The integration of artificial intelligence (AI) in healthcare has rapidly expanded, particularly in clinical decision-making. Large language models (LLMs) such as GPT-4 and GPT-3.5 have shown potential in various medical applications, including diagnostics and treatment planning. However, their efficacy in specialized fields like sports surgery and physiotherapy remains underexplored. This study aims to compare the performance of GPT-4 and GPT-3.5 in clinical decision-making within these domains using a structured assessment approach. This cross-sectional study included 56 professionals specializing in sports surgery and physiotherapy. Participants evaluated 10 standardized clinical scenarios generated by GPT-4 and GPT-3.5 using a 5-point Likert scale. The scenarios encompassed common musculoskeletal conditions, and assessments focused on diagnostic accuracy, treatment appropriateness, surgical technique detailing, and rehabilitation plan suitability. Data were collected anonymously via Google Forms. Statistical analysis included paired t-tests for direct model comparisons, one-way ANOVA to assess performance across multiple criteria, and Cronbach’s alpha to evaluate inter-rater reliability. GPT-4 significantly outperformed GPT-3.5 across all evaluated criteria. Paired t-test results (t(55) = 10.45, p < 0.001) demonstrated that GPT-4 provided more accurate diagnoses, superior treatment plans, and more detailed surgical recommendations. ANOVA results confirmed the higher suitability of GPT-4 in treatment planning (F(1, 55) = 35.22, p < 0.001) and rehabilitation protocols (F(1, 55) = 32.10, p < 0.001). Cronbach’s alpha values indicated higher internal consistency for GPT-4 (α = 0.478) compared to GPT-3.5 (α = 0.234), reflecting more reliable performance. GPT-4 demonstrates superior performance compared to GPT-3.5 in clinical decision-making for sports surgery and physiotherapy. These findings suggest that advanced AI models can aid in diagnostic accuracy, treatment planning, and rehabilitation strategies. However, AI should function as a decision-support tool rather than a substitute for expert clinical judgment. Future studies should explore the integration of AI into real-world clinical workflows, validate findings using larger datasets, and compare additional AI models beyond the GPT series.

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.

Background and Objectives: This study aimed to determine the relationship between non-simultaneous contralateral hip fractures, urban and rural differences, fracture localization, time between fractures, physiotherapy applications, comorbidity, and the second fracture outcomes. Materials and Methods: We retrospectively analyzed 107 patients aged 65 and older with proximal femur fractures (PFFs) who underwent surgery at Düzce University Medical Faculty between January 2010 and December 2022. High-energy fractures, pathological fractures, and patients with a history of old fractures were excluded. Results: The study included 66 females (61.7%) and 41 males (38.3%), with a mean age of 83.76 years. The mean interval between two fractures was 28.3 months. There was no statistical difference between the localization of the first and second fractures (p = 0.107). However, there was a significant difference in the first PFF localizations of patients living in rural areas (p = 0.023). Patients with heart failure, respiratory failure, osteoporosis, and cognitive impairment had shorter intervals between fractures (p < 0.001). Conclusions: This study shows that age, female gender, place of residence, comorbid diseases, and whether physical therapy is received after the first fracture are significant risk factors for a second hip fracture in patients over 65 years of age.

Objectives: Total hip arthroplasty is one of the most common procedures performed to reduce pain and improve hip functions in patients with advanced hip osteoarthritis, but perioperative blood loss, acute anemia and transfusion requirement increase the risk of morbidity and mortality during and after surgery and negatively affect functional recovery. We aimed to present the comparative results of oral + topical and only topical tranexamic acid application to reduce blood loss and postoperative transfusion in primary total hip arthroplasty. Methods: We retrospectively evaluated the patients who applied to the Orthopedics and Traumatology outpatient clinic with complaints of hip pain and limited movement between January 2014 and December 2020, who underwent primary total hip arthroplasty with the diagnosis of coxarthrosis and who were administered oral + topical and only topical tranexamic acid before and during surgery, in terms of blood loss and transfusion requirement. Results: No statistically significant difference was observed between the preoperative, day 0 and day 1 hemoglobin means in those that were applied oral + topical tranexamic acid and those that were applied only topical (p > 0.05). However, the second- and third-day hemoglobin means in those that were treated with topical medication alone were found to be statistically significantly lower than in those that were treated with oral + topical tranexamic acid (p = 0.032, p = 0.0001). Conclusions: Oral + topical tranexamic acid application in total hip arthroplasty surgery is more effective than topical applications alone when it comes to reducing blood loss, hemoglobin and hematocrit decrease without increasing the risk of thromboembolic diseases and wound complications.

Background: This study aimed to investigate the effect of omitting a distal locking screw in intramedullary nailing of stable intertrochanteric femur fractures on clinical outcomes. Methods: Ninety-six patients over 65 years old with stable pertrochanteric fractures (AO/OTA 31-A1 and A2) treated with short/intermediate proximal femoral nails (PFNA-II) were randomly assigned into two groups: Group 1 (distal locked) and Group 2 (distal unlocked). Comparative analyses were conducted on operative time, total fluoroscopy time, blood loss, incision length, complications, and functional outcomes. Results: The mean operative time was significantly shorter in Group 2 (35.73 ± 7.62 minutes) compared to Group 1 (47.40 ± 9.96 minutes) ( P < 0.001). Fluoroscopy time was also shorter in Group 2 (45.92 ± 6.08 seconds) compared to Group 1 (54.02 ± 5.94 seconds) ( P < 0.001). Incision length was reduced in Group 2 (9.21 ± 1.41 centimeters) compared to Group 1 (12.96 ± 1.68 centimeters) ( P < 0.001). Blood loss was lower in Group 2 (187.50 ± 32.00 milliliters) than in Group 1 (208.65 ± 49.12 milliliters) ( P < 0.05). There were no significant differences between the groups in fracture union time, hospital stay, fracture union weeks, or postoperative blood transfusion rates. Conclusions: Proximal femoral nailing without distal locking offers shorter operative times, reduced fluoroscopy exposure, and lower blood loss and complications, making it a viable option for treating stable intertrochanteric fractures.

Çelik M, et al. Clin Orthop Surg. 2024 Oct;16(5):836-844. https://doi.org/10.4055/cios24056