美国医疗保健中学习健康系统框架与人工智能及数据科学整合的范围综述
Learning health system frameworks and the integration of artificial intelligence and data science in United States health care: a scoping review
一项范围综述纳入54个学习健康系统(LHS)框架研究和30个人工智能/数据科学研究,发现五大重复出现的框架组件为数据基础设施与互操作性、治理与利益相关者参与、学习与改进循环、证据生成与转化、公平与伦理。
- Article
- Open access
- Published: 14 November 2026
- Rotana M. Radwan ORCID: orcid.org/0000-0003-0061-06371 na1,
- Hao Dai ORCID: orcid.org/0000-0001-7950-37592 na1,
- Yao An Lee3,
- Ronald Ramon4,
- Wei-han Chen ORCID: orcid.org/0000-0001-8545-61275,
- Hsin-Yueh Lin5,
- Ya-Yun Yeh5,
- Wenxi Huang ORCID: orcid.org/0000-0002-8237-64015,
- Hongyu Chen ORCID: orcid.org/0000-0001-6259-08336,
- Tiancheng Zhou6,
- Darlene C. Adirika4,
- Kate Luong4,
- Ying Lu5,
- Christina Scifres7,
- Emily C. Webber ORCID: orcid.org/0000-0001-5877-67078,
- Jingchuan Guo1,3 na2 &
- …
- Jiang Bian2,3,8 na2
npj Digital Medicine (2026) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Abstract
Learning Health Systems (LHSs) use routinely collected data to generate evidence that informs practice through continuous learning cycles. Artificial intelligence (AI) and data science may strengthen this model, but how LHS frameworks and AI applications relate remains unclear. We mapped LHS frameworks and their components and examined how AI and data science are integrated. Searches identified U.S.-based, English-language studies published January 2007–August 2025; two reviewers independently screened and extracted data, resolving disagreements by consensus. We included 54 framework studies (24 [44%] conceptual adaptations; 30 [56%] real-world implementations) and 30 AI/data science studies. Five components recurred across the frameworks: data infrastructure and interoperability, governance and stakeholder engagement, learning and improvement cycles, evidence generation and translation, and equity and ethics. Relative to framework studies, AI studies less often addressed governance and stakeholder engagement (17% vs 35%) or equity (13% vs 22%), emphasizing computational over organizational functions. Most AI studies (27/30) focused on the data-to-knowledge phase; only three extended to knowledge-to-practice, and none described practice-to-data feedback with post-deployment outcomes informing model updating. AI applications capture only part of the LHS vision, concentrating on knowledge generation with less attention to the organizational and feedback mechanisms needed to translate insights into practice and sustain learning.
Funding
No funding was received for this research.
Author information
Author notes
These authors contributed equally: Rotana M. Radwan, Hao Dai.
These authors jointly supervised this work: Jingchuan Guo, Jiang Bian.
Authors and Affiliations
Department of Pharmacy Practice, Purdue University College of Pharmacy, Indianapolis, IN, USA
Rotana M. Radwan & Jingchuan Guo
Department of Biostatistics & Health Data Science, Indiana University School of Medicine, Indianapolis, IN, USA
Hao Dai & Jiang Bian
Regenstrief Institute, Indianapolis, IN, USA
Yao An Lee, Jingchuan Guo & Jiang Bian
University of Florida College of Pharmacy, Gainesville, FL, USA
Ronald Ramon, Darlene C. Adirika & Kate Luong
Department of Pharmaceutical Outcomes and Policy, University of Florida, Gainesville, FL, USA
Wei-han Chen, Hsin-Yueh Lin, Ya-Yun Yeh, Wenxi Huang & Ying Lu
Department of Health Outcomes and Biomedical Informatics, University of Florida, Gainesville, FL, USA
Hongyu Chen & Tiancheng Zhou
Department of Obstetrics & Gynecology, Indiana University School of Medicine, Indianapolis, IN, USA
Christina Scifres
Indiana University Health, Indianapolis, IN, USA
Emily C. Webber & Jiang Bian
Authors
- Rotana M. Radwan
- Hao Dai
- Yao An Lee
- Ronald Ramon
- Wei-han Chen
- Hsin-Yueh Lin
- Ya-Yun Yeh
- Wenxi Huang
- Hongyu Chen
- Tiancheng Zhou
- Darlene C. Adirika
- Kate Luong
- Ying Lu
- Christina Scifres
- Emily C. Webber
- Jingchuan Guo
- Jiang Bian
Corresponding authors
Correspondence to Jingchuan Guo or Jiang Bian.
Ethics declarations
Competing interests
The authors declare no competing financial or non-financial interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Radwan, R.M., Dai, H., Lee, Y.A. et al. Learning health system frameworks and the integration of artificial intelligence and data science in United States health care: a scoping review. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-03452-1
Received: 26 August 2025
Accepted: 17 October 2026
Published: 14 November 2026
DOI: https://doi.org/10.1038/s41746-026-03452-1
来源:Nature 健康护理主题 · nature.com