The use of large language models (LLMs) in clinical medicine is currently thriving. Effectively transferring LLMs’ pertinent theoretical knowledge from computer science to their application in clinical medicine is crucial. Prompt engineering has shown potential as an effective method in this regard. To explore the application of prompt engineering in LLMs and to examine the reliability of LLMs, different styles of prompts were designed and used to ask different LLMs about their agreement with the American Academy of Orthopedic Surgeons (AAOS) osteoarthritis (OA) evidence-based guidelines. Each question was asked 5 times. We compared the consistency of the findings with guidelines across different evidence levels for different prompts and assessed the reliability of different prompts by asking the same question 5 times. gpt-4-Web with ROT prompting had the highest overall consistency (62.9%) and a significant performance for strong recommendations, with a total consistency of 77.5%. The reliability of the different LLMs for different prompts was not stable (Fleiss kappa ranged from −0.002 to 0.984). This study revealed that different prompts had variable effects across various models, and the gpt-4-Web with ROT prompt was the most consistent. An appropriate prompt could improve the accuracy of responses to professional medical questions.

Background: Visual clarity during shoulder arthroscopy can ensure an efficient and effective performance of the procedure, and it is highly related to bleeding without a tourniquet. Tranexamic acid (TXA) is widely used in adult reconstruction procedures; however, its use in shoulder arthroscopic operations is a relatively novel topic. Purpose: To analyze the available literature on visual clarity, blood loss, pain control, functional outcomes, and complications after the administration of tranexamic acid in shoulder arthroscopic surgery. Methods: A literature search was performed to retrieve randomized controlled trials examining the use of tranexamic acid at the time of shoulder arthroscopic surgery. The literature search included the MEDLINE, Embase, Web of Science, and Cochrane Library databases. The primary outcomes included visual clarity, blood loss, and visual analog scale scores for pain. Secondary outcomes were operative time, irrigation amount used, postoperative shoulder swelling, the need for pressure increase, mean arterial pressure (MAP), functional outcomes, postoperative adverse effects such as deep venous thrombosis, and pulmonary embolism. The outcomes were pooled to perform a meta-analysis. Results: Seven prospective randomized controlled trials met the inclusion criteria for analysis. All of the included studies performed arthroscopic rotator cuff repair. No significant difference in visual clarity was observed (SMD (standardized mean difference), 0.45 [95% CI(confidence interval), −0.68, 1.59]; p = 0.44) nor in pain score (MD (mean difference), −0.46 [95% CI, −0.97, 0.05]; p = 0.08) between the TXA group and the control group. Two studies found no significant difference in blood loss between the TXA group and the control group. The meta-analysis from five studies demonstrated no significant difference between the TXA and control groups in operative time (MD, −3.51 [95% CI, −15.82, 8.80]; p = 0.58) or irrigation amount used (MD, −2.53 [95% CI, −5.93, 0.87]; p = 0.14). Two trials reported different statistical results in postoperative shoulder swelling. No significant differences regarding the need for pressure increase and MAP were reported between groups. No wound complications or infections or cardiac, thrombotic, or thromboembolic complications were recorded in either group. Conclusion: The use of intravenous or local TXA in shoulder arthroscopic surgery did not increase complications or thromboembolic events, but TXA had no obviously effect of reducing bleeding to obtain a clear visual field or pain release in patients undergoing shoulder arthroscopic surgery.

Background: Surgical resection of Morton's neuroma includes dorsal and plantar approaches. However, there is no consensus on the choice of approach in clinic. The purpose of this study was to conduct a systematic review and meta‐analysis to compare the surgical results of dorsal and plantar approaches.Methods: The literatures of PubMed, Cochrane library, Embase and Web of Science were searched on April 26th, 2023. A systematic review was performed using the Preferred Reporting Items for Systematic Reviews and Meta‐Analysis guidelines. The data were extracted after screening the literature and evaluating the quality of the methodology included in the study. The RevMan5.4 software was used to analyze and calculate the OR value and 95% confidence interval.Results: A total of 7 randomized controlled trials and comparative studies were published, of which only 5 were included. There were 158 feet via plantar approach (plantar group, PG) and 189 via dorsal approach (dorsal group, DG). There was no significant difference between PG and DG in overall adverse events, sensory problems, incision infection and deep vein thrombosis (p > 0.05). In terms of scar problems, PG showed more than DG (OR, 2.90[95%CI, 1.40 to 5.98]; p = 0.004). Other outcome indicators such as visual analogue scale (VAS) scores and American Orthopedic Foot and Ankle Society (AOFAS) scores were difficult to be included in the comparison.Conclusions: Based on the relatively low quality and small amount of available evidence, the meta‐analysis conducted produces a hypothesis that the frequency of adverse events in surgical treatment of Morton's neuroma, dorsal approach and plantar approach may be the same, but the types are different. More high‐level evidence is needed to further verify this hypothesis.

Objective: Diffuse‐type tenosynovial giant cell tumors (Dt‐TGCTs) commonly occur in the knee joint and tend to recur postoperatively. However, limited clinical data are available on ankle joint involvement especially associated multiportal arthroscopic treatment outcomes. The purpose of this study was to report the clinical results of multiportal arthroscopy‐assisted resection of Dt‐TGCTs of the ankle.Methods: We retrospectively reviewed the clinical data of 33 patients with Dt‐TGCT of the ankle who underwent multiportal arthroscopic treatment between August 2011 and December 2020. Clinical follow‐up included the visual analogue scale (VAS) score, American Orthopedic Foot and Ankle Society (AOFAS) score, Kofoed score, and recurrence rate to assess surgical outcomes. The number of patients who achieved the patient acceptable symptom state (PASS) based on the AOFAS score was also examined. Additionally, the patients were categorized into two groups based on the final surgical approach: Group A who underwent multiportal arthroscopic synovectomy and Group AO who underwent combined arthroscopic and open surgical excision. Intergroup comparisons were conducted. Intraoperative characteristics, such as the number of patients with involvement of the tarsal tunnel and fibularis tendon and the Outerbridge grading of cartilage damage, were recorded to assess the selection of surgical procedures.Results: Among the 33 patients, 15 were assigned to Group A, and 18 were in Group AO. The median follow‐up duration for the 33 patients was 77 months (range, 28–142 months). The median VAS score was 1 (range, 0–4), the AOFAS score was 96 (range, 65–100), and the Kofoed score was 96 (range, 67–100). A total of 27 patients (82%) achieved PASS based on AOFAS scores, while five patients (15%) had recurrence. No statistically significant difference was observed between the two groups in recurrence rate, follow‐up VAS score, AOFAS score, Kofoed score, or number of patients who reached the PASS (p > 0.05). In the AO group, 16 cases of Dt‐TGCT involved the tarsal tunnel, and 11 cases involved the fibularis tendon. All these patients exhibited extension beyond the joint. In contrast, only one patient in Group A had involvement of the tarsal tunnel. Statistically significant differences were observed between the groups (p < 0.001).Conclusion: This study demonstrated that, with the assistance of a multiportal arthroscopic approach, surgical excision of Dt‐TGCT in the ankle resulted in favorable clinical outcomes with a relatively low recurrence rate. Additionally, patients with extra‐articular involvement were more likely to require concomitant open surgery.