Clinical Research Directory

Effects of a Contextual Decision-making Materials on Junior Nurses in Traumatic Learning Performance

Trauma leading to severe bleeding is one of the reasons for the high mortality rate in trauma patients, resulting in multiple and complex injuries from various accidental mechanisms. However, patients with abdominal-pelvic trauma accidents rank among the top three common accidents in the emergency department. There is a potential for both trauma and severe internal bleeding, making the care of such patients even more challenging. Currently, trauma nursing education focuses on emergency medical care, and teaching on the care of abdominal-pelvic trauma occupies only a small part of the entire nursing curriculum. In addition to insufficient knowledge teaching in emergency trauma medical care, learning relies heavily on the arrangement of clinical internships, and obtaining practical experience in the care of abdominal-pelvic trauma is often difficult. In the current era of thriving digital learning, allowing learning to be more diverse and unrestricted by time and location, it is essential to integrate appropriate guiding strategies alongside digital technology to make learning more efficient and promote meaningful learning. Therefore, this study introduces decision trees into an interactive scenario-based learning environment for the care of severe bleeding due to abdominal-pelvic trauma. The decision tree is coupled with a decision-making strategy, utilizing the relationships between leaf nodes to guide learners in clarifying their misconceptions, ultimately leading them to make appropriate decisions to reach the final nodes and solve problems. To understand the effectiveness of this study, a real experimental research design is adopted to investigate the impact of introducing decision tree-based interactive teaching materials on the care of severe bleeding in abdominal-pelvic trauma situations on the professional knowledge, self-efficacy, clinical reasoning assessment ability, and technology acceptance of surgical nursing students over a two-year period. It is hoped that this interactive teaching material for the care of severe bleeding in abdominal-pelvic trauma scenarios will enhance learners' professional knowledge, self-efficacy, clinical reasoning assessment, and technology acceptanc.

Diagnostic Reliability of ChatGPT in Letournel-Judet Acetabular Fracture Classification

This study aims to evaluate the diagnostic reliability of the multimodal artificial intelligence model ChatGPT-4o in classifying acetabular fractures using the Letournel-Judet classification system. The study retrospectively analyzed standardized pelvic radiographs (anteroposterior, iliac oblique, and obturator oblique) from 184 patients presenting with pelvic injuries. The diagnostic performance of ChatGPT-4o was compared against the independent assessments of two fourth-year orthopaedic residents and a reference standard established by an experienced trauma surgeon using multiplanar computed tomography (CT) and intraoperative findings. By utilizing a systematic radiographic checklist, the study assesses the AI (artificial intelligence) model's ability to identify key anatomical landmarks and integrate them into a final fracture pattern. This research aims to provide critical data on the current feasibility of using large language models as decision-support tools in complex orthopaedic trauma.