PDF(Pubmed)
Abstract：
OBJECTIVE: A recent study published in the JMIR Med Educ Journal explored the potential impact of the Generative Pre-Train (ChatGPT), a generative language model, on medical education, research, and practice. In the present study, an interview with ChatGPT was conducted to determine its capabilities and potential for use in anatomy education (AE) and anatomy research (AR).
METHODS: The study involved 18 questions asked of ChatGPT after obtaining an online subscription to the 4th edition. The questions were randomly selected and evaluated based on accuracy, relevance, and comprehensiveness.
RESULTS: The ChatGPT provided accurate and well-structured anatomical descriptions, including clinical relevance and relationships between structures. The chatbot also offered concise summaries of chapters and helpful advice on anatomical terminology, even with complex terms. However, when it came to anatomical variants and their clinical significance, the chatbot\'s replies were inadequate unless variants were systematically classified into types. ChatGPT-4 generated multiple-choice quizzes and matching questions of varying difficulty levels, as well as summaries of articles when presented with text. However, the chatbot recognized its limitations in terms of accuracy, as did the authors of the current study.
CONCLUSIONS: ChatGPT-4 can be a valuable interactive educational tool for students in the field of anatomy, encouraging engagement and further questions. However, it cannot replace the critical role of educators and should be used as a complementary tool. Future research should establish guidelines for ChatGPT\'s optimal use and application in medical education.
METHODS: The study involved 18 questions asked of ChatGPT after obtaining an online subscription to the 4th edition. The questions were randomly selected and evaluated based on accuracy, relevance, and comprehensiveness.
RESULTS: The ChatGPT provided accurate and well-structured anatomical descriptions, including clinical relevance and relationships between structures. The chatbot also offered concise summaries of chapters and helpful advice on anatomical terminology, even with complex terms. However, when it came to anatomical variants and their clinical significance, the chatbot\'s replies were inadequate unless variants were systematically classified into types. ChatGPT-4 generated multiple-choice quizzes and matching questions of varying difficulty levels, as well as summaries of articles when presented with text. However, the chatbot recognized its limitations in terms of accuracy, as did the authors of the current study.
CONCLUSIONS: ChatGPT-4 can be a valuable interactive educational tool for students in the field of anatomy, encouraging engagement and further questions. However, it cannot replace the critical role of educators and should be used as a complementary tool. Future research should establish guidelines for ChatGPT\'s optimal use and application in medical education.
摘要：
目标：最近发表在JMIRMedEducJournal上的一项研究探讨了生成预培训（ChatGPT）的潜在影响，生成语言模型，关于医学教育，研究,和实践。在本研究中,对ChatGPT进行了访谈,以确定其在解剖学教育(AE)和解剖学研究(AR)中的应用能力和潜力.
方法：该研究涉及ChatGPT在获得第4版在线订阅后提出的18个问题。问题是随机选择的，并根据准确性进行评估，相关性，和全面性。
结果：ChatGPT提供了准确且结构良好的解剖学描述，包括临床相关性和结构之间的关系。聊天机器人还提供了章节的简明摘要和有关解剖学术语的有用建议，即使是复杂的术语。然而,当谈到解剖学变异及其临床意义时，chatbot的答复是不充分的，除非变体被系统地分类到类型。ChatGPT-4生成了多项选择测验和不同难度级别的匹配问题，以及与文本一起呈现的文章摘要。然而,聊天机器人认识到它在准确性方面的局限性，就像当前研究的作者一样。
结论：ChatGPT-4对于解剖学领域的学生来说是一种有价值的互动教育工具，鼓励参与和进一步的问题。然而,它不能取代教育工作者的关键作用，应该作为补充工具。未来的研究应该为ChatGPT在医学教育中的最佳使用和应用建立指南。
方法：该研究涉及ChatGPT在获得第4版在线订阅后提出的18个问题。问题是随机选择的，并根据准确性进行评估，相关性，和全面性。
结果：ChatGPT提供了准确且结构良好的解剖学描述，包括临床相关性和结构之间的关系。聊天机器人还提供了章节的简明摘要和有关解剖学术语的有用建议，即使是复杂的术语。然而,当谈到解剖学变异及其临床意义时，chatbot的答复是不充分的，除非变体被系统地分类到类型。ChatGPT-4生成了多项选择测验和不同难度级别的匹配问题，以及与文本一起呈现的文章摘要。然而,聊天机器人认识到它在准确性方面的局限性，就像当前研究的作者一样。
结论：ChatGPT-4对于解剖学领域的学生来说是一种有价值的互动教育工具，鼓励参与和进一步的问题。然而,它不能取代教育工作者的关键作用，应该作为补充工具。未来的研究应该为ChatGPT在医学教育中的最佳使用和应用建立指南。
