• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

牙科放射学中的人工智能——利用ChatGPT提高报告效率：比较研究

AI in Dental Radiology-Improving the Efficiency of Reporting With ChatGPT: Comparative Study.

作者信息

Stephan Daniel, Bertsch Annika, Burwinkel Matthias, Vinayahalingam Shankeeth, Al-Nawas Bilal, Kämmerer Peer W, Thiem Daniel Ge

机构信息

Department of Oral and Maxillofacial Surgery, Facial Plastic Surgery, University Medical Centre of the Johannes Gutenberg-University Mainz, Mainz, Germany.

Department of Oral and Maxillofacial Surgery, Radboud University Medical Center, Nijmegen, Netherlands.

出版信息

J Med Internet Res. 2024 Dec 23;26:e60684. doi: 10.2196/60684.

DOI:10.2196/60684
PMID:39714078
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11704643/
Abstract

BACKGROUND

Structured and standardized documentation is critical for accurately recording diagnostic findings, treatment plans, and patient progress in health care. Manual documentation can be labor-intensive and error-prone, especially under time constraints, prompting interest in the potential of artificial intelligence (AI) to automate and optimize these processes, particularly in medical documentation.

OBJECTIVE

This study aimed to assess the effectiveness of ChatGPT (OpenAI) in generating radiology reports from dental panoramic radiographs, comparing the performance of AI-generated reports with those manually created by dental students.

METHODS

A total of 100 dental students were tasked with analyzing panoramic radiographs and generating radiology reports manually or assisted by ChatGPT using a standardized prompt derived from a diagnostic checklist.

RESULTS

Reports generated by ChatGPT showed a high degree of textual similarity to reference reports; however, they often lacked critical diagnostic information typically included in reports authored by students. Despite this, the AI-generated reports were consistent in being error-free and matched the readability of student-generated reports.

CONCLUSIONS

The findings from this study suggest that ChatGPT has considerable potential for generating radiology reports, although it currently faces challenges in accuracy and reliability. This underscores the need for further refinement in the AI's prompt design and the development of robust validation mechanisms to enhance its use in clinical settings.

摘要

背景

结构化和标准化的文档记录对于在医疗保健中准确记录诊断结果、治疗计划和患者进展至关重要。手动文档记录可能耗费大量人力且容易出错，尤其是在时间限制下，这引发了人们对人工智能（AI）自动化和优化这些流程的潜力的兴趣，特别是在医疗文档方面。

目的

本研究旨在评估ChatGPT（OpenAI）从牙科全景X光片生成放射学报告的有效性，并将人工智能生成的报告与牙科学生手动创建的报告的性能进行比较。

方法

共有100名牙科学生被要求分析全景X光片，并使用从诊断清单得出的标准化提示手动生成或在ChatGPT辅助下生成放射学报告。

结果

ChatGPT生成的报告与参考报告显示出高度的文本相似性；然而，它们通常缺少学生撰写的报告中通常包含的关键诊断信息。尽管如此，人工智能生成的报告在无错误方面是一致的，并且与学生生成的报告的可读性相当。

结论

本研究的结果表明，ChatGPT在生成放射学报告方面具有相当大的潜力，尽管它目前在准确性和可靠性方面面临挑战。这凸显了进一步完善人工智能的提示设计以及开发强大的验证机制以增强其在临床环境中的应用的必要性。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/834e6899bbd2/jmir_v26i1e60684_fig9.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/920e64f68c6c/jmir_v26i1e60684_fig1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/e0421f816769/jmir_v26i1e60684_fig2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/4cfc840001bb/jmir_v26i1e60684_fig3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/380c49d2e2d3/jmir_v26i1e60684_fig4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/08006375ef8a/jmir_v26i1e60684_fig5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/f7dad620d27a/jmir_v26i1e60684_fig6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/4d618e7ec23d/jmir_v26i1e60684_fig7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/f7fa536eea19/jmir_v26i1e60684_fig8.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/834e6899bbd2/jmir_v26i1e60684_fig9.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/920e64f68c6c/jmir_v26i1e60684_fig1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/e0421f816769/jmir_v26i1e60684_fig2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/4cfc840001bb/jmir_v26i1e60684_fig3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/380c49d2e2d3/jmir_v26i1e60684_fig4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/08006375ef8a/jmir_v26i1e60684_fig5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/f7dad620d27a/jmir_v26i1e60684_fig6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/4d618e7ec23d/jmir_v26i1e60684_fig7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/f7fa536eea19/jmir_v26i1e60684_fig8.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/91c9/11704643/834e6899bbd2/jmir_v26i1e60684_fig9.jpg

相似文献

1
AI in Dental Radiology-Improving the Efficiency of Reporting With ChatGPT: Comparative Study.牙科放射学中的人工智能——利用ChatGPT提高报告效率：比较研究
J Med Internet Res. 2024 Dec 23;26:e60684. doi: 10.2196/60684.
2
Practical Evaluation of ChatGPT Performance for Radiology Report Generation.ChatGPT 在放射科报告生成中的实际应用评估。
Acad Radiol. 2024 Dec;31(12):4823-4832. doi: 10.1016/j.acra.2024.07.020. Epub 2024 Aug 13.
3
ChatGPT and assistive AI in structured radiology reporting: A systematic review.ChatGPT 和辅助人工智能在结构化放射学报告中的应用：一项系统评价。
Curr Probl Diagn Radiol. 2024 Nov-Dec;53(6):728-737. doi: 10.1067/j.cpradiol.2024.07.007. Epub 2024 Jul 9.
4
Optimizing ChatGPT's Interpretation and Reporting of Delirium Assessment Outcomes: Exploratory Study.优化 ChatGPT 对谵妄评估结果的解释和报告：探索性研究。
JMIR Form Res. 2024 Oct 1;8:e51383. doi: 10.2196/51383.
5
Probing clarity: AI-generated simplified breast imaging reports for enhanced patient comprehension powered by ChatGPT-4o.探索清晰度：由 ChatGPT-4o 提供支持的人工智能生成的简化乳腺成像报告，以增强患者理解。
Eur Radiol Exp. 2024 Oct 30;8(1):124. doi: 10.1186/s41747-024-00526-1.
6
Evaluating the performance of Generative Pre-trained Transformer-4 (GPT-4) in standardizing radiology reports.评估生成式预训练变换器4（GPT-4）在规范放射学报告方面的性能。
Eur Radiol. 2024 Jun;34(6):3566-3574. doi: 10.1007/s00330-023-10384-x. Epub 2023 Nov 8.
7
Decoding medical jargon: The use of AI language models (ChatGPT-4, BARD, microsoft copilot) in radiology reports.解读医学行话：人工智能语言模型（ChatGPT-4、BARD、microsoft copilot）在放射科报告中的应用。
Patient Educ Couns. 2024 Sep;126:108307. doi: 10.1016/j.pec.2024.108307. Epub 2024 May 3.
8
Comparative analysis of diagnostic accuracy in endodontic assessments: dental students vs. artificial intelligence.牙髓评估诊断准确性的对比分析：牙科学学生与人工智能。
Diagnosis (Berl). 2024 May 3;11(3):259-265. doi: 10.1515/dx-2024-0034. eCollection 2024 Aug 1.
9
Gemini AI vs. ChatGPT: A comprehensive examination alongside ophthalmology residents in medical knowledge.Gemini人工智能与ChatGPT对比：与眼科住院医师一起对医学知识进行的全面考察
Graefes Arch Clin Exp Ophthalmol. 2025 Feb;263(2):527-536. doi: 10.1007/s00417-024-06625-4. Epub 2024 Sep 15.
10
Using ChatGPT-4 to Create Structured Medical Notes From Audio Recordings of Physician-Patient Encounters: Comparative Study.利用 ChatGPT-4 从医患对话的音频记录中创建结构化的医疗记录：比较研究。
J Med Internet Res. 2024 Apr 22;26:e54419. doi: 10.2196/54419.

引用本文的文献

1
Keyword-based AI assistance in the generation of radiology reports: A pilot study.基于关键词的人工智能辅助生成放射学报告：一项试点研究。
NPJ Digit Med. 2025 Aug 1;8(1):490. doi: 10.1038/s41746-025-01889-4.
2
Improving Patient Communication by Simplifying AI-Generated Dental Radiology Reports With ChatGPT: Comparative Study.通过使用ChatGPT简化人工智能生成的牙科放射学报告来改善患者沟通：比较研究
J Med Internet Res. 2025 Jun 9;27:e73337. doi: 10.2196/73337.
3
Young Adult Perspectives on Artificial Intelligence-Based Medication Counseling in China: Discrete Choice Experiment.

本文引用的文献

1
Comparative analysis of diagnostic accuracy in endodontic assessments: dental students vs. artificial intelligence.牙髓评估诊断准确性的对比分析：牙科学学生与人工智能。
Diagnosis (Berl). 2024 May 3;11(3):259-265. doi: 10.1515/dx-2024-0034. eCollection 2024 Aug 1.
2
ChatGPT's Performance in Cardiac Arrest and Bradycardia Simulations Using the American Heart Association's Advanced Cardiovascular Life Support Guidelines: Exploratory Study.ChatGPT 在使用美国心脏协会高级心血管生命支持指南进行心脏骤停和心动过缓模拟中的表现：探索性研究。
J Med Internet Res. 2024 Apr 22;26:e55037. doi: 10.2196/55037.
3
Can large language models reason about medical questions?
中国年轻人对基于人工智能的药物咨询的看法：离散选择实验
J Med Internet Res. 2025 Apr 9;27:e67744. doi: 10.2196/67744.
大型语言模型能对医学问题进行推理吗？
Patterns (N Y). 2024 Mar 1;5(3):100943. doi: 10.1016/j.patter.2024.100943. eCollection 2024 Mar 8.
4
The future of radiology and radiologists: AI is pivotal but not the only change afoot.放射学和放射科医生的未来：人工智能是关键，但不是唯一的变化。
J Med Imaging Radiat Sci. 2024 Dec;55(4):101377. doi: 10.1016/j.jmir.2024.02.002. Epub 2024 Feb 24.
5
Artificial Intelligence in Radiology: Opportunities and Challenges.人工智能在放射学中的应用：机遇与挑战。
Semin Ultrasound CT MR. 2024 Apr;45(2):152-160. doi: 10.1053/j.sult.2024.02.004. Epub 2024 Feb 23.
6
Readability of cerebrovascular diseases online educational material from major cerebrovascular organizations.主要脑血管组织的脑血管疾病在线教育材料的可读性
J Neurointerv Surg. 2024 Feb 23. doi: 10.1136/jnis-2023-021205.
7
For any disease a human can imagine, ChatGPT can generate a fake report.对于人类能想象到的任何疾病，ChatGPT都能生成一份虚假报告。
Diagnosis (Berl). 2024 Feb 23;11(3):329-332. doi: 10.1515/dx-2024-0007. eCollection 2024 Aug 1.
8
Can ChatGPT assist authors with abstract writing in medical journals? Evaluating the quality of scientific abstracts generated by ChatGPT and original abstracts.ChatGPT 能否协助医学期刊的作者撰写摘要？评估 ChatGPT 生成的科学摘要和原始摘要的质量。
PLoS One. 2024 Feb 14;19(2):e0297701. doi: 10.1371/journal.pone.0297701. eCollection 2024.
9
Usefulness and Accuracy of Artificial Intelligence Chatbot Responses to Patient Questions for Neurosurgical Procedures.人工智能聊天机器人对神经外科手术患者问题回答的实用性和准确性
Neurosurgery. 2024 Feb 14. doi: 10.1227/neu.0000000000002856.
10
Artificial Intelligence Language Model Performance for Rapid Intraoperative Queries in Plastic Surgery: ChatGPT and the Deep Inferior Epigastric Perforator Flap.人工智能语言模型在整形手术中快速术中查询的性能：ChatGPT与腹壁下动脉穿支皮瓣
J Clin Med. 2024 Feb 4;13(3):900. doi: 10.3390/jcm13030900.