• 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

大语言模型在医疗保健专业人员和科学家方面的实际应用。

Practical Applications of Large Language Models for Health Care Professionals and Scientists.

作者信息

Reis Florian, Lenz Christian, Gossen Manfred, Volk Hans-Dieter, Drzeniek Norman Michael

机构信息

Medical Affairs, Pfizer Pharma GmbH, Berlin, Germany.

Institute of Active Polymers, Helmholtz-Zentrum Hereon, Teltow, Germany.

出版信息

JMIR Med Inform. 2024 Sep 5;12:e58478. doi: 10.2196/58478.

DOI:10.2196/58478
PMID:39235317
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11391657/
Abstract

With the popularization of large language models (LLMs), strategies for their effective and safe usage in health care and research have become increasingly pertinent. Despite the growing interest and eagerness among health care professionals and scientists to exploit the potential of LLMs, initial attempts may yield suboptimal results due to a lack of user experience, thus complicating the integration of artificial intelligence (AI) tools into workplace routine. Focusing on scientists and health care professionals with limited LLM experience, this viewpoint article highlights and discusses 6 easy-to-implement use cases of practical relevance. These encompass customizing translations, refining text and extracting information, generating comprehensive overviews and specialized insights, compiling ideas into cohesive narratives, crafting personalized educational materials, and facilitating intellectual sparring. Additionally, we discuss general prompting strategies and precautions for the implementation of AI tools in biomedicine. Despite various hurdles and challenges, the integration of LLMs into daily routines of physicians and researchers promises heightened workplace productivity and efficiency.

摘要

随着大语言模型(LLMs)的普及,在医疗保健和研究中有效且安全地使用它们的策略变得越来越重要。尽管医疗保健专业人员和科学家对挖掘大语言模型的潜力兴趣日益浓厚且热情高涨,但由于缺乏用户经验,最初的尝试可能会产生不理想的结果,从而使将人工智能(AI)工具整合到工作流程中变得复杂。针对大语言模型经验有限的科学家和医疗保健专业人员,这篇观点文章重点介绍并讨论了6个具有实际相关性且易于实施的用例。这些用例包括定制翻译、完善文本和提取信息、生成全面概述和专业见解、将想法整理成连贯的叙述、制作个性化教育材料以及促进智力交锋。此外,我们还讨论了在生物医学中实施人工智能工具的一般提示策略和注意事项。尽管存在各种障碍和挑战,但将大语言模型整合到医生和研究人员的日常工作中有望提高工作场所的生产力和效率。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6199/11391657/3d3a7edf4daf/medinform-v12-e58478-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6199/11391657/67bf1029e29e/medinform-v12-e58478-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6199/11391657/e9fdd2433324/medinform-v12-e58478-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6199/11391657/3d3a7edf4daf/medinform-v12-e58478-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6199/11391657/67bf1029e29e/medinform-v12-e58478-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6199/11391657/e9fdd2433324/medinform-v12-e58478-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6199/11391657/3d3a7edf4daf/medinform-v12-e58478-g004.jpg

相似文献

1
Practical Applications of Large Language Models for Health Care Professionals and Scientists.大语言模型在医疗保健专业人员和科学家方面的实际应用。
JMIR Med Inform. 2024 Sep 5;12:e58478. doi: 10.2196/58478.
2
Large Language Models and User Trust: Consequence of Self-Referential Learning Loop and the Deskilling of Health Care Professionals.大语言模型与用户信任:自我参照学习循环的后果及医疗保健专业人员的技能退化
J Med Internet Res. 2024 Apr 25;26:e56764. doi: 10.2196/56764.
3
Utility of Large Language Models for Health Care Professionals and Patients in Navigating Hematopoietic Stem Cell Transplantation: Comparison of the Performance of ChatGPT-3.5, ChatGPT-4, and Bard.大型语言模型在造血干细胞移植导航中对医疗保健专业人员和患者的实用性:ChatGPT-3.5、ChatGPT-4 和 Bard 的性能比较。
J Med Internet Res. 2024 May 17;26:e54758. doi: 10.2196/54758.
4
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.
5
Challenges and barriers of using large language models (LLM) such as ChatGPT for diagnostic medicine with a focus on digital pathology - a recent scoping review.使用大型语言模型(如 ChatGPT)进行诊断医学的挑战和障碍,重点是数字病理学——近期的范围综述。
Diagn Pathol. 2024 Feb 27;19(1):43. doi: 10.1186/s13000-024-01464-7.
6
The Role of Large Language Models in Transforming Emergency Medicine: Scoping Review.大型语言模型在变革急诊医学中的作用:范围综述
JMIR Med Inform. 2024 May 10;12:e53787. doi: 10.2196/53787.
7
Large language models: a primer and gastroenterology applications.大语言模型:入门介绍及胃肠病学应用
Therap Adv Gastroenterol. 2024 Feb 22;17:17562848241227031. doi: 10.1177/17562848241227031. eCollection 2024.
8
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.
9
A Systematic Review of ChatGPT and Other Conversational Large Language Models in Healthcare.ChatGPT及其他对话式大语言模型在医疗保健领域的系统评价
medRxiv. 2024 Apr 27:2024.04.26.24306390. doi: 10.1101/2024.04.26.24306390.
10
Implications of Large Language Models for Quality and Efficiency of Neurologic Care: Emerging Issues in Neurology.大语言模型对神经科护理质量和效率的影响:神经病学的新问题。
Neurology. 2024 Jun 11;102(11):e209497. doi: 10.1212/WNL.0000000000209497. Epub 2024 May 17.

引用本文的文献

1
Evaluating a Large Language Model's Ability to Synthesize a Health Science Master's Thesis: Case Study.评估大型语言模型合成健康科学硕士论文的能力:案例研究
JMIR Form Res. 2025 Jul 3;9:e73248. doi: 10.2196/73248.
2
Adoption of Large Language Model AI Tools in Everyday Tasks: Multisite Cross-Sectional Qualitative Study of Chinese Hospital Administrators.大型语言模型人工智能工具在日常任务中的应用:中国医院管理人员的多中心横断面定性研究
J Med Internet Res. 2025 Apr 1;27:e70789. doi: 10.2196/70789.
3
Can ChatGPT pass the Turkish Orthopedics and Traumatology Board Examination? Turkish orthopedic surgeons versus artificial intelligence.

本文引用的文献

1
Potential of Large Language Models in Health Care: Delphi Study.大语言模型在医疗保健中的潜力:德尔菲研究。
J Med Internet Res. 2024 May 13;26:e52399. doi: 10.2196/52399.
2
Almanac - Retrieval-Augmented Language Models for Clinical Medicine.用于临床医学的年鉴检索增强语言模型。
NEJM AI. 2024 Feb;1(2). doi: 10.1056/aioa2300068. Epub 2024 Jan 25.
3
Black Box Warning: Large Language Models and the Future of Infectious Diseases Consultation.黑框警告:大型语言模型与传染病咨询的未来。
ChatGPT能通过土耳其骨科学与创伤外科学委员会考试吗?土耳其骨科医生与人工智能的较量。
Ulus Travma Acil Cerrahi Derg. 2025 Mar;31(3):310-315. doi: 10.14744/tjtes.2025.07724.
Clin Infect Dis. 2024 Apr 10;78(4):860-866. doi: 10.1093/cid/ciad633.
4
ChatGPT in medicine: an overview of its applications, advantages, limitations, future prospects, and ethical considerations.医学领域的ChatGPT:其应用、优势、局限性、未来前景及伦理考量概述
Front Artif Intell. 2023 May 4;6:1169595. doi: 10.3389/frai.2023.1169595. eCollection 2023.
5
Ethics of large language models in medicine and medical research.医学及医学研究中大型语言模型的伦理问题。
Lancet Digit Health. 2023 Jun;5(6):e333-e335. doi: 10.1016/S2589-7500(23)00083-3. Epub 2023 Apr 27.
6
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.
7
ChatGPT Utility in Healthcare Education, Research, and Practice: Systematic Review on the Promising Perspectives and Valid Concerns.ChatGPT在医学教育、研究与实践中的应用:对其前景与合理担忧的系统评价
Healthcare (Basel). 2023 Mar 19;11(6):887. doi: 10.3390/healthcare11060887.
8
ChatGPT: the future of discharge summaries?ChatGPT:出院小结的未来?
Lancet Digit Health. 2023 Mar;5(3):e107-e108. doi: 10.1016/S2589-7500(23)00021-3. Epub 2023 Feb 6.
9
ChatGPT: five priorities for research.ChatGPT:研究的五个优先事项。
Nature. 2023 Feb;614(7947):224-226. doi: 10.1038/d41586-023-00288-7.
10
ChatGPT is fun, but not an author.ChatGPT 很有趣,但不是作者。
Science. 2023 Jan 27;379(6630):313. doi: 10.1126/science.adg7879. Epub 2023 Jan 26.