Journal of cardiothoracic and vascular anesthesia
-
J. Cardiothorac. Vasc. Anesth. · May 2024
The Year in Graduate Medical Education: Selected Highlights from 2023.
This special article is the third in an annual series of the Journal of Cardiothoracic and Vascular Anesthesia that highlights significant literature from the world of graduate medical education published over the past year. Major themes addressed in this review include the potential uses and pitfalls of artificial intelligence in graduate medical education, trainee well-being and the rise of unionized house staff, the effect of gender and race/ethnicity on residency application and attrition rates, and the adoption of novel technologies in medical simulation and education. The authors thank the editorial board for again allowing us to draw attention to some of the more interesting work published in the field of graduate medical education during 2023. We hope that the readers find these highlights thought-provoking and informative as we all strive to successfully educate the next generation of anesthesiologists.
-
J. Cardiothorac. Vasc. Anesth. · May 2024
ReviewArtificial Intelligence for Anesthesiology Board-Style Examination Questions: Role of Large Language Models.
New artificial intelligence tools have been developed that have implications for medical usage. Large language models (LLMs), such as the widely used ChatGPT developed by OpenAI, have not been explored in the context of anesthesiology education. Understanding the reliability of various publicly available LLMs for medical specialties could offer insight into their understanding of the physiology, pharmacology, and practical applications of anesthesiology. ⋯ GPT-4 significantly outperformed GPT-3.5 and Bard in terms of overall performance, but lacked consistency in providing explanations that aligned with scientific and medical consensus. Although GPT-4 shows promise, current LLMs are not sufficiently advanced to answer anesthesiology board examination questions with passing success. Further iterations and domain-specific training may enhance their utility in medical education.