ABSTRACT
Background: ChatGPT is an artificial intelligence chatbot capable of providing human-like responses for virtually every possible inquiry. This advancement has provoked public interest regarding the use of ChatGPT, including in health care. The purpose of the present study was to investigate the quantity and accuracy of ChatGPT outputs for general patient-focused inquiries regarding 40 orthopaedic conditions. Methods: For each of the 40 conditions, ChatGPT (GPT-3.5) was prompted with the text "I have been diagnosed with [condition]. Can you tell me more about it?" The numbers of treatment options, risk factors, and symptoms given for each condition were compared with the number in the corresponding American Academy of Orthopaedic Surgeons (AAOS) OrthoInfo website article for information quantity assessment. For accuracy assessment, an attending orthopaedic surgeon ranked the outputs in the categories of <50%, 50% to 74%, 75% to 99%, and 100% accurate. An orthopaedics sports medicine fellow also independently ranked output accuracy. Results: Compared with the AAOS OrthoInfo website, ChatGPT provided significantly fewer treatment options (mean difference, -2.5; p < 0.001) and risk factors (mean difference, -1.1; p = 0.02) but did not differ in the number of symptoms given (mean difference, -0.5; p = 0.31). The surgical treatment options given by ChatGPT were often nondescript (n = 20 outputs), such as "surgery" as the only operative treatment option. Regarding accuracy, most conditions (26 of 40; 65%) were ranked as mostly (75% to 99%) accurate, with the others (14 of 40; 35%) ranked as moderately (50% to 74%) accurate, by an attending surgeon. Neither surgeon ranked any condition as mostly inaccurate (<50% accurate). Interobserver agreement between accuracy ratings was poor (κ = 0.03; p = 0.30). Conclusions: ChatGPT provides at least moderately accurate outputs for general inquiries of orthopaedic conditions but is lacking in the quantity of information it provides for risk factors and treatment options. Professional organizations, such as the AAOS, are the preferred source of musculoskeletal information when compared with ChatGPT. Clinical Relevance: ChatGPT is an emerging technology with potential roles and limitations in patient education that are still being explored.
ABSTRACT
BACKGROUND: Patient sex is known to affect patient outcomes in sports medicine. Historically, many studies on athletes have focused on male athletes and been generalized to female athletes. HYPOTHESIS: Studies with female first or senior authors will isolate female athletes as study participants more frequently than studies with male first or senior authors. STUDY DESIGN: Systematic review; Level of evidence, 4. METHODS: Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) protocols, original research studies published between 2017 and 2021 that analyzed athletes were systematically screened from the 6 top sports medicine journals (British Journal of Sports Medicine; Arthroscopy: The Journal of Arthroscopic and Related Surgery; Knee Surgery, Sports Traumatology, Arthroscopy; American Journal of Sports Medicine; Orthopaedic Journal of Sports Medicine; Sports Health: A Multidisciplinary Approach). Articles were included for analysis if they met the following criteria: (1) original sports medicine research study, (2) analysis involving athletes, and (3) inclusion of ≥10 participants. Exclusion criteria included (1) review articles of any type and (2) cadaveric studies. The determination of author sex was completed using the name-to-gender assignment algorithm Genderize.io (https://genderize.io/). RESULTS: A total of 1146 studies were included in quantitative analysis. There were 246 studies with a female first author (21.5%) and 191 studies with a female senior author (16.7%). When looking at all authors (first, senior, and intermediate), 19.9% were female. Female first authors were over 4 times more likely to isolate female athletes in clinical research than male first authors (17.5% vs 3.8%, respectively; P < .001). Female senior authors were approximately twice as likely to isolate female athletes compared with male senior authors (11.5% vs 5.8%, respectively; P < .001). CONCLUSION: Female first authors were significantly more likely to perform research isolating female athletes. While improving the frequency of female athlete research is multifactorial, increasing the number of female researchers may have a direct effect on improving gender equality in sports medicine research.
ABSTRACT
BACKGROUND: The purpose of this study was to perform a systematic review of the literature to identify Shoulder Instability Return to Sport after Injury (SIRSI) scores in athletes who underwent open Latarjet surgery, determine the reasons why athletes failed to return to play (RTP) after Latarjet surgery, and compare SIRSI scores of those who did vs. did not RTP. METHODS: According to PRISMA guidelines, the PubMed, SportDiscus, and Ovid MEDLINE databases were queried to identify studies evaluating return to sport after Latarjet surgery. Study quality was assessed using the MINORS criteria. Studies were included if RTP after Latarjet surgery and a psychological factor were evaluated, with potential psychological factors including readiness to RTP and reasons for failure to RTP. RESULTS: Fourteen studies, 10 of level III evidence and 4 of level IV evidence, with 1034 patients were included. A total of 978 athletes were eligible to RTP. Of these, 792 (79%) successfully returned to play and 447 (56.4%) returned to play at their previous level of play. Mean RTP time was 6.2 months. Postoperative SIRSI scores averaged 71.2 ± 8.8 at a mean of 21 months' follow-up. Postoperative SIRSI scores for those able to RTP was 73.2, whereas athletes unable to RTP scored an average of 41.5. Mean postoperative SIRSI scores for those in contact sports was 71.4, whereas those in noncontact sports was 86.5. There were 31 athletes with a documented reason why they did not RTP, with postoperative shoulder injury being the most common reason (54.5%). Fear of reinjury and feeling "not psychologically confident" each represented 6.5% of the total. CONCLUSION: Athletes who RTP have higher average SIRSI scores than those who are unable to RTP. Of the athletes who documented why they did not RTP, more than half cited a shoulder injury as their reason for not returning to play, whereas fear of reinjury and lack of psychological readiness were other common reasons.
