Radiologic Technology最新文献

Purpose: To compare the performance of multiple large language models (LLMs) on a practice radiography certification exam.

Method: Using an exploratory, nonexperimental approach, 200 multiple-choice question stems and options (correct answers and distractors) from a practice radiography certification exam were entered into 5 LLMs: ChatGPT (OpenAI), Claude (Anthropic), Copilot (Microsoft), Gemini (Google), and Perplexity (Perplexity AI). Responses were recorded as correct or incorrect, and overall accuracy rates were calculated for each LLM. McNemar tests determined if there were significant differences between accuracy rates. Performance also was evaluated and aggregated by content categories and subcategories.

Results: ChatGPT had the highest overall accuracy of 83.5%, followed by Perplexity (78.9%), Copilot (78.0%), Gemini (75.0%), and Claude (71.0%). ChatGPT had a significantly higher accuracy rate than did Claude (P , .001) and Gemini (P 5 .02). Regarding content categories, ChatGPT was the only LLM to correctly answer all 38 patient care questions. In addition, ChatGPT had the highest number of correct responses in the areas of safety (38/48, 79.2%) and procedures (50/59, 84.7%). Copilot had the highest number of correct responses in the area of image production (43/55, 78.2%). ChatGPT also achieved superior accuracy in 4 of the 8 subcategories.

Discussion: Findings from this study provide valuable insights into the performance of multiple LLMs in answering practice radiography certification exam questions. Although ChatGPT emerged as the most accurate LLM for this practice exam, caution should be exercised when using generative artificial intelligence (AI) models. Because LLMs can generate false and incorrect information, responses must be checked for accuracy, and the models should be corrected when inaccurate responses are given.

Conclusion: Among the 5 LLMs compared in this study, ChatGPT was the most accurate model. As interest in generative AI continues to increase and new language applications become readily available, users should understand the limitations of LLMs and check responses for accuracy. Future research could include additional practice exams in other primary pathways, including magnetic resonance imaging, nuclear medicine technology, radiation therapy, and sonography.

Background: This case describes a 72-year-old man with substantial lower gastrointestinal bleeding (LGIB) for whom initial diagnostic workup failed to identify the source of bleeding, leading to progressive hemodynamic instability. A thorough reevaluation of the patient's computed tomography scan revealed a duplicated left colic artery originating directly from the aorta, a rare vascular variant not previously reported in the literature. Angiography identified this aberrant artery as the source of diverticular bleeding, guiding successful superselective coil embolization. At a 6-month follow-up, the patient had recovered well with no further evidence of bleeding.

Discussion: Acute LGIB presents a substantial medical challenge because of its diverse etiologies and potential for morbidity and mortality. Although diverticular bleeding is the most common cause of LGIB in western countries, rare anatomic variances can complicate diagnosis and treatment.

Conclusion: Awareness of rare anatomic variations in the setting of acute LGIB with hemodynamic compromise can be critical in improving patient outcomes.

Purpose: To investigate long-term effectiveness of immersive virtual reality (VR) compared with traditional learning methods in a radiography education program through a comparative longitudinal analysis.

Methods: For 3 years, educational outcomes, such as student engagement and knowledge retention, were assessed to determine the effects of hybrid simulation methods incorporating immersive VR. The study used Virtual Medical Coaching's X-Ray Pro VR software to integrate VR into the curriculum.

Results: The data and graphical analyses substantiate the effectiveness of the hybrid learning model over traditional physical methods in terms of academic and practical performance metrics, affective measures, and career preparedness. Students using a hybrid of VR and physical simulations had significantly higher mean posttest scores, mean practical exam scores, career readiness, internship performance, mean motivation level, and mean engagement level compared with the students who only used physical simulation machines (P < .001).

Discussion: The significant improvements in student engagement and retention observed in this study suggest that VR can effectively address some of the limitations of traditional learning methods. The immersive nature of VR might provide a more engaging and interactive learning environment, leading to better educational outcomes. These findings support the potential for VR to be a valuable tool in higher education, particularly in fields that benefit from simulation-based training. However, further research is needed to explore the practical challenges of implementing VR at scale and to evaluate its effectiveness across various educational disciplines.

Conclusion: This study uniquely contributes to the literature by providing empirical evidence of the sustained benefits of VR in educational settings, highlighting its potential to transform learning experiences and outcomes. The implications of these results suggest the need for educational institutions to consider integrating VR technologies strategically into their curricula to optimize teaching and learning effectiveness.