Evaluation of ChatGPT’s Performance in the Turkish Board of Orthopaedic Surgery Examination - The Medical Bulletin of Haseki

Joint Diseases and Related Surgery (JDRS), the official journal of the Turkish Joint Diseases Foundation, is an international, peer-reviewed, immediate open access journal. All published articles in JDRS has been free for everyone, without embargo, since 1990.

Aims: Artificial Intelligence (AI)–based language models are increasingly used to generate medical information and patient education materials. However, the reliability and safety of AI-generated rehabilitation guidance remain uncertain. This study aimed to evaluate the accuracy, safety, clinical utility, and readability of rehabilitation recommendations generated by ChatGPT-5 for Bankart lesions and to compare these outputs with expert-developed rehabilitation protocols.Methods: A blinded, cross-sectional comparative quality assessment was conducted. Standardized prompts regarding nonoperative and postoperative Bankart rehabilitation were used to generate responses from ChatGPT-5. AI-generated texts were compared with protocols prepared by a panel of orthopedic shoulder surgeons and an experienced physiotherapist. All texts were anonymized and independently evaluated by three blinded expert raters using a structured 5-point Likert scale assessing clinical accuracy, safety, actionability, comprehensiveness, and overall quality. Major clinical errors were recorded separately. Readability was assessed using Flesch Reading Ease and Flesch–Kincaid Grade Level scores. Inter-rater reliability was analyzed using intraclass correlation coefficients (ICC). Results: A total of 20 rehabilitation texts (10 AI-generated and 10 expert-developed) were evaluated. Expert protocols demonstrated significantly higher scores in clinical accuracy (4.6±0.4 vs 3.4±0.7, p

Transphyseal fractures of the distal humerus are usually seen in children younger than 3 years of age and are considered as Salter-Harris Type I epiphysiolysis. Neonatal transphyseal distal humerus injuries are extremely rare. It usually occurs due to trauma during difficult labour but can also be seen after child abuse. Since the distal humerus is composed of cartilaginous tissue in newborns, it is difficult to make a diagnosis with direct radiography. Patients are often diagnosed with elbow dislocation. However, elbow dislocation is almost never seen under the age of 3 years. Transphyseal fractures can be seen as a result of manoeuvres performed to deliver the baby during difficult normal delivery. Transphyseal humeral injuries can also be seen after caesarean section, child abuse and falling on the hyperextended arm. Clinical symptoms include pain, swelling, ecchymosis and crepitation at the elbow. Pseudoparalysis is present due to pain. In children with a history of difficult birth or trauma, evaluation with direct radiography should be performed initially. Radiocapitellar line is distorted on radiographs and the elbow joint appears subluxated. The treatment algorithm for transfusional humeral fractures in neonates is varied. It should be remembered that patients in this age group have a tremendous healing capacity. In conservative treatment, 2-4 weeks of follow-up with a long-arm splint after reduction is sufficient. In addition, closed reduction-internal fixation or open reduction-internal fixation can be applied according to the amount of displacement of the fracture. Cubitus varus, osteonecrosis, growth disturbance, decreased range of motion, compartment syndrome, neurovascular injury and infection are the main complications seen after transfusional humeral fractures.

Aim: This study aims to perform a bibliometric analysis of articles published in Acta Orthopaedica et Traumatologica Turcica (AOTT) from 2013 to 2023. Methods: Articles published in AOTT from January 2013 to December 2023 were analyzed using bibliometric methods. The analysis included article type, number of authors, number of institutions authors worked for, country of the first author, international collaboration for Turkish authors, citation counts, and numbers of reads and downloads. Results: 1035 articles were reviewed, with a significant portion being retrospective studies (44.4%). Basic science studies constituted 16.5% of the total, closely followed by case reports (15.7%). The structure of the institution where the first author worked was a university hospital, in 603 articles (58.26%). In 932 articles (90.05%), the gender of the first author was male, and in 103 articles (9.95%), the gender of the first author was female. The total number of authors ranged from 1 to 15 (average: 4.75±1.53, median: 5), and the number of institutions authors worked for averaged 2.24±1.32 (range: 1-14, median: 2). Citation numbers ranged from 1 to 186 (average: 12.78±15.68, median: 8). The total number of citations to all articles was 15127. Conclusion: This study reveals the status and trends of articles published in AOTT over 11 years.