文献速递技术与安全

ChatGPT在放射学委员会风格考试中的表现:对其当前优势与局限的洞察

Performance of ChatGPT on a Radiology Board-style Examination: Insights into Current Strengths and Limitations.
PubMed 文献 · Radiology · 2023-05-16

这项探索性前瞻性研究于2023年2月25日至3月3日进行,用150道无图像的多选题评估ChatGPT的放射学考试表现,题目风格参照加拿大皇家学院和美国放射学委员会考试。ChatGPT总体正确率为69%(104/150),低阶思维题正确率84%(51/61)高于高阶思维题60%(53/89)(P=0.002);在影像表现描述、计算与分类、概念应用类高阶题上表现较差,但在临床管理类高阶题上表现与低阶题相当(89%,16/18;P=0.88)。

要点

  • ChatGPT总体正确率69%(104/150),接近通过放射学委员会风格考试。
  • 低阶思维题正确率84%(51/61)高于高阶思维题60%(53/89)(P=0.002)。
  • 影像表现描述题正确率61%(28/46),低于低阶思维题(P=0.04)。

核心结论

  • 尽管没有放射学专项预训练,ChatGPT在无图像放射学委员会风格考试中接近通过;低阶思维题和临床管理题表现好,但高阶思维题中影像表现描述、计算与分类、概念应用题表现不佳。

研究设计与样本

  • 探索性前瞻性研究,于2023年2月25日至3月3日进行,使用150道无图像多选题,题目风格、内容和难度参照加拿大皇家学院和美国放射学委员会考试,按思维类型(低阶:回忆、理解;高阶:应用、分析、综合)和主题(物理、临床)分组。

诊断标准与关键数值

  • 总体正确率69%(104/150);低阶思维题84%(51/61)vs 高阶思维题60%(53/89)(P=0.002);影像表现描述题61%(28/46)vs 低阶思维题(P=0.04);计算与分类题25%(2/8)(P=0.01);概念应用题30%(3/10)(P=0.01);临床管理题89%(16/18)vs 低阶思维题(P=0.88);物理题40%(6/15)vs 临床题73%(98/135)(P=0.02)。

临床应用与阅片要点

  • 作者指出ChatGPT在低阶思维题和临床管理题上表现良好,但在涉及影像表现描述、计算与分类及概念应用的高阶思维题上表现不佳;模型即使回答错误也始终使用自信的语言(100%,46/46)。

局限性

  • 本研究为探索性研究,仅评估无图像的多选题,未涉及图像解读。
  • 题目数量有限,共150道。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

Background ChatGPT is a powerful artificial intelligence large language model with great potential as a tool in medical practice and education, but its performance in radiology remains unclear. Purpose To assess the performance of ChatGPT on radiology board-style examination questions without images and to explore its strengths and limitations. Materials and Methods In this exploratory prospective study performed from February 25 to March 3, 2023, 150 multiple-choice questions designed to match the style, content, and difficulty of the Canadian Royal College and American Board of Radiology examinations were grouped by question type (lower-order [recall, understanding] and higher-order [apply, analyze, synthesize] thinking) and topic (physics, clinical). The higher-order thinking questions were further subclassified by type (description of imaging findings, clinical management, application of concepts, calculation and classification, disease associations). ChatGPT performance was evaluated overall, by question type, and by topic. Confidence of language in responses was assessed. Univariable analysis was performed. Results ChatGPT answered 69% of questions correctly (104 of 150). The model performed better on questions requiring lower-order thinking (84%, 51 of 61) than on those requiring higher-order thinking (60%, 53 of 89) (P = .002). When compared with lower-order questions, the model performed worse on questions involving description of imaging findings (61%, 28 of 46; P = .04), calculation and classification (25%, two of eight; P = .01), and application of concepts (30%, three of 10; P = .01). ChatGPT performed as well on higher-order clinical management questions (89%, 16 of 18) as on lower-order questions (P = .88). It performed worse on physics questions (40%, six of 15) than on clinical questions (73%, 98 of 135) (P = .02). ChatGPT used confident language consistently, even when incorrect (100%, 46 of 46). Conclusion Despite no radiology-specific pretraining, ChatGPT nearly passed a radiology board-style examination without images; it performed well on lower-order thinking questions and clinical management questions but struggled with higher-order thinking questions involving description of imaging findings, calculation and classification, and application of concepts. © RSNA, 2023 See also the editorial by Lourenco et al and the article by Bhayana et al in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Bhayana R, Krishna S, Bleakney RR, et al. Performance of ChatGPT on a Radiology Board-style Examination: Insights into Current Strengths and Limitations. Radiology. 2023. PMID: 37191485. doi:10.1148/radiol.230582

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。