ABSTRACT
Purpose: To assess the performance of Chat Generative Pre-Trained Transformer (ChatGPT) when answering self-assessment exam questions in hand surgery and to compare correct results for text-only questions to those for questions that included images. Methods: This study used 10 self-assessment exams from 2004 to 2013 provided by the American Society for Surgery of the Hand (ASSH). ChatGPT's performance on text-only questions and image-based questions was compared. The primary outcomes were ChatGPT's total score, score on text-only questions, and score on image-based questions. The secondary outcomes were the proportion of questions for which ChatGPT provided additional explanations, the length of those elaborations, and the number of questions for which ChatGPT provided answers with certainty. Results: Out of 1,583 questions, ChatGPT answered 573 (36.2%) correct. ChatGPT performed better on text-only questions than image-based questions. Out of 1,127 text-only questions, ChatGPT answered 442 (39.2%) correctly. Out of the 456 image-based questions, it answered 131 (28.7%) correctly. There was no difference between the proportion of elaborations among text-only and image-based questions. Although there was no difference between the length of elaborations for questions ChatGPT got correct and incorrect, the length of elaborations provided for image-based questions were longer than those provided for text-only questions. Out of 1,441 confident answers, 548 (38.0%) were correct; out of 142 unconfident answers, 25 (17.6%) were correct. Conclusions: ChatGPT performed poorly on the ASSH self-assessment exams from 2004 to 2013. It performed better on text-only questions. Even with its highest score of 42% for the year 2012, the AI platform would not have received continuing medical education credit from ASSH or the American Board of Surgery. Even when only considering questions without images, ChatGPT's high score of 44% correct would not have "passed" the examination. Clinical relevance: At this time, medical professionals, trainees, and patients should use ChatGPT with caution as the program has not yet developed proficiency with hand subspecialty knowledge.
ABSTRACT
Purpose The purpose of this study was to investigate the reported rates and characteristics of injuries among CrossFit athletes with specific attention to the hand and wrist. We further sought to identify trends and associations of these injuries by examining demographic data. Methods A questionnaire was created to capture self-reported information on the incidence of hand or wrist injuries and their associations in CrossFit athletes. It was distributed between April 2020 and July 2020 to athletes training at CrossFit affiliated gyms in the New York and Pennsylvania regions. Bivariate logistic regression analysis was used to identify factors correlated with an injury. Results A total of 270 responses (97.5% response rate) were available for final analysis. The median age of respondents was 34 years and 72.2% had been participating in CrossFit for at least two years. CrossFit athletes reported injury rates of 62.2% while engaged in CrossFit training and 20.4% reported an injury specific to the hand or wrist. The majority of hand or wrist injuries occurred after one year of CrossFit training (65.4%). The majority of reported initial injuries occurred to the wrist (75.4%); subsequently, 29.1% reported reinjuring the same region. While 58.2% reported not yet having healed or taking longer than one month to feel fully healed, 72.8% reported returning to unmodified training within one month. Only 15 respondents reported seeking medical attention from a physician for their injury. Physicians generally recommended a training break of over one month, but only two patients reported taking a break this long. Male sex and length of participation in CrossFit were associated with an increased risk of developing a hand or wrist injury. Discussion Hand and wrist injuries represent a significant proportion of injuries among CrossFit athletes. CrossFit practitioners are potentially returning to unmodified training too early following injury, leaving them susceptible to further injury. Physicians and therapists must consider these findings and address both therapies and preventative measures for these types of injuries with their patients.
