Preprint · 2025 · Open access

Bridging AI and Healthcare: A Scoping Review of Retrieval-Augmented Generation—Ethics, Bias, Transparency, Improvements, and Applications

David J. Bunnell, Mary Jo Bondy, Lucy M. Fromtling, Emilie M. Ludeman, Krishnaj Gourab

medRxiv · Published 1 April 2025 · DOI 10.1101/2025.04.01.25325033

Open full textCite this paper

In brief

“Bridging AI and Healthcare: A Scoping Review of Retrieval-Augmented Generation—Ethics, Bias, Transparency, Improvements, and Applications” is a 2025 preprint by David J. Bunnell and 4 co-authors, published in medRxiv. OpenAlex counts 32 citations as of 21 November 2026. It is open access under a CC BY licence: the full text is free to read at medRxiv.

Citations
32
Most cited in
2026 (22)
References
32
Authors
5

Abstract

Background Retrieval-augmented generation (RAG) is an emerging artificial intelligence (AI) strategy that integrates encoded model knowledge with external data sources to enhance accuracy, transparency, and reliability. Unlike traditional large language models (LLMs), which are limited by static training data and potential misinformation, RAG dynamically retrieves and integrates relevant medical literature, clinical guidelines, and real-time data. Given the rapid adoption of AI in healthcare, this scoping review aims to systematically map the current applications, implementation challenges, and research gaps related to RAG in health professions. Methods A scoping review was conducted following the Joanna Briggs Institute (JBI) framework and reported using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses for Scoping Reviews (PRISMA-ScR) guidelines. A systematic search strategy was designed in collaboration with faculty and a research and education librarian to include PubMed, Scopus, Embase, Google Scholar, and Trip, covering studies published between January 2020 and August 2024. Eligible studies examined the use of RAG in healthcare. Studies were screened in two stages: title/abstract review followed by full-text assessment. Data extraction focused on study characteristics, applications of RAG, ethical and technical challenges, and proposed improvements. Results A total of 31 studies met inclusion criteria, with 90.32% published in 2024. Authors came from 17 countries with the most frequent publications coming from the USA ( n = 15), China ( n = 3), and the Republic of Korea ( n = 3). Key applications included clinical decision support, healthcare education, and pharmacovigilance. Ethical concerns centered on data privacy, algorithmic bias, explainability, and potential overreliance on AI-generated recommendations. Bias mitigation strategies included dataset diversification, fine-tuning techniques, and expert oversight. Transparency measures such as structured citations, traceable information retrieval, and explainable diagnostic pathways were explored to enhance clinician trust in AI-generated outputs. Identified challenges included optimizing retrieval mechanisms, improving real-time integration, and standardizing validation frameworks. Conclusion RAG AI has the potential to improve clinical decision-making and healthcare education by addressing key limitations of traditional LLMs. However, significant challenges remain regarding ethical implementation, model reliability, and regulatory oversight. Future research should prioritize refining retrieval accuracy, strengthening bias mitigation strategies, and establishing standardized evaluation metrics. Responsible deployment of RAG-based systems requires interdisciplinary collaboration between AI researchers, clinicians, and policymakers to ensure ethical, transparent, and effective integration into healthcare workflows.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Bunnell, D. J., Bondy, M. J., Fromtling, L. M., Ludeman, E. M., & Gourab, K. (2025). Bridging AI and Healthcare: A Scoping Review of Retrieval-Augmented Generation—Ethics, Bias, Transparency, Improvements, and Applications. medRxiv. https://doi.org/10.1101/2025.04.01.25325033

MLA 9

Bunnell, David J., et al. “Bridging AI and Healthcare: A Scoping Review of Retrieval-Augmented Generation—Ethics, Bias, Transparency, Improvements, and Applications.” medRxiv, 2025. https://doi.org/10.1101/2025.04.01.25325033.

Chicago

Bunnell, David J., Mary Jo Bondy, Lucy M. Fromtling, Emilie M. Ludeman, and Krishnaj Gourab. 2025. “Bridging AI and Healthcare: A Scoping Review of Retrieval-Augmented Generation—Ethics, Bias, Transparency, Improvements, and Applications.” medRxiv. https://doi.org/10.1101/2025.04.01.25325033.

Harvard

Bunnell, D. J. et al. (2025) ‘Bridging AI and Healthcare: A Scoping Review of Retrieval-Augmented Generation—Ethics, Bias, Transparency, Improvements, and Applications’, medRxiv. doi:10.1101/2025.04.01.25325033.

IEEE

D. J. Bunnell, M. J. Bondy, L. M. Fromtling, E. M. Ludeman, and K. Gourab, “Bridging AI and Healthcare: A Scoping Review of Retrieval-Augmented Generation—Ethics, Bias, Transparency, Improvements, and Applications,” medRxiv, 2025, doi: 10.1101/2025.04.01.25325033.

BibTeX

@misc{bunnell2025bridging,
  title     = {{Bridging AI and Healthcare: A Scoping Review of Retrieval-Augmented Generation—Ethics, Bias, Transparency, Improvements, and Applications}},
  author    = {Bunnell, David J. and Bondy, Mary Jo and Fromtling, Lucy M. and Ludeman, Emilie M. and Gourab, Krishnaj},
  howpublished = {medRxiv},
  year      = {2025},
  doi       = {10.1101/2025.04.01.25325033},
  url       = {https://doi.org/10.1101/2025.04.01.25325033}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education

  • retrieval-augmented generation
  • large language models
  • clinical decision support
  • healthcare education
  • pharmacovigilance
  • algorithmic bias
  • data privacy
  • explainability

Work with this paper

Most-cited papers in Medicine

All highly cited Medicine papers

Questions about this paper

How do I cite this paper in APA style?

Bunnell, D. J., Bondy, M. J., Fromtling, L. M., Ludeman, E. M., & Gourab, K. (2025). Bridging AI and Healthcare: A Scoping Review of Retrieval-Augmented Generation—Ethics, Bias, Transparency, Improvements, and Applications. medRxiv. https://doi.org/10.1101/2025.04.01.25325033

How many times has this paper been cited?

32 times, according to OpenAlex on 21 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at medRxiv: sign in and open the full text from this page.

Who wrote this paper?

David J. Bunnell, Mary Jo Bondy, Lucy M. Fromtling, Emilie M. Ludeman, Krishnaj Gourab.

What is the DOI of this paper?

10.1101/2025.04.01.25325033, permanently at https://doi.org/10.1101/2025.04.01.25325033. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 21 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.