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.

Age-related meniscus injury (MI) involves inflammaging, but biomarkers and mechanisms remain unclear. Ribonucleic acid (RNA) sequencing of meniscal tissues

Finite element analysis (FEA) can translate tissue-level mechanical information into fabrication-ready designs. However, its use for spatially graded hydro

Femoroacetabular impingement syndrome (FAIS) is a prevalent cause of hip pain, yet comparative evidence on the clinical efficacy of hip arthroscopic surger

Discoid lateral meniscus (DLM) is susceptible to tearing and degeneration, but the molecular basis of its altered extracellular matrix (ECM) remains unclear. We integrated histology, electron microscopy, transcriptomics, quantitative proteomics, and donor-derived cell and spheroid models to investigate the association between thrombospondin-1 (THBS1) and matrix organization in symptomatic DLM. Compared with traumatic morphologically normal lateral meniscus (NLM), DLM tissue contained fewer cells per analyzed image (mean difference, −16.10; 95% confidence interval (CI), −23.49 to −8.71; P < 0.0001); lower type-I and II collagen signals; and thinner, less dense, and less organized collagen fibrils. Cross-omics analysis nominated THBS1 and ECM-receptor interaction, and independent assays confirmed a 6.67-fold lower THBS1 protein abundance in DLM (95% CI, 5.04 to 8.27; P < 0.0001). In donor-derived models, THBS1 knockdown in NLM cells reduced area-confluence trajectories, increased migration, and decreased collagen-rich matrix in 4-week spheroids, whereas THBS1 overexpression in DLM cells produced reciprocal changes; aggrecan was not consistently altered. These data associate reduced THBS1 with altered collagen-rich matrix organization and support a functional contribution in vitro . The cross-sectional clinical comparison does not establish chronology, and the spheroid experiments do not demonstrate a fibrillogenesis-specific mechanism.