• 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

人工智能驱动的聊天机器人在医疗保健中的效用与局限性

The Utility and Limitations of Artificial Intelligence-Powered Chatbots in Healthcare.

作者信息

Hayat Jafar, Lari Mohammad, AlHerz Mohammad, Lari Ali

机构信息

Department of Surgery, Jaber Al-Ahmad Al-Sabah Hospital, Kuwait City, KWT.

Department of Orthopedic Surgery, Al-Razi National Orthopedic Hospital, Kuwait City, KWT.

出版信息

Cureus. 2024 Nov 6;16(11):e73127. doi: 10.7759/cureus.73127. eCollection 2024 Nov.

DOI:10.7759/cureus.73127
PMID:39650926
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11624039/
Abstract

At the intersection of artificial intelligence (AI) and healthcare, it is essential that clinicians grasp the ability of chatbots. AI-powered chatbots such as ChatGPT are being explored for their potential benefits by both individuals and institutions. The utility of ChatGPT (OpenAI) in various scenarios was explored through a series of recorded prompts and responses. In the clinical aspects, the chatbot facilitated tasks such as triage, patient consultation, diagnosis, and administrative responsibilities. Their capacity to translate and simplify intricate medical topics was also evaluated. For research purposes, the chatbots' abilities to suggest ideas, prepare protocols, assist in manuscript writing, guide statistical analyses, and recommend suitable journals were assessed. In the educational domain, chatbots were tested for simplifying complex subjects, reviewing procedural steps, generating clinical scenarios, and formulating multiple-choice questions. A comprehensive literature review was also conducted across Medline, Embase, and Web of Science. Chatbots, when optimally employed, can serve as invaluable resources in healthcare, spanning clinical, research, and educational domains. Their potential lies in enhancing efficiency, guiding decision-making, and facilitating patient care and education. However, their application requires a nuanced understanding and caution regarding their limitations.

摘要

在人工智能(AI)与医疗保健的交叉领域,临床医生掌握聊天机器人的能力至关重要。诸如ChatGPT之类的人工智能驱动的聊天机器人正受到个人和机构对其潜在益处的探索。通过一系列记录的提示和回复,探讨了ChatGPT(OpenAI)在各种场景中的效用。在临床方面,聊天机器人促进了诸如分诊、患者咨询、诊断和行政职责等任务。还评估了它们翻译和简化复杂医学主题的能力。出于研究目的,评估了聊天机器人提出想法、制定方案、协助撰写稿件、指导统计分析以及推荐合适期刊的能力。在教育领域,测试了聊天机器人简化复杂主题、复习程序步骤、生成临床场景以及编写选择题的能力。还对Medline、Embase和科学网进行了全面的文献综述。聊天机器人若得到最佳应用,可成为医疗保健领域临床、研究和教育等方面的宝贵资源。它们的潜力在于提高效率、指导决策以及促进患者护理和教育。然而,它们的应用需要对其局限性有细致入微的理解并谨慎对待。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c321/11624039/6e066c87576a/cureus-0016-00000073127-i07.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c321/11624039/59ca1f745174/cureus-0016-00000073127-i01.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c321/11624039/3ec030f249d7/cureus-0016-00000073127-i02.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c321/11624039/8bc81ec92d59/cureus-0016-00000073127-i03.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c321/11624039/7df5d6f1e58c/cureus-0016-00000073127-i04.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c321/11624039/8e5d49a6f470/cureus-0016-00000073127-i05.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c321/11624039/daa167a67c85/cureus-0016-00000073127-i06.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c321/11624039/6e066c87576a/cureus-0016-00000073127-i07.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c321/11624039/59ca1f745174/cureus-0016-00000073127-i01.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c321/11624039/3ec030f249d7/cureus-0016-00000073127-i02.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c321/11624039/8bc81ec92d59/cureus-0016-00000073127-i03.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c321/11624039/7df5d6f1e58c/cureus-0016-00000073127-i04.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c321/11624039/8e5d49a6f470/cureus-0016-00000073127-i05.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c321/11624039/daa167a67c85/cureus-0016-00000073127-i06.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c321/11624039/6e066c87576a/cureus-0016-00000073127-i07.jpg

相似文献

1
The Utility and Limitations of Artificial Intelligence-Powered Chatbots in Healthcare.人工智能驱动的聊天机器人在医疗保健中的效用与局限性
Cureus. 2024 Nov 6;16(11):e73127. doi: 10.7759/cureus.73127. eCollection 2024 Nov.
2
Accuracy of Prospective Assessments of 4 Large Language Model Chatbot Responses to Patient Questions About Emergency Care: Experimental Comparative Study.前瞻性评估 4 种大型语言模型聊天机器人对患者关于急救护理问题的回答的准确性:实验性对比研究。
J Med Internet Res. 2024 Nov 4;26:e60291. doi: 10.2196/60291.
3
The performance of artificial intelligence chatbot large language models to address skeletal biology and bone health queries.人工智能聊天机器人大型语言模型在解决骨骼生物学和骨骼健康问题方面的表现。
J Bone Miner Res. 2024 Mar 22;39(2):106-115. doi: 10.1093/jbmr/zjad007.
4
Comparative assessment of artificial intelligence chatbots' performance in responding to healthcare professionals' and caregivers' questions about Dravet syndrome.人工智能聊天机器人在回答医疗专业人员和护理人员有关德雷维特综合征问题时的性能比较评估。
Epilepsia Open. 2025 Apr 1. doi: 10.1002/epi4.70022.
5
Nursing education in the age of artificial intelligence powered Chatbots (AI-Chatbots): Are we ready yet?人工智能驱动的聊天机器人(AI-Chatbots)时代的护理教育:我们准备好了吗?
Nurse Educ Today. 2023 Oct;129:105917. doi: 10.1016/j.nedt.2023.105917. Epub 2023 Jul 18.
6
Knowledge and use, perceptions of benefits and limitations of artificial intelligence chatbots among Italian physiotherapy students: a cross-sectional national study.意大利物理治疗专业学生对人工智能聊天机器人的了解与使用、对其益处和局限性的认知:一项全国性横断面研究。
BMC Med Educ. 2025 Apr 18;25(1):572. doi: 10.1186/s12909-025-07176-w.
7
A systematic review of artificial intelligence-powered (AI-powered) chatbot intervention for managing chronic illness.人工智能驱动的(AI 驱动)聊天机器人干预管理慢性疾病的系统评价。
Ann Med. 2024 Dec;56(1):2302980. doi: 10.1080/07853890.2024.2302980. Epub 2024 Mar 11.
8
AI-Powered Chatbots in Medical Education: Potential Applications and Implications.医学教育中的人工智能驱动聊天机器人:潜在应用与影响
Cureus. 2023 Aug 10;15(8):e43271. doi: 10.7759/cureus.43271. eCollection 2023 Aug.
9
Parental Perception on Usage of AI Chatbot to Understand Paediatric Otorhinolaryngology Condition: A Survey.家长对使用人工智能聊天机器人了解小儿耳鼻咽喉科疾病的认知:一项调查
Indian J Otolaryngol Head Neck Surg. 2025 May;77(5):2078-2087. doi: 10.1007/s12070-025-05451-2. Epub 2025 Apr 7.
10
User Intentions to Use ChatGPT for Self-Diagnosis and Health-Related Purposes: Cross-sectional Survey Study.用户使用ChatGPT进行自我诊断及与健康相关目的的意图:横断面调查研究。
JMIR Hum Factors. 2023 May 17;10:e47564. doi: 10.2196/47564.

引用本文的文献

1
Evaluating AI Versus Examiner Feedback in Ophthalmology Exit Examinations: A Pilot Study.评估人工智能与考官反馈在眼科结业考试中的作用:一项试点研究。
Cureus. 2025 Jul 9;17(7):e87591. doi: 10.7759/cureus.87591. eCollection 2025 Jul.
2
Accuracy and teachability of artificial intelligence chatbots in solving pharmaceutical calculations: a descriptive study.人工智能聊天机器人在解决药物计算问题中的准确性和可教性:一项描述性研究。
Int J Clin Pharm. 2025 Jun 10. doi: 10.1007/s11096-025-01947-7.

本文引用的文献

1
Does Google's Bard Chatbot perform better than ChatGPT on the European hand surgery exam?谷歌的巴德(Bard)聊天机器人在欧洲手外科考试中比 ChatGPT 表现更好吗?
Int Orthop. 2024 Jan;48(1):151-158. doi: 10.1007/s00264-023-06034-y. Epub 2023 Nov 15.
2
Assessment of ChatGPT in the Prehospital Management of Ophthalmological Emergencies - An Analysis of 10 Fictional Case Vignettes.ChatGPT在眼科急诊院前管理中的评估——对10个虚构病例 vignettes的分析
Klin Monbl Augenheilkd. 2024 May;241(5):675-681. doi: 10.1055/a-2149-0447. Epub 2023 Oct 27.
3
Evaluating ChatGPT in Medical Contexts: The Imperative to Guard Against Hallucinations and Partial Accuracies.
在医学背景下评估ChatGPT:防范幻觉和部分准确性的必要性。
Clin Gastroenterol Hepatol. 2024 May;22(5):1145-1146. doi: 10.1016/j.cgh.2023.09.035. Epub 2023 Oct 19.
4
ChatGPT-Generated Differential Diagnosis Lists for Complex Case-Derived Clinical Vignettes: Diagnostic Accuracy Evaluation.基于复杂病例临床案例生成的ChatGPT鉴别诊断列表:诊断准确性评估。
JMIR Med Inform. 2023 Oct 9;11:e48808. doi: 10.2196/48808.
5
Large Language Model-Based Chatbot vs Surgeon-Generated Informed Consent Documentation for Common Procedures.基于大语言模型的聊天机器人与外科医生生成的常见手术知情同意书文档。
JAMA Netw Open. 2023 Oct 2;6(10):e2336997. doi: 10.1001/jamanetworkopen.2023.36997.
6
ChatGPT and artificial hallucinations in stem cell research: assessing the accuracy of generated references - a preliminary study.ChatGPT与干细胞研究中的人工幻觉:评估生成参考文献的准确性——一项初步研究
Ann Med Surg (Lond). 2023 Sep 1;85(10):5275-5278. doi: 10.1097/MS9.0000000000001228. eCollection 2023 Oct.
7
Assessing the ability of an artificial intelligence chatbot to translate dermatopathology reports into patient-friendly language: A cross-sectional study.评估人工智能聊天机器人将皮肤病理学报告翻译成患者易懂语言的能力:一项横断面研究。
J Am Acad Dermatol. 2024 Feb;90(2):397-399. doi: 10.1016/j.jaad.2023.09.072. Epub 2023 Oct 5.
8
ChatGPT makes medicine easy to swallow: an exploratory case study on simplified radiology reports.ChatGPT 让医学文献通俗易懂:简化放射学报告的探索性案例研究。
Eur Radiol. 2024 May;34(5):2817-2825. doi: 10.1007/s00330-023-10213-1. Epub 2023 Oct 5.
9
Prompt Engineering as an Important Emerging Skill for Medical Professionals: Tutorial.医学专业人员的新兴技能:提示工程教程
J Med Internet Res. 2023 Oct 4;25:e50638. doi: 10.2196/50638.
10
Comparison of Diagnostic and Triage Accuracy of Ada Health and WebMD Symptom Checkers, ChatGPT, and Physicians for Patients in an Emergency Department: Clinical Data Analysis Study.Ada 健康和 WebMD 症状检查器、ChatGPT 和医生对急诊科患者的诊断和分诊准确性比较:临床数据分析研究。
JMIR Mhealth Uhealth. 2023 Oct 3;11:e49995. doi: 10.2196/49995.