• 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

正畸学中的大语言模型：评估ChatGPT在治疗前患者教育中的可靠性和有效性。

Large-Language Models in Orthodontics: Assessing Reliability and Validity of ChatGPT in Pretreatment Patient Education.

作者信息

Vassis Stratos, Powell Harriet, Petersen Emma, Barkmann Asta, Noeldeke Beatrice, Kristensen Kasper D, Stoustrup Peter

机构信息

Section of Orthodontics, Department of Dentistry and Oral Health, Aarhus University, Aarhus, DNK.

Section of Orthodontics, Department of Dentistry and Oral Health, Aarhus Universiy, Aarhus, DNK.

出版信息

Cureus. 2024 Aug 29;16(8):e68085. doi: 10.7759/cureus.68085. eCollection 2024 Aug.

DOI:10.7759/cureus.68085
PMID:39347180
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11437517/
Abstract

BACKGROUND

Patients seeking orthodontic treatment may use large language models (LLMs) such as Chat-GPT for self-education, thereby impacting their decision-making process. This study assesses the reliability and validity of Chat-GPT prompts aimed at informing patients about orthodontic side effects and examines patients' perceptions of this information.

MATERIALS AND METHODS

To assess reliability, n = 28 individuals were asked to generate information from GPT-3.5 and Generative Pretrained Transformer 4 (GPT-4) about side effects related to orthodontic treatment using both self-formulated and standardized prompts. Three experts evaluated the content generated based on these prompts regarding its validity. We asked a cohort of 46 orthodontic patients about their perceptions after reading an AI-generated information text about orthodontic side effects and compared it with the standard text from the postgraduate orthodontic program at Aarhus University.

RESULTS

Although the GPT-generated answers mentioned several relevant side effects, the replies were diverse. The experts rated the AI-generated content generally as "neither deficient nor satisfactory," with GPT-4 achieving higher scores than GPT-3.5. The patients perceived the GPT-generated information as more useful and more comprehensive and experienced less nervousness when reading the GPT-generated information. Nearly 80% of patients preferred the AI-generated information over the standard text.

CONCLUSIONS

Although patients generally prefer AI-generated information regarding the side effects of orthodontic treatment, the tested prompts fall short of providing thoroughly satisfactory and high-quality education to patients.

摘要

背景

寻求正畸治疗的患者可能会使用Chat-GPT等大语言模型进行自我教育，从而影响他们的决策过程。本研究评估了旨在告知患者正畸副作用的Chat-GPT提示的可靠性和有效性，并考察了患者对这些信息的看法。

材料与方法

为评估可靠性，28名个体被要求使用自行制定和标准化的提示，从GPT-3.5和生成式预训练变换器4（GPT-4）生成有关正畸治疗相关副作用的信息。三位专家根据这些提示对生成的内容进行有效性评估。我们询问了46名正畸患者在阅读关于正畸副作用的人工智能生成的信息文本后的看法，并将其与奥胡斯大学正畸研究生课程的标准文本进行比较。

结果

尽管GPT生成的答案提到了几种相关副作用，但回答各不相同。专家们普遍将人工智能生成的内容评为“既不欠缺也不令人满意”，GPT-4的得分高于GPT-3.5。患者认为GPT生成的信息更有用、更全面，并且在阅读GPT生成的信息时紧张感更低。近80%的患者更喜欢人工智能生成的信息而不是标准文本。

结论

尽管患者总体上更喜欢关于正畸治疗副作用的人工智能生成的信息，但所测试的提示未能为患者提供完全令人满意和高质量的教育。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/113b/11437517/32fb0699aaf2/cureus-0016-00000068085-i04.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/113b/11437517/2191ddb5fc00/cureus-0016-00000068085-i01.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/113b/11437517/9ff5b163b30a/cureus-0016-00000068085-i02.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/113b/11437517/a7a57b7bb3bf/cureus-0016-00000068085-i03.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/113b/11437517/32fb0699aaf2/cureus-0016-00000068085-i04.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/113b/11437517/2191ddb5fc00/cureus-0016-00000068085-i01.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/113b/11437517/9ff5b163b30a/cureus-0016-00000068085-i02.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/113b/11437517/a7a57b7bb3bf/cureus-0016-00000068085-i03.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/113b/11437517/32fb0699aaf2/cureus-0016-00000068085-i04.jpg

相似文献

1
Large-Language Models in Orthodontics: Assessing Reliability and Validity of ChatGPT in Pretreatment Patient Education.正畸学中的大语言模型：评估ChatGPT在治疗前患者教育中的可靠性和有效性。
Cureus. 2024 Aug 29;16(8):e68085. doi: 10.7759/cureus.68085. eCollection 2024 Aug.
2
Assessing the Application of Large Language Models in Generating Dermatologic Patient Education Materials According to Reading Level: Qualitative Study.评估大语言模型在根据阅读水平生成皮肤科患者教育材料方面的应用：定性研究。
JMIR Dermatol. 2024 May 16;7:e55898. doi: 10.2196/55898.
3
Quality of Answers of Generative Large Language Models Versus Peer Users for Interpreting Laboratory Test Results for Lay Patients: Evaluation Study.生成式大语言模型与同行用户对解释非专业患者实验室检测结果的答案质量比较：评估研究。
J Med Internet Res. 2024 Apr 17;26:e56655. doi: 10.2196/56655.
4
Evidence-based potential of generative artificial intelligence large language models in orthodontics: a comparative study of ChatGPT, Google Bard, and Microsoft Bing.生成式人工智能大语言模型在正畸学中的循证潜力：ChatGPT、谷歌巴德和微软必应的比较研究
Eur J Orthod. 2024 Apr 13. doi: 10.1093/ejo/cjae017.
5
Learning to Make Rare and Complex Diagnoses With Generative AI Assistance: Qualitative Study of Popular Large Language Models.利用生成式人工智能辅助学习罕见且复杂的诊断：对流行的大型语言模型的定性研究。
JMIR Med Educ. 2024 Feb 13;10:e51391. doi: 10.2196/51391.
6
Quality of Answers of Generative Large Language Models vs Peer Patients for Interpreting Lab Test Results for Lay Patients: Evaluation Study.生成式大语言模型与同侪患者为非专业患者解读实验室检查结果的答案质量：评估研究
ArXiv. 2024 Jan 23:arXiv:2402.01693v1.
7
Use of Generative AI for Improving Health Literacy in Reproductive Health: Case Study.利用生成式人工智能提高生殖健康素养：案例研究
JMIR Form Res. 2024 Aug 6;8:e59434. doi: 10.2196/59434.
8
Assessing the Alignment of Large Language Models With Human Values for Mental Health Integration: Cross-Sectional Study Using Schwartz's Theory of Basic Values.评估大型语言模型与人类心理健康整合价值观的一致性：使用施瓦茨基本价值观理论的横断面研究。
JMIR Ment Health. 2024 Apr 9;11:e55988. doi: 10.2196/55988.
9
Evaluation of the Performance of Generative AI Large Language Models ChatGPT, Google Bard, and Microsoft Bing Chat in Supporting Evidence-Based Dentistry: Comparative Mixed Methods Study.评估生成式 AI 大语言模型 ChatGPT、Google Bard 和 Microsoft Bing Chat 在支持循证牙科方面的性能：比较混合方法研究。
J Med Internet Res. 2023 Dec 28;25:e51580. doi: 10.2196/51580.
10
Performance of GPT-4V in Answering the Japanese Otolaryngology Board Certification Examination Questions: Evaluation Study.GPT-4V 在回答日本耳鼻喉科学委员会认证考试问题方面的表现：评估研究。
JMIR Med Educ. 2024 Mar 28;10:e57054. doi: 10.2196/57054.

引用本文的文献

1
Reliability of Large Language Model-Based Chatbots Versus Clinicians as Sources of Information on Orthodontics: A Comparative Analysis.基于大语言模型的聊天机器人与临床医生作为正畸学信息来源的可靠性：一项比较分析。
Dent J (Basel). 2025 Jul 24;13(8):343. doi: 10.3390/dj13080343.
2
Using large language models to generate child-friendly education materials on myopia.使用大语言模型生成适合儿童的近视教育材料。
Digit Health. 2025 Jul 30;11:20552076251362338. doi: 10.1177/20552076251362338. eCollection 2025 Jan-Dec.
3
Comparative analysis of AI chatbot (ChatGPT-4.0 and Microsoft Copilot) and expert responses to common orthodontic questions: patient and orthodontist evaluations.

本文引用的文献

1
Large language models as a source of health information: Are they patient-centered? A longitudinal analysis.作为健康信息来源的大语言模型：它们是以患者为中心的吗？一项纵向分析。
Healthc (Amst). 2024 Mar;12(1):100731. doi: 10.1016/j.hjdsi.2023.100731. Epub 2023 Dec 22.
2
Application of Artificial Intelligence in Orthodontics: Current State and Future Perspectives.人工智能在正畸学中的应用：现状与未来展望。
Healthcare (Basel). 2023 Oct 18;11(20):2760. doi: 10.3390/healthcare11202760.
3
The future landscape of large language models in medicine.
人工智能聊天机器人（ChatGPT-4.0和Microsoft Copilot）与正畸专家对常见正畸问题回答的比较分析：患者和正畸医生的评估
BMC Oral Health. 2025 Jun 3;25(1):896. doi: 10.1186/s12903-025-06194-w.
4
Evaluating the impact of AI-generated educational content on patient understanding and anxiety in endodontics and restorative dentistry: a comparative study.评估人工智能生成的教育内容对牙髓病学和修复牙科学中患者理解及焦虑的影响：一项对比研究。
BMC Oral Health. 2025 May 7;25(1):689. doi: 10.1186/s12903-025-06069-0.
医学领域大语言模型的未来前景。
Commun Med (Lond). 2023 Oct 10;3(1):141. doi: 10.1038/s43856-023-00370-1.
4
Benefits, Limits, and Risks of GPT-4 as an AI Chatbot for Medicine.GPT-4作为医学人工智能聊天机器人的益处、局限性和风险
N Engl J Med. 2023 Mar 30;388(13):1233-1239. doi: 10.1056/NEJMsr2214184.
5
Artificial intelligence in orthodontics: Where are we now? A scoping review.正畸学中的人工智能：我们现在处于什么阶段？一项范围综述。
Orthod Craniofac Res. 2021 Dec;24 Suppl 2:6-15. doi: 10.1111/ocr.12517. Epub 2021 Aug 2.
6
Machine learning and orthodontics, current trends and the future opportunities: A scoping review.机器学习与口腔正畸学：当前趋势与未来机遇——范围综述。
Am J Orthod Dentofacial Orthop. 2021 Aug;160(2):170-192.e4. doi: 10.1016/j.ajodo.2021.02.013. Epub 2021 Jun 5.
7
How do healthcare professionals respond to ethical challenges regarding information management? A review of empirical studies.医疗保健专业人员如何应对信息管理方面的伦理挑战？实证研究综述。
Glob Bioeth. 2021 Apr 5;32(1):67-84. doi: 10.1080/11287462.2021.1909820.
8
Scope and performance of artificial intelligence technology in orthodontic diagnosis, treatment planning, and clinical decision-making - A systematic review.人工智能技术在正畸诊断、治疗计划和临床决策中的应用范围与性能——一项系统综述
J Dent Sci. 2021 Jan;16(1):482-492. doi: 10.1016/j.jds.2020.05.022. Epub 2020 Jun 5.
9
Adverse effects of orthodontic treatment: A clinical perspective.正畸治疗的不良反应：临床视角
Saudi Dent J. 2011 Apr;23(2):55-9. doi: 10.1016/j.sdentj.2011.01.003. Epub 2011 Jan 28.