Search

Introduction:. Publicly available AI language models such as ChatGPT have demonstrated utility in text generation and even problem-solving when provided with clear instructions. Amidst this transformative shift, the aim of this study is to assess ChatGPT's performance on the orthopaedic surgery in-training examination (OITE). Methods:. All 213 OITE 2021 web-based questions were retrieved from the AAOS-ResStudy website (https://www.aaos.org/education/examinations/ResStudy). Two independent reviewers copied and pasted the questions and response options into ChatGPT Plus (version 4.0) and recorded the generated answers. All media-containing questions were flagged and carefully examined. Twelve OITE media-containing questions that relied purely on images (clinical pictures, radiographs, MRIs, CT scans) and could not be rationalized from the clinical presentation were excluded. Cohen's Kappa coefficient was used to examine the agreement of ChatGPT-generated responses between reviewers. Descriptive statistics were used to summarize the performance (% correct) of ChatGPT Plus. The 2021 norm table was used to compare ChatGPT Plus' performance on the OITE to national orthopaedic surgery residents in that same year. Results:. A total of 201 questions were evaluated by ChatGPT Plus. Excellent agreement was observed between raters for the 201 ChatGPT-generated responses, with a Cohen's Kappa coefficient of 0.947. 45.8% (92/201) were media-containing questions. ChatGPT had an average overall score of 61.2% (123/201). Its score was 64.2% (70/109) on non-media questions. When compared to the performance of all national orthopaedic surgery residents in 2021, ChatGPT Plus performed at the level of an average PGY3. Discussion:. ChatGPT Plus is able to pass the OITE with an overall score of 61.2%, ranking at the level of a third-year orthopaedic surgery resident. It provided logical reasoning and justifications that may help residents improve their understanding of OITE cases and general orthopaedic principles. Further studies are still needed to examine their efficacy and impact on long-term learning and OITE/ABOS performance.

Background: The outcomes of total joint arthroplasty during the coronavirus disease 2019 (COVID-19) pandemic are unknown. We sought to compare early postoperative complications in total hip arthroplasty (THA) and total knee arthroplasty (TKA) prior to and during the COVID-19 pandemic. Methods: Patients in the American College of Surgeons National Surgical Quality Improvement Program database who had THA or TKA in the latter halves (July to December) of 2019 and 2020 were identified. Patients were divided into pre-COVID-19 (2019) and during-COVID-19 (2020) cohorts. Propensity score matching and logistic regression were used to detect correlations between operative period and outcomes. Statistical significance was set at α = 0.05. Results: A total of 38,234 THA and 61,956 TKA patients were included. There was a significantly higher rate of outpatient procedures in 2020 than that in 2019 for both THA (41.68% vs 6.59%, P < .001) and TKA (41.68% vs 7.56%, P < .001). On matched analysis, surgery in 2020 had lower odds of hospital stay for >1 day (THA: odds ratio [OR] 0.889; P < .001) (TKA: OR 0.644; P < .001) and nonhome discharge (THA: 0.655; P < .001) (TKA: 0.497; P < .001). There was also increased odds of superficial surgical site infection in THA (OR 1.272; P = .040) and myocardial infarction in TKA patients (OR 1.488; P = .042) in 2020 compared to those in 2019. There was no difference in the 15 other outcomes assessed. Conclusions: Total joint arthroplasty surgery remains safe despite the COVID-19 pandemic. A statistically significant increase was detected in superficial surgical site infection and myocardial infarction risk during 2020 compared to 2019; however, the clinical significance of this is questionable. A shift away from inpatient stay was also present, possibly reflecting efforts to minimize nosocomial exposure to COVID-19.

Abstract. Objectives:. To determine whether (1) early postoperative complications and (2) time to surgery for operative fixation of fractures distal to the knee differ for Black versus White patients and to assess whether disparities exist within fracture subtypes. Design:. Retrospective database review. Setting:. Hospitals participating in the American College of Surgeons National Surgical Quality Improvement Program database. Patients/Participants:. Patients (18 years or older) undergoing open fixation of fractures distal to the knee between 2010 and 2019 (n = 9172 patients). Intervention:. Open reduction and internal fixation of fractures distal to the knee. Main Outcome Measurements:. Thirty-day postoperative complications and time to surgery by race, as compared by multivariable regression with nearest-neighbor propensity score matching. Results:. Of the 9172 patients in our cohort, 1120 (12%) were Black. After matching, we identified 1120 White patients with equal propensity scores as our Black patients. Black patients had 1.5 times higher odds (95% confidence interval [CI]: 1.0–2.0) of experiencing any early adverse event when compared with matched White counterparts. Black patients also had 1.9 times higher odds (95% CI: 1.2–3.0) of requiring unplanned readmission within 30 days of operative fixation. There were no significant differences by race in time to surgery. Fracture subtype (tibia/fibula shaft, isolated malleolar, bi/trimalleolar, and pilon fractures) was not associated with postoperative complications or time to surgery in the multivariable analysis. Conclusion:. Racial disparities in the early postoperative course after open fixation of fractures distal to the knee exist, with significantly higher rates of early adverse events and unplanned readmission persist for Black versus White patients after propensity matching. Level of Evidence:. Prognostic level III.