• 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

探索 ChatGPT 的能力:评估其在处理幽门螺杆菌相关查询时的准确性和可重复性。

Exploring the capacities of ChatGPT: A comprehensive evaluation of its accuracy and repeatability in addressing helicobacter pylori-related queries.

机构信息

Department of Gastroenterology, Ganzhou People's Hospital, Jiangxi Medical College, Nanchang University, Nanchang, China.

Department of Gastroenterology, Shanghai Changhai Hospital, Naval Medical University, Shanghai, China.

出版信息

Helicobacter. 2024 May-Jun;29(3):e13078. doi: 10.1111/hel.13078.

DOI:10.1111/hel.13078
PMID:38867649
Abstract

BACKGROUND

Educational initiatives on Helicobacter pylori (H. pylori) constitute a highly effective approach for preventing its infection and establishing standardized protocols for its eradication. ChatGPT, a large language model, is a potentially patient-friendly online tool capable of providing health-related knowledge. This study aims to assess the accuracy and repeatability of ChatGPT in responding to questions related to H. pylori.

MATERIALS AND METHODS

Twenty-one common questions about H. pylori were collected and categorized into four domains: basic knowledge, diagnosis, treatment, and prevention. ChatGPT was utilized to individually answer the aforementioned 21 questions. Its responses were independently assessed by two experts on H. pylori. Questions with divergent ratings were resolved by a third reviewer. Cohen's kappa coefficient was calculated to assess the consistency between the scores of the two reviewers.

RESULTS

The responses of ChatGPT on H. pylori-related questions were generally satisfactory, with 61.9% marked as "completely correct" and 33.33% as "correct but inadequate." The repeatability of the responses of ChatGPT to H. pylori-related questions was 95.23%. Among the responses, those related to prevention (comprehensive: 75%) had the best response, followed by those on treatment (comprehensive: 66.7%), basic knowledge (comprehensive: 60%), and diagnosis (comprehensive: 50%). In the "treatment" domain, 16.6% of the ChatGPT responses were categorized as "mixed with correct or incorrect/outdated data." However, ChatGPT still lacks relevant knowledge regarding H. pylori resistance and the use of sensitive antibiotics.

CONCLUSIONS

ChatGPT can provide correct answers to the majority of H. pylori-related queries. It exhibited good reproducibility and delivered responses that were easily comprehensible to patients. Further enhancement of real-time information updates and correction of inaccurate information will make ChatGPT an essential auxiliary tool for providing accurate H. pylori-related health information to patients.

摘要

背景

关于幽门螺杆菌(H. pylori)的教育计划是预防其感染和建立标准化根除方案的一种非常有效的方法。ChatGPT 是一种大型语言模型,是一种具有潜在患者友好性的在线工具,能够提供健康相关知识。本研究旨在评估 ChatGPT 在回答与 H. pylori 相关问题时的准确性和可重复性。

材料与方法

收集了 21 个关于 H. pylori 的常见问题,并分为四个领域:基础知识、诊断、治疗和预防。利用 ChatGPT 分别回答上述 21 个问题。由两位 H. pylori 专家对其回答进行独立评估。对评分存在分歧的问题,由第三位审稿人进行裁决。计算 Cohen's kappa 系数以评估两位审稿人评分的一致性。

结果

ChatGPT 对 H. pylori 相关问题的回答总体上令人满意,61.9%标记为“完全正确”,33.33%标记为“正确但不充分”。ChatGPT 对 H. pylori 相关问题的回答的可重复性为 95.23%。在回答中,与预防相关的问题(全面:75%)回答最好,其次是治疗(全面:66.7%)、基础知识(全面:60%)和诊断(全面:50%)。在“治疗”领域,16.6%的 ChatGPT 回答被归类为“包含正确或错误/过时的数据”。然而,ChatGPT 仍然缺乏有关 H. pylori 耐药性和敏感抗生素使用的相关知识。

结论

ChatGPT 可以为大多数 H. pylori 相关问题提供正确答案。它表现出良好的重现性,并为患者提供易于理解的回答。进一步增强实时信息更新和纠正不准确信息的能力,将使 ChatGPT 成为向患者提供准确的 H. pylori 相关健康信息的重要辅助工具。

相似文献

1
Exploring the capacities of ChatGPT: A comprehensive evaluation of its accuracy and repeatability in addressing helicobacter pylori-related queries.探索 ChatGPT 的能力:评估其在处理幽门螺杆菌相关查询时的准确性和可重复性。
Helicobacter. 2024 May-Jun;29(3):e13078. doi: 10.1111/hel.13078.
2
Assessing Accuracy of ChatGPT on Addressing Helicobacter pylori Infection-Related Questions: A National Survey and Comparative Study.评估 ChatGPT 在解答与幽门螺杆菌感染相关问题方面的准确性:一项全国性调查和对比研究。
Helicobacter. 2024 Jul-Aug;29(4):e13116. doi: 10.1111/hel.13116.
3
Letter to the Editor Regarding the Article: "Exploring the Capacities of ChatGPT: A Comprehensive Evaluation of Its Accuracy and Repeatability in Addressing Helicobacter pylori-Related Queries".致编辑的信:关于文章《探索ChatGPT的能力:对其在解答幽门螺杆菌相关问题时的准确性和可重复性的全面评估》
Helicobacter. 2024 Jul-Aug;29(4):e13131. doi: 10.1111/hel.13131.
4
Is ChatGPT accurate and reliable in answering questions regarding head and neck cancer?ChatGPT在回答有关头颈癌的问题时准确可靠吗?
Front Oncol. 2023 Dec 1;13:1256459. doi: 10.3389/fonc.2023.1256459. eCollection 2023.
5
Evaluating accuracy and reproducibility of ChatGPT responses to patient-based questions in Ophthalmology: An observational study.评估 ChatGPT 对眼科患者问题回答的准确性和可重复性:一项观察性研究。
Medicine (Baltimore). 2024 Aug 9;103(32):e39120. doi: 10.1097/MD.0000000000039120.
6
A Multidisciplinary Assessment of ChatGPT's Knowledge of Amyloidosis: Observational Study.对ChatGPT关于淀粉样变性知识的多学科评估:观察性研究。
JMIR Cardio. 2024 Apr 19;8:e53421. doi: 10.2196/53421.
7
Performance of large language models on benign prostatic hyperplasia frequently asked questions.大语言模型在良性前列腺增生常见问题解答方面的表现。
Prostate. 2024 Jun;84(9):807-813. doi: 10.1002/pros.24699. Epub 2024 Apr 1.
8
Appropriateness of ChatGPT in Answering Heart Failure Related Questions.ChatGPT 在回答心力衰竭相关问题方面的适宜性。
Heart Lung Circ. 2024 Sep;33(9):1314-1318. doi: 10.1016/j.hlc.2024.03.005. Epub 2024 May 31.
9
Comparative analysis of large language models in medical counseling: A focus on Helicobacter pylori infection.大语言模型在医学咨询中的比较分析:以幽门螺杆菌感染为例。
Helicobacter. 2024 Jan-Feb;29(1):e13055. doi: 10.1111/hel.13055.
10
ChatGPT accurately performs genetic counseling for gynecologic cancers.ChatGPT 能准确地为妇科癌症提供遗传咨询。
Gynecol Oncol. 2024 Apr;183:115-119. doi: 10.1016/j.ygyno.2024.04.006. Epub 2024 Apr 26.

引用本文的文献

1
Diastasis recti abdominis: A comprehensive review.腹直肌分离:一项全面综述。
Hernia. 2025 Jul 7;29(1):222. doi: 10.1007/s10029-025-03417-5.
2
Comparative evaluation of the accuracy and reliability of ChatGPT versions in providing information on infection.ChatGPT不同版本在提供感染相关信息方面的准确性和可靠性的比较评估
Front Public Health. 2025 May 15;13:1566982. doi: 10.3389/fpubh.2025.1566982. eCollection 2025.
3
Knowledge, attitude, and practice toward Helicobacter pylori among residents in Northeast China‌.中国东北地区居民对幽门螺杆菌的认知、态度及行为
Sci Rep. 2025 May 1;15(1):15288. doi: 10.1038/s41598-025-00323-9.
4
Perceptions of Artificial Intelligence Among Gastroenterologists in Italy: A National Survey.意大利胃肠病学家对人工智能的认知:一项全国性调查。
Cancers (Basel). 2025 Apr 17;17(8):1353. doi: 10.3390/cancers17081353.
5
Large Language Models' Responses to Spinal Cord Injury: A Comparative Study of Performance.大语言模型对脊髓损伤的反应:性能比较研究
J Med Syst. 2025 Mar 25;49(1):39. doi: 10.1007/s10916-025-02170-7.
6
Advantages and limitations of large language models for antibiotic prescribing and antimicrobial stewardship.大型语言模型在抗生素处方和抗菌药物管理方面的优势与局限性
NPJ Antimicrob Resist. 2025 Feb 27;3(1):14. doi: 10.1038/s44259-025-00084-5.
7
Potential application of ChatGPT in disease relevant queries.ChatGPT在疾病相关查询中的潜在应用。
Front Med (Lausanne). 2024 Oct 10;11:1489117. doi: 10.3389/fmed.2024.1489117. eCollection 2024.
8
The Application of Large Language Models in Gastroenterology: A Review of the Literature.大语言模型在胃肠病学中的应用:文献综述
Cancers (Basel). 2024 Sep 28;16(19):3328. doi: 10.3390/cancers16193328.