Hairui Li

Background: Artificial intelligence and large language models (LLMs) are emerging as transformative technologies in medicine. However, their ability to develop physical exercise rehabilitation programs and provide insights into musculoskeletal (MSK) disorders remains underexplored. This study aimed to evaluate the quality and readability of LLM-generated responses to consultation questions addressing various stages of the clinical process encountered by patients with MSK disorders. Methods: This study recruited 50 patients with musculoskeletal disorders and extracted disease-related frequently asked questions from Google search. We developed three clinical scenario-based question types simulating real consultations, which were processed by four LLMs (GPT-3.5-turbo, GPT-4-turbo, GPT-4o, and Claude-3-haiku-20240307). Response quality was assessed by orthopedic specialists and therapists using the DISCERN instrument, and GPT-4o-assisted evaluation was used to extend the assessment after validation with expert ratings. Readability was systematically assessed via six validated indices. Results: Among the 1476 LLM-generated responses, the generated rehabilitation programs demonstrated consistent adherence to the specified query requirements. The DISCERN scores ranged from 26 (poor) to 68 (excellent), with a mean score of 55.60 ± 8.40. The intraclass correlation coefficient (0.68) indicated moderate interrater agreement, and Cronbach’s α showed good internal consistency. The readability scores across six indices indicated that most responses exceeded the recommended reading levels (p < 0.05). Conclusions: LLMs generated moderate-to-high-quality PE rehabilitation recommendations for patients with MSK disorders across simulated consultation scenarios. However, limited supporting materials and suboptimal readability may restrict their effectiveness. With physician oversight, improved readability, and enhanced supplementary resources, LLMs demonstrate considerable potential as supportive tools in orthopedics.

Background: Controversy remains over the choice of anaesthetic technique for patients undergoing surgery for hip fracture. Aim: The aim was to compare the risk of complication of neuraxial anaesthesia with that of general anaesthesia in patients undergoing hip fracture surgery. Methods: This systematic review was performed according to Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines and was registered at PROSPERO (CRD42022337384). The study included eligible randomised controlled trials published before February 2022. Data synthesis was performed to compare the differences between general and neuraxial anaesthesia. Meta-regression analysis was performed to investigate the influence of the publication year. A subgroup analysis was performed based on patient age and the anaesthetic technique used. A grading of recommendations, assessment, development and evaluations assessment was performed to assess the quality of each outcome. Results: Twenty randomised controlled trials and 4802 patients were included. Data synthesis revealed significant higher risk of acute kidney injury in the general anaesthesia group (P=0.01). There were no significant differences between the two techniques in postoperative short-term mortality (P=0.34), delirium (P=0.40), postoperative nausea and vomiting (P=0.40), cardiac infarction (P=0.31), acute heart failure (P=0.34), pulmonary embolism (P=0.24) and pneumonia (P=0.15). Subgroup analysis based on patient age and use of sedative medication did not reveal any significant differences. Meta-regression analysis of the publication year versus each adverse event revealed no statistically significant differences. Conclusion: A significantly higher risk of postoperative acute kidney injury was found in patients receiving general anaesthesia. This study revealed no significant differences in terms of postoperative mortality and other complications between general and neuraxial anaesthesia. The results were consistent across the age groups.