizing some of the important technical details for surgeons to understand as they encounter, evaluate or lead deep learning projects. However, this series would be remiss without providing practical examples of how deep learning models have begun to be deployed and highlighting the areas where the authors feel deep learning may have the most profound potential. While computer vision applications of deep learning were the focus of Parts I and II, due to the enormous impact that natural language processing (NLP) has had in recent months, NLP‐based deep learning models are also discussed in this final part of the series. In this review, three applications that the authors believe can be impacted the most by deep learning but with which many surgeons may not be familiar are discussed: (1) registry construction, (2) diagnostic AI and (3) data privacy. Deep learning‐based registry construction will be essential for the development of more impactful clinical applications, with diagnostic AI being one of those applications likely to augment clinical decision‐making in the near future. As the applications of deep learning continue to grow, the protection of patient information will become increasingly essential; as such, applications of deep learning to enhance data privacy are likely to become more important than ever before.Level of Evidence: Level IV.

AbstractDeep learning has a profound impact on daily life. As Orthopedics makes use of this rapid escalation in technology, Orthopedic surgeons will need to take leadership roles on deep learning projects. Moreover, surgeons must possess an understanding of what is necessary to design and implement deep learning‐based project pipelines. This review provides a practical guide for the Orthopedic surgeon to understand the steps needed to design, develop, and deploy a deep learning pipeline for clinical applications. A detailed description of the processes involved in defining the problem, building the team, acquiring and curating the data, labeling the data, establishing the ground truth, pre‐processing and augmenting the data, and selecting the required hardware is provided. In addition, an overview of unique considerations involved in the training and evaluation of deep learning models is provided. This review strives to provide surgeons with the groundwork needed to identify gaps in the clinical landscape that deep learning models may be able to fill and equips them with the knowledge needed to lead an interdisciplinary team through the process of creating novel deep‐learning‐based solutions to fill those gaps.

Background: Although restricted hip range of motion (ROM) is associated with an increased risk for injuries in baseball players, the evolution of hip ROM over the season remains undefined. Hypothesis: Hip ROM profiles would be symmetric between hips and positions (pitchers vs position players) but would decrease from preseason to postseason. Additionally, it was hypothesized that this decrease in motion would correlate with workload. Study Design: Cohort study; Level of evidence, 2. Methods: Bilateral hip ROM was assessed in 96 professional baseball players (54 pitchers, 42 position players) preseason and postseason. ROM comparisons were made between lead and trailing hips, pitchers and position players, and preseason and postseason measures. The change from preseason to postseason was correlated with player demographics and measures of workload for pitchers and position players. Results: Preseason hip ROM was symmetric between hips; however, pitchers demonstrated increased preseason lead hip internal rotation (IR) ( P = .018) and bilateral hip total ROM (TROM) ( P < .020) compared with position players. From preseason to postseason, position players lost 7° of external rotation (ER) ( P ≤ .005 ). In pitchers, the loss of IR correlated with increased pitches ( P = .016) and innings ( P = .037), while the loss of ER ( P = .005 ) and TROM ( P = .014) correlated with increasing mean fastball velocity. Workload for position players did not correlate with motion loss. Conclusion: Symmetric hip ROM profiles should be anticipated in baseball players; however, pitchers may have increased preseason IR and TROM and postseason ER and TROM relative to position players. Although loss of motion correlated with workload in pitchers, this was not the case for position players. Hip motion should be monitored over the course of the season. This is particularly true for pitchers who lose IR as workload increases, which may place them at a greater risk for injuries.

Purpose To evaluate the association of preoperative intra‐articular hip injection with surgical site infection after hip arthroscopy. Methods A large administrative database was used to identify all patients undergoing hip arthroscopy from 2007 to 2015 within a single private insurer and from 2005 to 2012 within Medicare in the United States. Those that received an ipsilateral preoperative intra‐articular hip injection were identified. The patients were then divided into the following groups based on the interval between preoperative injection and ipsilateral hip arthroscopy: (1) <3 months, (2) 3 to 6 months, and (3) 6 to 12 months. These groups were compared to a control group composed of patients with no history or a remote history (>12 months) of preoperative hip injection. Patients developing a surgical site infection within 6 months following hip arthroscopy were identified using International Classification of Diseases, Ninth Revision, and Current Procedural Terminology codes associated with infection. Groups were compared using a multivariate logistic regression analysis to control for age, gender, body mass index, smoking status, alcohol usage, and multiple medical comorbidities including diabetes mellitus, hemodialysis use, inflammatory arthritis, and peripheral vascular disease. Results In total, 19% of privately insured and 6% of Medicare patients received a hip injection within 12 months of hip arthroscopy. The overall infection rate in privately insured and Medicare patients was 1.19% and 1.10%, respectively. Preoperative hip injection within 3 months of surgery was associated with a significantly higher risk of postoperative infection versus controls (2.16%, odds ratio [OR] 6.1, P < .001, for privately insured group; 2.80%, OR 1.99, P = .037, for Medicare group). In contrast, preoperative hip injection given after more than 3 months of surgery was not associated with an increased risk of postoperative infection versus controls. Conclusions Risk of infection after hip arthroscopy increased when preoperative intra‐articular hip injections were given within 3 months of surgery. Level of Evidence Level III, retrospective comparative study.