Fu, Michael C.

Purpose To assess the ability of ChatGPT‐4, an automated Chatbot powered by artificial intelligence, to answer common patient questions concerning the Latarjet procedure for patients with anterior shoulder instability and compare this performance with Google Search Engine. Methods Using previously validated methods, a Google search was first performed using the query “Latarjet.” Subsequently, the top 10 frequently asked questions (FAQs) and associated sources were extracted. ChatGPT‐4 was then prompted to provide the top 10 FAQs and answers concerning the procedure. This process was repeated to identify additional FAQs requiring discrete‐numeric answers to allow for a comparison between ChatGPT‐4 and Google. Discrete, numeric answers were subsequently assessed for accuracy on the basis of the clinical judgment of 2 fellowship‐trained sports medicine surgeons who were blinded to search platform. Results Mean (± standard deviation) accuracy to numeric‐based answers was 2.9 ± 0.9 for ChatGPT‐4 versus 2.5 ± 1.4 for Google ( P = .65). ChatGPT‐4 derived information for answers only from academic sources, which was significantly different from Google Search Engine ( P = .003), which used only 30% academic sources and websites from individual surgeons (50%) and larger medical practices (20%). For general FAQs, 40% of FAQs were found to be identical when comparing ChatGPT‐4 and Google Search Engine. In terms of sources used to answer these questions, ChatGPT‐4 again used 100% academic resources, whereas Google Search Engine used 60% academic resources, 20% surgeon personal websites, and 20% medical practices ( P = .087). Conclusions ChatGPT‐4 demonstrated the ability to provide accurate and reliable information about the Latarjet procedure in response to patient queries, using multiple academic sources in all cases. This was in contrast to Google Search Engine, which more frequently used single‐surgeon and large medical practice websites. Despite differences in the resources accessed to perform information retrieval tasks, the clinical relevance and accuracy of information provided did not significantly differ between ChatGPT‐4 and Google Search Engine. Clinical Relevance Commercially available large language models (LLMs), such as ChatGPT‐4, can perform diverse information retrieval tasks on‐demand. An important medical information retrieval application for LLMs consists of the ability to provide comprehensive, relevant, and accurate information for various use cases such as investigation about a recently diagnosed medical condition or procedure. Understanding the performance and abilities of LLMs for use cases has important implications for deployment within health care settings.

AbstractPurposeRecovery following elective knee arthroscopy can be compromised by prolonged postoperative opioid utilization, yet an effective and validated risk calculator for this outcome remains elusive. The purpose of this study is to develop and validate a machine‐learning algorithm that can reliably and effectively predict prolonged opioid consumption in patients following elective knee arthroscopy.MethodsA retrospective review of an institutional outcome database was performed at a tertiary academic medical centre to identify adult patients who underwent knee arthroscopy between 2016 and 2018. Extended postoperative opioid consumption was defined as opioid consumption at least 150 days following surgery. Five machine‐learning algorithms were assessed for the ability to predict this outcome. Performances of the algorithms were assessed through discrimination, calibration, and decision curve analysis.ResultsOverall, of the 381 patients included, 60 (20.3%) demonstrated sustained postoperative opioid consumption. The factors determined for prediction of prolonged postoperative opioid prescriptions were reduced preoperative scores on the following patient‐reported outcomes: the IKDC, KOOS ADL, VR12 MCS, KOOS pain, and KOOS Sport and Activities. The ensemble model achieved the best performance based on discrimination (AUC = 0.74), calibration, and decision curve analysis. This model was integrated into a web‐based open‐access application able to provide both predictions and explanations.ConclusionFollowing appropriate external validation, the algorithm developed presently could augment timely identification of patients who are at risk of extended opioid use. Reduced scores on preoperative patient‐reported outcomes, symptom duration and perioperative oral morphine equivalents were identified as novel predictors of prolonged postoperative opioid use. The predictive model can be easily deployed in the clinical setting to identify at risk patients thus allowing providers to optimize modifiable risk factors and appropriately counsel patients preoperatively.Level of evidenceIII.

Background: The medial ulnar collateral ligament (UCL) insertion of the elbow has been shown to extend distally beyond the sublime tubercle. The contribution to valgus stability of the distal aspect of the footprint is unknown. Purpose/Hypothesis: The purpose of this study was to determine the contribution of each part of the UCL footprint to the elbow valgus stability provided by the UCL. It was hypothesized that the distal two-thirds of the ulnar UCL footprint would not contribute significantly to valgus stability provided by the UCL. Study Design: Descriptive laboratory study. Methods: Fifteen cadaveric arms were dissected to the capsuloligamentous elbow structures and potted. A servohydraulic load frame was used to place 5 N·m of valgus stress on the intact elbow at 30°, 60°, 90°, and 120° of flexion. The UCL insertional footprint was measured and divided into thirds (proximal, middle, and distal). One-third of the UCL footprint was elevated off the bone (leaving the ligament in continuity), and the elbow was retested at the same degrees of flexion. This was repeated until the entire UCL footprint on the ulna was sectioned. Each elbow was randomized for how the UCL would be sectioned (sectioning the proximal, then middle, and then distal third or sectioning the distal, then middle, and then proximal third). Ulnohumeral joint gapping (millimeters) was recorded with a 3-dimensional motion capture system using physical and virtual markers. Two-group comparisons were made between each sectioned status versus the intact condition for each flexion angle. Results: When the UCL was sectioned from distal to proximal, none of the ligaments failed prior to complete sectioning. When the UCL was sectioned from proximal to distal, 3 of the 6 ligaments failed after sectioning of the proximal third, while 2 more failed after the proximal and middle thirds were sectioned. Of the specimens with the distal third of the ligament sectioned first, no significant differences were found between intact, distal third cut, and distal plus middle thirds cut at all flexion angles. Conclusion: The middle and distal thirds of the insertional footprint of the UCL on the ulna did not significantly contribute to gap resistance at 5 N·m of valgus load. The proximal third of the footprint is the primary resistor of valgus load. Clinical Relevance: This cadaveric biomechanical study demonstrated that the middle and distal thirds of the native UCL insertion onto the ulna did not significantly contribute to valgus resistance at the elbow. When a UCL reconstruction is performed, the proximal third of the UCL insertion may be the most clinically important portion of the ligament to reconstruct.