• 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

符合人工智能法规的人工智能设计与验证嵌套模型实施协议。

Protocol for implementing the nested model for AI design and validation in compliance with AI regulations.

作者信息

Dubey Akshat, Yang Zewen, Anžel Aleksandar, Hattab Georges

机构信息

Center for Artificial Intelligence in the Public Health Research (ZKI-PH) at Robert Koch Institute, Nordufer 20, 13353 Berlin, Germany; Department of Mathematics and Computer Science, Freie Universität Berlin, Arnimallee 14, 14195 Berlin, Germany.

Center for Artificial Intelligence in the Public Health Research (ZKI-PH) at Robert Koch Institute, Nordufer 20, 13353 Berlin, Germany.

出版信息

STAR Protoc. 2025 Apr 11;6(2):103771. doi: 10.1016/j.xpro.2025.103771.

DOI:10.1016/j.xpro.2025.103771
PMID:40220299
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12018536/
Abstract

Here, we present a protocol for implementing the nested model for developing and validating artificial intelligence (AI) systems in compliance with AI regulations. We describe steps for defining the regulations and associated ethical and technical key requirements through the potential research questions. We then detail the procedures for designing and validating an AI application across the domain, data, model, and prediction layers, enabling users to interact with layers through a front-end interface. For complete information on the generation and use of this protocol, please refer to Dubey et al..

摘要

在此，我们展示了一个用于实施嵌套模型的协议，该模型用于开发和验证符合人工智能法规的人工智能（AI）系统。我们描述了通过潜在研究问题来定义法规以及相关伦理和技术关键要求的步骤。然后，我们详细说明了跨领域、数据、模型和预测层设计和验证AI应用程序的程序，使用户能够通过前端界面与各层进行交互。有关此协议的生成和使用的完整信息，请参考杜比等人的文献。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3e10/12018536/211010bc61b7/gr2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3e10/12018536/5f4f0cc77b71/fx1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3e10/12018536/cf691a0dc55c/gr1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3e10/12018536/211010bc61b7/gr2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3e10/12018536/5f4f0cc77b71/fx1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3e10/12018536/cf691a0dc55c/gr1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3e10/12018536/211010bc61b7/gr2.jpg

相似文献

1
Protocol for implementing the nested model for AI design and validation in compliance with AI regulations.符合人工智能法规的人工智能设计与验证嵌套模型实施协议。
STAR Protoc. 2025 Apr 11;6(2):103771. doi: 10.1016/j.xpro.2025.103771.
2
AI-Driven Antimicrobial Peptide Discovery: Mining and Generation.人工智能驱动的抗菌肽发现：挖掘与生成
Acc Chem Res. 2025 Jun 17;58(12):1831-1846. doi: 10.1021/acs.accounts.0c00594. Epub 2025 Jun 3.
3
Expectations and Requirements of Surgical Staff for an AI-Supported Clinical Decision Support System for Older Patients: Qualitative Study.外科医护人员对用于老年患者的人工智能支持临床决策支持系统的期望与要求：定性研究
JMIR Aging. 2024 Dec 17;7:e57899. doi: 10.2196/57899.
4
Trust, Trustworthiness, and the Future of Medical AI: Outcomes of an Interdisciplinary Expert Workshop.信任、可信度与医学人工智能的未来：跨学科专家研讨会成果
J Med Internet Res. 2025 Jun 2;27:e71236. doi: 10.2196/71236.
5
What makes a 'good' decision with artificial intelligence? A grounded theory study in paediatric care.如何利用人工智能做出“好”的决策？一项关于儿科护理的扎根理论研究。
BMJ Evid Based Med. 2025 May 20;30(3):183-193. doi: 10.1136/bmjebm-2024-112919.
6
Safety and User Experience of a Generative Artificial Intelligence Digital Mental Health Intervention: Exploratory Randomized Controlled Trial.生成式人工智能数字心理健康干预的安全性与用户体验：探索性随机对照试验
J Med Internet Res. 2025 May 23;27:e67365. doi: 10.2196/67365.
7
A deep learning approach to direct immunofluorescence pattern recognition in autoimmune bullous diseases.深度学习方法在自身免疫性大疱性疾病中的直接免疫荧光模式识别。
Br J Dermatol. 2024 Jul 16;191(2):261-266. doi: 10.1093/bjd/ljae142.
8
Transcriptome analysis and artificial intelligence for predicting lymph node metastasis of esophageal squamous cell carcinoma.用于预测食管鳞状细胞癌淋巴结转移的转录组分析与人工智能
J Thorac Dis. 2025 May 30;17(5):3283-3296. doi: 10.21037/jtd-2025-662. Epub 2025 May 28.
9
A Systematic Review and Bibliometric Analysis of Applications of Artificial Intelligence and Machine Learning in Vascular Surgery.人工智能和机器学习在血管外科应用的系统评价与文献计量分析
Ann Vasc Surg. 2022 Sep;85:395-405. doi: 10.1016/j.avsg.2022.03.019. Epub 2022 Mar 24.
10
AI chatbots in pet health care: Opportunities and challenges for owners.宠物保健中的 AI 聊天机器人：主人的机遇与挑战。
Vet Med Sci. 2024 May;10(3):e1464. doi: 10.1002/vms3.1464.

本文引用的文献

1
Collaborative weighting in federated graph neural networks for disease classification with the human-in-the-loop.联邦图神经网络中的协同加权方法，用于有人类参与的疾病分类。
Sci Rep. 2024 Sep 19;14(1):21839. doi: 10.1038/s41598-024-72748-7.
2
A nested model for AI design and validation.一种用于人工智能设计与验证的嵌套模型。
iScience. 2024 Jul 30;27(9):110603. doi: 10.1016/j.isci.2024.110603. eCollection 2024 Sep 20.
3
CLARUS: An interactive explainable AI platform for manual counterfactuals in graph neural networks.CLARUS：一个用于图神经网络中人工反事实的交互式可解释 AI 平台。
J Biomed Inform. 2024 Feb;150:104600. doi: 10.1016/j.jbi.2024.104600. Epub 2024 Jan 30.
4
The FeatureCloud Platform for Federated Learning in Biomedicine: Unified Approach.FeatureCloud 平台在生物医学领域的联邦学习：统一方法。
J Med Internet Res. 2023 Jul 12;25:e42621. doi: 10.2196/42621.
5
Guideline for software life cycle in health informatics.健康信息学软件生命周期指南。
iScience. 2022 Nov 9;25(12):105534. doi: 10.1016/j.isci.2022.105534. eCollection 2022 Dec 22.
6
Federated Random Forests can improve local performance of predictive models for various healthcare applications.联邦随机森林可以提高各种医疗保健应用预测模型的局部性能。
Bioinformatics. 2022 Apr 12;38(8):2278-2286. doi: 10.1093/bioinformatics/btac065.
7
Fostering reproducibility, reusability, and technology transfer in health informatics.促进健康信息学中的可重复性、可重用性和技术转移。
iScience. 2021 Jul 1;24(7):102803. doi: 10.1016/j.isci.2021.102803. eCollection 2021 Jul 23.