8 August 2023 in Knee Surgery, Sports Traumatology, Arthroscopy
Purpose: To investigate the potential use of large language models (LLMs) in orthopaedics by presenting queries pertinent to anterior cruciate ligament (ACL) surgery to generative pre‐trained transformer (ChatGPT, specifically using its GPT‐4 model of March 14th 2023). Additionally, this study aimed to evaluate the depth of the LLM’s knowledge and investigate its adaptability to different user groups. It was hypothesized that the ChatGPT would be able to adapt to different target groups due to its strong language understanding and processing capabilities.Methods: ChatGPT was presented with 20 questions and response was requested for two distinct target audiences: patients and non‐orthopaedic medical doctors. Two board‐certified orthopaedic sports medicine surgeons and two expert orthopaedic sports medicine surgeons independently evaluated the responses generated by ChatGPT. Mean correctness, completeness, and adaptability to the target audiences (patients and non‐orthopaedic medical doctors) were determined. A three‐point response scale facilitated nuanced assessment.Results: ChatGPT exhibited fair accuracy, with average correctness scores of 1.69 and 1.66 (on a scale from 0, incorrect, 1, partially correct, to 2, correct) for patients and medical doctors, respectively. Three of the 20 questions (15.0%) were deemed incorrect by any of the four orthopaedic sports medicine surgeon assessors. Moreover, overall completeness was calculated to be 1.51 and 1.64 for patients and medical doctors, respectively, while overall adaptiveness was determined to be 1.75 and 1.73 for patients and doctors, respectively.Conclusion: Overall, ChatGPT was successful in generating correct responses in approximately 65% of the cases related to ACL surgery. The findings of this study imply that LLMs offer potential as a supplementary tool for acquiring orthopaedic knowledge. However, although ChatGPT can provide guidance and effectively adapt to diverse target audiences, it cannot supplant the expertise of orthopaedic sports medicine surgeons in diagnostic and treatment planning endeavours due to its limited understanding of orthopaedic domains and its potential for erroneous responses.Level of evidence: V.
16 May 2018 in Journal of Bone and Joint Surgery
Background: The purpose of this study was to examine the relationship between distal femoral morphology and anterior cruciate ligament (ACL) injury, ACL reconstruction (ACLR) failure, and contralateral ACL injury. It was hypothesized that increased posterior femoral condylar depth, quantified as the lateral femoral condyle ratio, would correlate with increased risk of primary ACL injuries, ACLR failures, and contralateral ACL injuries. Methods: The charts of consecutive patients who underwent arthroscopic knee surgery at an academic medical center from 2012 to 2016 with minimum follow-up of 24 months were retrospectively reviewed. Patients were stratified into 4 groups: (1) a control group of patients with no ACL injury, (2) patients with primary ACL injury, (3) patients with failed ACLR, and (4) patients with previous ACL injury and subsequent contralateral ACL injury. With use of lateral radiographs, the ratio of posterior femoral condylar depth to total condylar length was defined as the lateral femoral condyle ratio. Differences between study groups were identified with use of analysis-of-variance (ANOVA) and post-hoc testing with significance set at p < 0.05. Receiver operating characteristic (ROC) curve analysis was performed to determine the optimal cutoff for detecting increased risk of ACL injury. Results: Two hundred patients met the inclusion criteria. The mean lateral femoral condyle ratios (and standard deviations) were 61.2% ± 2.4% in the control group, 64.2% ± 3.8% in the primary ACL injury group, 64.4% ± 3.6% in the failed ACLR group, and 66.9% ± 4.3% in the contralateral ACL injury group. Patients who had a primary ACL injury, failed ACLR, or contralateral ACL injury had significantly higher ratios compared with the control group (p < 0.008). ROC curve analysis demonstrated that a lateral femoral condyle ratio of >63% was associated with an increased risk for ACL injury, with a sensitivity of 77% and a specificity of 72%. Conclusions: The data from this study show that increased posterior femoral condylar depth, quantified as the lateral femoral condyle ratio, is associated with an increased risk of ACL injury, including primary and contralateral ACL injuries. The data from this study may help clinicians to identify patients at a greater risk of ACL injury. Level of Evidence: Prognostic Level III. See Instructions for Authors for a complete description of levels of evidence.
1 July 2017 in Orthopaedic Journal of Sports Medicine
Background: The prevalence of rotator cuff repair continues to rise, with a noted transition from open to arthroscopic techniques in recent years. One reported advantage of arthroscopic repair is a lower infection rate. However, to date, the infection rates of these 2 techniques have not been directly compared with large samples at a single institution with fully integrated medical records. Purpose: To retrospectively compare postoperative infection rates between arthroscopic and open rotator cuff repair. Study Design: Cohort study; Level of evidence, 3. Methods: From January 2003 until May 2011, a total of 1556 patients underwent rotator cuff repair at a single institution. These patients were divided into an arthroscopic repair group and an open group. A Pearson chi-square test and Fisher exact test were used, with a subgroup analysis to segment the open repair group into mini-open and open procedures. The odds ratio and 95% CI of developing a postoperative infection was calculated for the 2 groups. A multiple-regressions model was then utilized to identify predictors of the presence of infection. Infection was defined as only those treated with surgical intervention, thus excluding superficial infections treated with antibiotics alone. Results: A total of 903 patients had an arthroscopic repair, while 653 had open repairs (600 mini-open, 53 open). There were 4 confirmed infections in the arthroscopic group and 16 in the open group (15 mini-open, 1 open), resulting in postoperative infection rates of 0.44% and 2.45%, respectively. Subgroup analysis of the mini-open and open groups demonstrated a postoperative infection rate of 2.50% and 1.89%, respectively. The open group had an odds ratio of 5.645 (95% CI, 1.9-17.0) to develop a postoperative infection compared with the arthroscopic group. Conclusion: Patients undergoing open rotator cuff repair had a significantly higher rate of postoperative infection compared with those undergoing arthroscopic rotator cuff repair.
29 October 2018 in Knee Surgery, Sports Traumatology, Arthroscopy
22 February 2023 in Journal of Shoulder and Elbow Surgery
6 December 2022 in The American Journal of Sports Medicine
SCShaquille J.-C. Charles
+3
Background: The “distance to dislocation” (DTD) calculation has been proposed as 1 method to predict the risk of recurrent dislocation after arthroscopic Bankart repair for an “on-track” shoulder. Rates of recurrent dislocation at specific DTD values are unknown. Hypothesis: Among patients with “on-track” shoulder lesions who underwent primary arthroscopic Bankart repair, the rate of recurrent dislocation would increase as DTD values decrease. Study Design: Case-control study; Level of evidence, 3. Methods: We performed a retrospective analysis of 188 patients with “on-track” shoulder lesions who underwent primary arthroscopic anterior labral repair between 2007 and 2019, with a minimum 2-year follow-up. Glenoid bone loss, Hill-Sachs interval, glenoid track, and DTD were determined from preoperative magnetic resonance imaging scans. The rate of recurrent dislocation was determined at 2-mm DTD intervals. Univariate and multivariate regression analyses were used to evaluate the relationship between recurrent dislocation, patient characteristics, and bone loss variables. A multivariate regression model was created to predict the probability of failure at continuous DTD values. A subgroup analysis of failure rate based on collision sports participation was also performed. Results: A total of 29 patients (15.4%) sustained recurrent dislocations. Patient age ( P = .046), multiple dislocations ( P = .03), glenoid bone loss ( P < .001), Hill-Sachs interval length ( P < .001), and DTD ( P < .001) were all independent predictors of failure. As the DTD decreased, the rate of recurrent dislocation increased. Below a DTD threshold of 10 mm, the recurrent dislocation rate increased exponentially. Up to a threshold of 24 mm, the failure rate for collision athletes remained >12.3%, independent of the DTD. Conversely, the failure rate among noncollision athletes decreased steadily as the DTD increased. Conclusion: For “on-track” shoulder lesions, as the DTD approached 0 mm (“off-track” threshold), the risk of recurrent dislocation after arthroscopic Bankart repair increased significantly. Below a DTD threshold of 10 mm, the risk of failure increased exponentially. The risk of recurrent dislocation for collision sports athletes remained elevated at higher DTD values than for noncollision athletes.