Journal article · 2026 · Open access

Assessment of Memorization, Prompt Inference, and Retrieval Risks in Healthcare Large Language Models

Olufunke Adebola Akande, Onuh Matthew Ijiga, Otugene Victor Bamigwojo, Agbo Ogloji James

International Journal of Innovative Science and Research Technology (IJISRT), 2887 · Published 5 February 2026 · DOI 10.38124/ijisrt/26jan1453

Open PDFView at the publisherCite this paper

In brief

“Assessment of Memorization, Prompt Inference, and Retrieval Risks in Healthcare Large Language Models” is a 2026 journal article by Olufunke Adebola Akande and 3 co-authors, published in International Journal of Innovative Science and Research Technology (IJISRT). OpenAlex counts 5 citations as of 19 November 2026, which puts it in the top 3% of works published in 2026 by citations. It is open access under a CC BY-NC licence: the full text is free to read at International Journal of Innovative Science and Research Technology (IJISRT).

Citations
5
Most cited in
2026 (5)
Field-weighted impact
4.81
References
12
Authors
4

Abstract

This study examines the risks associated with the deployment of large language models (LLMs) in healthcare, focusing on memorization, prompt inference errors, and retrieval hazards. LLMs, such as GPT-4, MedPaLM, and fine- tuned clinical models like ClinicalBERT, are increasingly used in clinical decision support, diagnostic assistance, and administrative automation. While these models offer significant potential in improving healthcare delivery, they also present privacy and safety risks. The study investigates how these models memorize sensitive data, generate incorrect or unsafe responses due to prompt errors, and retrieve irrelevant or confidential information through external knowledge bases. The findings reveal that GPT-4, a general-purpose model, exhibits higher memorization and inference risks compared to domain-specific models like MedPaLM and ClinicalBERT, which showed improved performance in healthcare tasks and reduced memorization tendencies. The study also emphasizes the importance of prompt engineering, the potential hazards of retrieval-augmented generation (RAG) systems, and the necessity of privacy-preserving techniques. Based on these findings, the paper proposes a set of practical recommendations for safe LLM integration in healthcare, including data governance practices, prompt validation protocols, and retrieval safeguards. Finally, the study outlines a framework for risk mitigation and suggests directions for future research, including longitudinal studies on model drift, cross-institutional validation of risk profiles, and human-in-the-loop interventions for real-world deployment. The findings provide essential insights for clinicians, AI researchers, and policymakers working to safely deploy AI in healthcare.

Cite this paper

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

APA 7

Akande, O. A., Ijiga, O. M., Bamigwojo, O. V., & James, A. O. (2026). Assessment of Memorization, Prompt Inference, and Retrieval Risks in Healthcare Large Language Models. International Journal of Innovative Science and Research Technology (IJISRT), 2887. https://doi.org/10.38124/ijisrt/26jan1453

MLA 9

Akande, Olufunke Adebola, et al. “Assessment of Memorization, Prompt Inference, and Retrieval Risks in Healthcare Large Language Models.” International Journal of Innovative Science and Research Technology (IJISRT), 2026, p. 2887. https://doi.org/10.38124/ijisrt/26jan1453.

Chicago

Akande, Olufunke Adebola, Onuh Matthew Ijiga, Otugene Victor Bamigwojo, and Agbo Ogloji James. 2026. “Assessment of Memorization, Prompt Inference, and Retrieval Risks in Healthcare Large Language Models.” International Journal of Innovative Science and Research Technology (IJISRT): 2887. https://doi.org/10.38124/ijisrt/26jan1453.

Harvard

Akande, O. A. et al. (2026) ‘Assessment of Memorization, Prompt Inference, and Retrieval Risks in Healthcare Large Language Models’, International Journal of Innovative Science and Research Technology (IJISRT), p. 2887. doi:10.38124/ijisrt/26jan1453.

IEEE

O. A. Akande, O. M. Ijiga, O. V. Bamigwojo, and A. O. James, “Assessment of Memorization, Prompt Inference, and Retrieval Risks in Healthcare Large Language Models,” International Journal of Innovative Science and Research Technology (IJISRT), p. 2887, 2026, doi: 10.38124/ijisrt/26jan1453.

BibTeX

@article{akande2026assessment,
  title     = {{Assessment of Memorization, Prompt Inference, and Retrieval Risks in Healthcare Large Language Models}},
  author    = {Akande, Olufunke Adebola and Ijiga, Onuh Matthew and Bamigwojo, Otugene Victor and James, Agbo Ogloji},
  journal   = {International Journal of Innovative Science and Research Technology (IJISRT)},
  year      = {2026},
  pages     = {2887},
  doi       = {10.38124/ijisrt/26jan1453},
  url       = {https://doi.org/10.38124/ijisrt/26jan1453}
}

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

  • large language models in healthcare
  • retrieval-augmented generation
  • GPT-4
  • ClinicalBERT
  • prompt engineering
  • privacy risks
  • clinical decision support
  • risk mitigation

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?

Akande, O. A., Ijiga, O. M., Bamigwojo, O. V., & James, A. O. (2026). Assessment of Memorization, Prompt Inference, and Retrieval Risks in Healthcare Large Language Models. International Journal of Innovative Science and Research Technology (IJISRT), 2887. https://doi.org/10.38124/ijisrt/26jan1453

How many times has this paper been cited?

5 times, according to OpenAlex on 19 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 International Journal of Innovative Science and Research Technology (IJISRT): sign in and open the PDF from this page.

Who wrote this paper?

Olufunke Adebola Akande, Onuh Matthew Ijiga, Otugene Victor Bamigwojo, Agbo Ogloji James.

What is the DOI of this paper?

10.38124/ijisrt/26jan1453, permanently at https://doi.org/10.38124/ijisrt/26jan1453. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 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.