• 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

加强医疗服务机构内部人工智能的使用:平衡监管合规和患者安全。

Strengthening the use of artificial intelligence within healthcare delivery organizations: balancing regulatory compliance and patient safety.

机构信息

Duke Institute for Health Innovation, Duke University, Durham, NC 27701, United States.

Division of Research, Kaiser Permanente, Oakland, CA 94612, United States.

出版信息

J Am Med Inform Assoc. 2024 Jun 20;31(7):1622-1627. doi: 10.1093/jamia/ocae119.

DOI:10.1093/jamia/ocae119
PMID:38767890
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11187419/
Abstract

OBJECTIVES

Surface the urgent dilemma that healthcare delivery organizations (HDOs) face navigating the US Food and Drug Administration (FDA) final guidance on the use of clinical decision support (CDS) software.

MATERIALS AND METHODS

We use sepsis as a case study to highlight the patient safety and regulatory compliance tradeoffs that 6129 hospitals in the United States must navigate.

RESULTS

Sepsis CDS remains in broad, routine use. There is no commercially available sepsis CDS system that is FDA cleared as a medical device. There is no public disclosure of an HDO turning off sepsis CDS due to regulatory compliance concerns. And there is no public disclosure of FDA enforcement action against an HDO for using sepsis CDS that is not cleared as a medical device.

DISCUSSION AND CONCLUSION

We present multiple policy interventions that would relieve the current tension to enable HDOs to utilize artificial intelligence to improve patient care while also addressing FDA concerns about product safety, efficacy, and equity.

摘要

目的

揭示医疗保健提供组织(HDO)在遵循美国食品和药物管理局(FDA)关于临床决策支持(CDS)软件使用的最终指南时所面临的紧迫困境。

材料和方法

我们以脓毒症为例,强调了美国 6129 家医院必须权衡的患者安全和法规遵从性之间的取舍。

结果

脓毒症 CDS 仍在广泛常规使用。没有经过 FDA 批准作为医疗器械的商业化可用的脓毒症 CDS 系统。没有公开披露任何 HDO 因监管合规问题而关闭脓毒症 CDS。也没有公开披露 FDA 对 HDO 使用未经医疗器械批准的脓毒症 CDS 采取执法行动的情况。

讨论与结论

我们提出了多种政策干预措施,旨在缓解当前的紧张局势,使 HDO 能够利用人工智能来改善患者护理,同时解决 FDA 对产品安全性、有效性和公平性的关注。

相似文献

1
Strengthening the use of artificial intelligence within healthcare delivery organizations: balancing regulatory compliance and patient safety.加强医疗服务机构内部人工智能的使用:平衡监管合规和患者安全。
J Am Med Inform Assoc. 2024 Jun 20;31(7):1622-1627. doi: 10.1093/jamia/ocae119.
2
Recommendations for the safe, effective use of adaptive CDS in the US healthcare system: an AMIA position paper.美国医疗保健系统中自适应 CDS 安全有效使用的建议:AMIA 立场文件。
J Am Med Inform Assoc. 2021 Mar 18;28(4):677-684. doi: 10.1093/jamia/ocaa319.
3
Industry ties and evidence in public comments on the FDA framework for modifications to artificial intelligence/machine learning-based medical devices: a cross sectional study.关于美国食品药品监督管理局(FDA)基于人工智能/机器学习的医疗器械修改框架的公众意见中的行业关系与证据:一项横断面研究
BMJ Open. 2020 Oct 14;10(10):e039969. doi: 10.1136/bmjopen-2020-039969.
4
Addressing health disparities in the Food and Drug Administration's artificial intelligence and machine learning regulatory framework.解决食品和药物管理局人工智能和机器学习监管框架中的健康差异问题。
J Am Med Inform Assoc. 2020 Dec 9;27(12):2016-2019. doi: 10.1093/jamia/ocaa133.
5
How the FDA Regulates AI.FDA 如何监管 AI
Acad Radiol. 2020 Jan;27(1):58-61. doi: 10.1016/j.acra.2019.09.017.
6
Effects of machine learning-based clinical decision support systems on decision-making, care delivery, and patient outcomes: a scoping review.基于机器学习的临床决策支持系统对决策制定、护理提供和患者结局的影响:范围综述。
J Am Med Inform Assoc. 2023 Nov 17;30(12):2050-2063. doi: 10.1093/jamia/ocad180.
7
Regulatory Framework for Clinical Decision Support Software: Present Uncertainty and Prospective Proposition.临床决策支持软件的监管框架:当前的不确定性与前瞻性建议
J Am Coll Radiol. 2015 Jul;12(7):672-5. doi: 10.1016/j.jacr.2014.12.011. Epub 2015 Mar 13.
8
FDA Perspective on the Regulation of Artificial Intelligence in Health Care and Biomedicine.美国食品药品监督管理局对医疗保健和生物医学领域人工智能监管的看法。
JAMA. 2025 Jan 21;333(3):241-247. doi: 10.1001/jama.2024.21451.
9
FDA-cleared artificial intelligence and machine learning-based medical devices and their 510(k) predicate networks.FDA 批准的人工智能和基于机器学习的医疗器械及其 510(k) 前序网络。
Lancet Digit Health. 2023 Sep;5(9):e618-e626. doi: 10.1016/S2589-7500(23)00126-7.
10
Concepts in U.S. Food and Drug Administration Regulation of Artificial Intelligence for Medical Imaging.美国食品和药物管理局对医学影像人工智能监管的概念。
AJR Am J Roentgenol. 2019 Oct;213(4):886-888. doi: 10.2214/AJR.18.20410. Epub 2019 Jun 5.

引用本文的文献

1
Rethinking clinical trials for medical AI with dynamic deployments of adaptive systems.通过自适应系统的动态部署对医学人工智能的临床试验进行重新思考。
NPJ Digit Med. 2025 May 6;8(1):252. doi: 10.1038/s41746-025-01674-3.
2
Regulation of artificial intelligence in healthcare: Clinical Laboratory Improvement Amendments (CLIA) as a model.医疗保健领域人工智能的监管:以《临床实验室改进修正案》(CLIA)为范例
J Am Med Inform Assoc. 2025 Feb 1;32(2):404-407. doi: 10.1093/jamia/ocae296.

本文引用的文献

1
FDA's proposed rule for the regulation of laboratory-developed tests.FDA 关于实验室研发测试监管的拟议规则。
J Clin Microbiol. 2024 Feb 14;62(2):e0148823. doi: 10.1128/jcm.01488-23. Epub 2024 Jan 11.
2
Deployment of machine learning algorithms to predict sepsis: systematic review and application of the SALIENT clinical AI implementation framework.部署机器学习算法预测脓毒症:SALIENT 临床人工智能实施框架的系统评价与应用。
J Am Med Inform Assoc. 2023 Jun 20;30(7):1349-1361. doi: 10.1093/jamia/ocad075.
3
Accelerating health system innovation: principles and practices from the Duke Institute for Health Innovation.加速卫生系统创新:杜克健康创新研究所的原则与实践
Patterns (N Y). 2023 Mar 22;4(4):100710. doi: 10.1016/j.patter.2023.100710. eCollection 2023 Apr 14.
4
More than algorithms: an analysis of safety events involving ML-enabled medical devices reported to the FDA.超越算法:对 FDA 报告的涉及机器学习医疗器械的安全事件的分析。
J Am Med Inform Assoc. 2023 Jun 20;30(7):1227-1236. doi: 10.1093/jamia/ocad065.
5
Factors Associated With Variability in the Performance of a Proprietary Sepsis Prediction Model Across 9 Networked Hospitals in the US.美国9家联网医院中,与一种专利脓毒症预测模型性能变异性相关的因素
JAMA Intern Med. 2023 Jun 1;183(6):611-612. doi: 10.1001/jamainternmed.2022.7182.
6
Assessment of Adherence to Reporting Guidelines by Commonly Used Clinical Prediction Models From a Single Vendor: A Systematic Review.评估单一供应商常用临床预测模型报告指南的依从性:系统评价。
JAMA Netw Open. 2022 Aug 1;5(8):e2227779. doi: 10.1001/jamanetworkopen.2022.27779.
7
Prospective, multi-site study of patient outcomes after implementation of the TREWS machine learning-based early warning system for sepsis.采用 TREWS 机器学习为基础的脓毒症早期预警系统后,对患者预后的前瞻性、多中心研究。
Nat Med. 2022 Jul;28(7):1455-1460. doi: 10.1038/s41591-022-01894-0. Epub 2022 Jul 21.
8
Improving Timeliness of Antibiotic Administration Using a Provider and Pharmacist Facing Sepsis Early Warning System in the Emergency Department Setting: A Randomized Controlled Quality Improvement Initiative.在急诊科环境中使用面向医护人员和药剂师的脓毒症早期预警系统提高抗生素使用及时性:一项随机对照质量改进计划。
Crit Care Med. 2022 Mar 1;50(3):418-427. doi: 10.1097/CCM.0000000000005267.
9
External Validation of a Widely Implemented Proprietary Sepsis Prediction Model in Hospitalized Patients.在住院患者中验证广泛实施的专有脓毒症预测模型的外部有效性。
JAMA Intern Med. 2021 Aug 1;181(8):1065-1070. doi: 10.1001/jamainternmed.2021.2626.
10
Early Prediction of Sepsis in the ICU Using Machine Learning: A Systematic Review.使用机器学习对重症监护病房中的脓毒症进行早期预测:一项系统综述。
Front Med (Lausanne). 2021 May 28;8:607952. doi: 10.3389/fmed.2021.607952. eCollection 2021.