GPT-4V 在回答日本耳鼻喉科医师资格考试问题时的表现:评估研究。

IF 3.2 Q1 EDUCATION, SCIENTIFIC DISCIPLINES JMIR Medical Education Pub Date : 2024-03-28 DOI:10.2196/57054
Masao Noda, Takayoshi Ueno, Ryota Koshu, Yuji Takaso, Mari Dias Shimada, Chizu Saito, Hisashi Sugimoto, Hiroaki Fushiki, Makoto Ito, Akihiro Nomura, Tomokazu Yoshizaki
{"title":"GPT-4V 在回答日本耳鼻喉科医师资格考试问题时的表现:评估研究。","authors":"Masao Noda, Takayoshi Ueno, Ryota Koshu, Yuji Takaso, Mari Dias Shimada, Chizu Saito, Hisashi Sugimoto, Hiroaki Fushiki, Makoto Ito, Akihiro Nomura, Tomokazu Yoshizaki","doi":"10.2196/57054","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Artificial intelligence models can learn from medical literature and clinical cases and generate answers that rival human experts. However, challenges remain in the analysis of complex data containing images and diagrams.</p><p><strong>Objective: </strong>This study aims to assess the answering capabilities and accuracy of ChatGPT-4 Vision (GPT-4V) for a set of 100 questions, including image-based questions, from the 2023 otolaryngology board certification examination.</p><p><strong>Methods: </strong>Answers to 100 questions from the 2023 otolaryngology board certification examination, including image-based questions, were generated using GPT-4V. The accuracy rate was evaluated using different prompts, and the presence of images, clinical area of the questions, and variations in the answer content were examined.</p><p><strong>Results: </strong>The accuracy rate for text-only input was, on average, 24.7% but improved to 47.3% with the addition of English translation and prompts (P<.001). The average nonresponse rate for text-only input was 46.3%; this decreased to 2.7% with the addition of English translation and prompts (P<.001). The accuracy rate was lower for image-based questions than for text-only questions across all types of input, with a relatively high nonresponse rate. General questions and questions from the fields of head and neck allergies and nasal allergies had relatively high accuracy rates, which increased with the addition of translation and prompts. In terms of content, questions related to anatomy had the highest accuracy rate. For all content types, the addition of translation and prompts increased the accuracy rate. As for the performance based on image-based questions, the average of correct answer rate with text-only input was 30.4%, and that with text-plus-image input was 41.3% (P=.02).</p><p><strong>Conclusions: </strong>Examination of artificial intelligence's answering capabilities for the otolaryngology board certification examination improves our understanding of its potential and limitations in this field. Although the improvement was noted with the addition of translation and prompts, the accuracy rate for image-based questions was lower than that for text-based questions, suggesting room for improvement in GPT-4V at this stage. Furthermore, text-plus-image input answers a higher rate in image-based questions. Our findings imply the usefulness and potential of GPT-4V in medicine; however, future consideration of safe use methods is needed.</p>","PeriodicalId":36236,"journal":{"name":"JMIR Medical Education","volume":null,"pages":null},"PeriodicalIF":3.2000,"publicationDate":"2024-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11009855/pdf/","citationCount":"0","resultStr":"{\"title\":\"Performance of GPT-4V in Answering the Japanese Otolaryngology Board Certification Examination Questions: Evaluation Study.\",\"authors\":\"Masao Noda, Takayoshi Ueno, Ryota Koshu, Yuji Takaso, Mari Dias Shimada, Chizu Saito, Hisashi Sugimoto, Hiroaki Fushiki, Makoto Ito, Akihiro Nomura, Tomokazu Yoshizaki\",\"doi\":\"10.2196/57054\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Artificial intelligence models can learn from medical literature and clinical cases and generate answers that rival human experts. However, challenges remain in the analysis of complex data containing images and diagrams.</p><p><strong>Objective: </strong>This study aims to assess the answering capabilities and accuracy of ChatGPT-4 Vision (GPT-4V) for a set of 100 questions, including image-based questions, from the 2023 otolaryngology board certification examination.</p><p><strong>Methods: </strong>Answers to 100 questions from the 2023 otolaryngology board certification examination, including image-based questions, were generated using GPT-4V. The accuracy rate was evaluated using different prompts, and the presence of images, clinical area of the questions, and variations in the answer content were examined.</p><p><strong>Results: </strong>The accuracy rate for text-only input was, on average, 24.7% but improved to 47.3% with the addition of English translation and prompts (P<.001). The average nonresponse rate for text-only input was 46.3%; this decreased to 2.7% with the addition of English translation and prompts (P<.001). The accuracy rate was lower for image-based questions than for text-only questions across all types of input, with a relatively high nonresponse rate. General questions and questions from the fields of head and neck allergies and nasal allergies had relatively high accuracy rates, which increased with the addition of translation and prompts. In terms of content, questions related to anatomy had the highest accuracy rate. For all content types, the addition of translation and prompts increased the accuracy rate. As for the performance based on image-based questions, the average of correct answer rate with text-only input was 30.4%, and that with text-plus-image input was 41.3% (P=.02).</p><p><strong>Conclusions: </strong>Examination of artificial intelligence's answering capabilities for the otolaryngology board certification examination improves our understanding of its potential and limitations in this field. Although the improvement was noted with the addition of translation and prompts, the accuracy rate for image-based questions was lower than that for text-based questions, suggesting room for improvement in GPT-4V at this stage. Furthermore, text-plus-image input answers a higher rate in image-based questions. Our findings imply the usefulness and potential of GPT-4V in medicine; however, future consideration of safe use methods is needed.</p>\",\"PeriodicalId\":36236,\"journal\":{\"name\":\"JMIR Medical Education\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2024-03-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11009855/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"JMIR Medical Education\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2196/57054\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"EDUCATION, SCIENTIFIC DISCIPLINES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"JMIR Medical Education","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2196/57054","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"EDUCATION, SCIENTIFIC DISCIPLINES","Score":null,"Total":0}
引用次数: 0

摘要

背景:人工智能模型可以从医学文献和临床病例中学习,并生成可与人类专家相媲美的答案。然而,在分析包含图像和图表的复杂数据方面仍存在挑战:本研究旨在评估 ChatGPT-4 Vision(GPT-4V)对 2023 年耳鼻喉科医师资格认证考试中 100 道题目(包括基于图像的题目)的回答能力和准确性:方法:使用 GPT-4V 生成 2023 年耳鼻喉科医师资格认证考试中 100 道问题的答案,其中包括基于图像的问题。结果:纯文本输入的准确率为0.5%,而纯文字输入的准确率为0.5%,纯文本输入的准确率为0.5%,而纯文字输入的准确率为0.5%:结果:纯文本输入的准确率平均为 24.7%,但在增加了英文翻译和提示后,准确率提高到 47.3%(结论:对人工智能回答能力的研究表明,人工智能在回答临床问题方面具有很高的准确率:对人工智能在耳鼻喉科医师资格认证考试中的答题能力进行研究,有助于我们更好地了解人工智能在这一领域的潜力和局限性。虽然增加翻译和提示后,答题准确率有所提高,但图像题的答题准确率低于文本题,这表明 GPT-4V 在现阶段仍有改进的余地。此外,在基于图像的问题中,文字加图像输入的答案正确率更高。我们的研究结果表明,GPT-4V 在医学领域具有实用性和潜力;但是,未来还需要考虑安全使用方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Performance of GPT-4V in Answering the Japanese Otolaryngology Board Certification Examination Questions: Evaluation Study.

Background: Artificial intelligence models can learn from medical literature and clinical cases and generate answers that rival human experts. However, challenges remain in the analysis of complex data containing images and diagrams.

Objective: This study aims to assess the answering capabilities and accuracy of ChatGPT-4 Vision (GPT-4V) for a set of 100 questions, including image-based questions, from the 2023 otolaryngology board certification examination.

Methods: Answers to 100 questions from the 2023 otolaryngology board certification examination, including image-based questions, were generated using GPT-4V. The accuracy rate was evaluated using different prompts, and the presence of images, clinical area of the questions, and variations in the answer content were examined.

Results: The accuracy rate for text-only input was, on average, 24.7% but improved to 47.3% with the addition of English translation and prompts (P<.001). The average nonresponse rate for text-only input was 46.3%; this decreased to 2.7% with the addition of English translation and prompts (P<.001). The accuracy rate was lower for image-based questions than for text-only questions across all types of input, with a relatively high nonresponse rate. General questions and questions from the fields of head and neck allergies and nasal allergies had relatively high accuracy rates, which increased with the addition of translation and prompts. In terms of content, questions related to anatomy had the highest accuracy rate. For all content types, the addition of translation and prompts increased the accuracy rate. As for the performance based on image-based questions, the average of correct answer rate with text-only input was 30.4%, and that with text-plus-image input was 41.3% (P=.02).

Conclusions: Examination of artificial intelligence's answering capabilities for the otolaryngology board certification examination improves our understanding of its potential and limitations in this field. Although the improvement was noted with the addition of translation and prompts, the accuracy rate for image-based questions was lower than that for text-based questions, suggesting room for improvement in GPT-4V at this stage. Furthermore, text-plus-image input answers a higher rate in image-based questions. Our findings imply the usefulness and potential of GPT-4V in medicine; however, future consideration of safe use methods is needed.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
JMIR Medical Education
JMIR Medical Education Social Sciences-Education
CiteScore
6.90
自引率
5.60%
发文量
54
审稿时长
8 weeks
期刊最新文献
ChatGPT-4 Omni Performance in USMLE Disciplines and Clinical Skills: Comparative Analysis. Leveraging the Electronic Health Record to Measure Resident Clinical Experiences and Identify Training Gaps: Development and Usability Study. The Potential of Artificial Intelligence Tools for Reducing Uncertainty in Medicine and Directions for Medical Education. A Pilot Project to Promote Research Competency in Medical Students Through Journal Clubs: Mixed Methods Study. Transforming the Future of Digital Health Education: Redesign of a Graduate Program Using Competency Mapping.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1