Emergency Patient Triage Improvement through a Retrieval-Augmented Generation Enhanced Large-Scale Language Model.

OBJECTIVES: Emergency medical triage is crucial for prioritizing patient care in emergency situations, yet its effectiveness can vary significantly based on the experience and training of the personnel involved. This study aims to evaluate the efficacy of integrating Retrieval Augmented Generation (RAG) with Large Language Models (LLMs), specifically OpenAI's GPT models, to standardize triage procedures and reduce variability in emergency care. METHODS: We created 100 simulated triage scenarios based on modified cases from the Japanese National Examination for Emergency Medical Technicians. These scenarios were processed by the RAG-enhanced LLMs, and the models were given patient vital signs, symptoms, and observations from emergency medical services (EMS) teams as inputs. The primary outcome was the accuracy of triage classifications, which was used to compare the performance of the RAG-enhanced LLMs with that of emergency medical technicians and emergency physicians. Secondary outcomes included the rates of under-triage and over-triage. RESULTS: The Generative Pre-trained Transformer 3.5 (GPT-3.5) with RAG model achieved a correct triage rate of 70%, significantly outperforming Emergency Medical Technicians (EMTs) with 35% and 38% correct rates, and emergency physicians with 50% and 47% correct rates (p < 0.05). Additionally, this model demonstrated a substantial reduction in under-triage rates to 8%, compared with 33% for GPT-3.5 without RAG, and 39% for GPT-4 without RAG. CONCLUSIONS: The integration of RAG with LLMs shows promise in improving the accuracy and consistency of medical assessments in emergency settings. Further validation in diverse medical settings with broader datasets is necessary to confirm the effectiveness and adaptability of these technologies in live environments.

No definite advantage of a portable accelerometer-based navigation system over conventional technique in total knee arthroplasty: A systematic review and meta-analysis.

BACKGROUND: Precise implant alignment is a crucial prognostic factor in total knee arthroplasty (TKA). Portable navigation systems (PN-TKA) were reported to be better than the conventional technique (CON-TKA). We hypothesized that PN-TKA offered greater radiologic precision than CON-TKA in mechanically aligning components. We investigated whether (1) it improved global mechanical alignment, and (2) optimized component placement with respect to the tibial and femoral mechanical axes. PATIENTS AND METHODS: A systematic literature review compared PN-TKA versus CON-TKA. PubMed, Web of Science and Cochrane Library search retrieved ten studies. Their data were pooled using RevMan 5.3. Odds ratios (OR) for dichotomous data were calculated with 95% confidence intervals (CIs) for each outcome. Statistical heterogeneity was assessed as I2 using a standard χ2 test. I2>50% denoted significant heterogeneity requiring a random effects model; otherwise, a fixed effects model was applied. RESULTS: There were significantly fewer outliers for mechanical axis (I2=24%, OR=0.62, 95% CI=0.42-0.91, p=0.02) and coronal femoral component angle (I2=58%, OR=0.31, 95% CI=0.13-0.73, p=0.007) using PN-TKA; however, no significant difference was observed for coronal tibial component angle outliers (I2=0%, OR=0.66, 95% CI=0.38-1.15, p=0.14). DISCUSSION: Although PN-TKA appeared to improve global alignment, it had no effect on coronal tibial alignment, which is a key factor in predicting the long-term success of component fixation. There thus appeared to be no definite advantage of PN-TKA over CON-TKA. LEVEL OF EVIDENCE: III.

Total hip arthroplasty after failed transtrochanteric rotational osteotomy for osteonecrosis of the femoral head: A systematic review and meta-analysis.

BACKGROUND: Several studies have reported regarding total hip arthroplasty (THA) for osteonecrosis of the femoral head after failed transtrochanteric rotational osteotomy (TRO). However, to our knowledge, no formal systematic review and meta-analysis have been published yet summarizing the clinical results of a THA after failed TRO. Therefore, we conducted a systematic review and meta-analysis of the THA outcomes after failed TRO. We focussed on the issue whether a previous TRO affects the results of subsequent THA, including operative time, operative blood loss, radiological parameters, postoperative complications, and clinical outcomes. METHODS: Literatures published up to January 2018 were searched in the PubMed, Web of Science, and Cochrane Library, and the pooling of data was performed using a RevMan software (version 5.3, Cochrane Collaboration, Oxford, UK). A p-value<0.05 was considered statistically significant. We calculated the mean differences (MD) for continuous data and the odds ratio (OR) for dichotomous data with 95% confidence intervals (CI) for each outcome. Statistical heterogeneity was assessed based on I2 using the standard Chi2. When I2>50%, significant heterogeneity was assumed, and a random-effects model was applied for the meta-analysis. A fixed-effects model was applied in the absence of significant heterogeneity. RESULTS: Five studies were included in this meta-analysis. The results showed that operative time was significantly longer in the THA after the TRO than that for the THA without previous osteotomy (I2=92%; MD=31.62; 95% CI: 5.95 to 57.28; p=0.02). Operative blood loss was significantly greater in the THA after the TRO than that in the THA without previous osteotomy (I2=71%; MD=123.30; 95% CI: 22.21 to 224.39; p=0.02). The rate of stem malalignment was significantly higher in the THA after the TRO than that in the THA without previous osteotomy (I2=0%; OR=5.23, 95% CI: 1.95 to 14.06; p=0.001). There was no significant difference in the dislocation rate (I2=0%; OR=2.12; 95% CI: 0.64 to 6.99; p=0.22), and the postoperative Harris hip score at the final follow-up (I2=75%, MD=-0.46, 95% CI: -3.92 to 3.01, p=0.80) between the groups. CONCLUSION: The results demonstrate that, performing the THA after the TRO is technically more demanding than the THA without previous osteotomy. TRO does not affect the clinical results of future THA, and is a sufficient therapeutic alternative in younger patients. LEVEL OF EVIDENCE: III, systematic and meta-analysis of case control studies.

Acute Traumatic Patellar Tendon Rupture at the Tibial Tuberosity Attachment without Avulsion Fracture.

Patellar tendon rupture in children is especially rare. The fact that the area of traumatic rupture has wide variations makes surgical treatment difficult. We present an 11-year-old boy with acute traumatic patellar tendon rupture at the tibial tuberosity attachment without avulsion fracture. Primary end-to-end repair and reinforcement using 1.5 mm stainless steel wires as a surgical strategy were undertaken. Early range of motion began with a functional knee brace and the reinforced stainless wire was removed 3 months after surgery. Knee function at the final follow-up was satisfactory. We suggest that this strategy may provide a useful option for surgical treatment.