Journal article · 2025 · Open access

Privacy-Aware Clinical NLP with Differentially Private Fine-Tuning of Large Language Models

Susan Lopez, Joseph Hill

Frontiers in Biotechnology and Genetics, 2(1), 61–68 · Published 30 December 2025 · DOI 10.71465/fbg549

Open PDFView at the publisherCite this paper

In brief

“Privacy-Aware Clinical NLP with Differentially Private Fine-Tuning of Large Language Models” is a 2025 journal article by Susan Lopez and Joseph Hill, published in Frontiers in Biotechnology and Genetics. OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at Frontiers in Biotechnology and Genetics.

Citations
0
References
10
Authors
2

Abstract

The integration of Large Language Models (LLMs) into clinical workflows promises to revolutionize medical informatics by automating tasks such as clinical note summarization, diagnostic coding, and patient triage. However, the deployment of these models is severely constrained by the sensitivity of clinical data and stringent regulatory frameworks regarding Protected Health Information (PHI). Standard de-identification techniques often fail to prevent memorization of training data, leaving models vulnerable to membership inference and reconstruction attacks. This paper presents a comprehensive framework for Privacy-Aware Clinical NLP, utilizing Differentially Private Fine-Tuning (DP-FT) on transformer-based architectures. We propose a hybrid approach that integrates Low-Rank Adaptation (LoRA) with Differentially Private Stochastic Gradient Descent (DP-SGD) to mitigate the computational overhead and utility degradation typically associated with private training. By injecting calibrated Gaussian noise into the gradient updates of low-rank adapters while keeping the pre-trained backbone frozen, we achieve a rigorous privacy guarantee without catastrophic forgetting. Our experimental results on the MIMIC-III and MIMIC-IV datasets demonstrate that our method retains high clinical utility in Named Entity Recognition (NER) and summarization tasks while satisfying strict differential privacy budgets (ε<3). This work bridges the gap between theoretical privacy guarantees and practical clinical utility, offering a viable path for the secure deployment of LLMs in healthcare environments.

Cite this paper

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

APA 7

Lopez, S., & Hill, J. (2025). Privacy-Aware Clinical NLP with Differentially Private Fine-Tuning of Large Language Models. Frontiers in Biotechnology and Genetics, 2(1), 61–68. https://doi.org/10.71465/fbg549

MLA 9

Lopez, Susan, and Joseph Hill. “Privacy-Aware Clinical NLP with Differentially Private Fine-Tuning of Large Language Models.” Frontiers in Biotechnology and Genetics, vol. 2, no. 1, 2025, pp. 61–68. https://doi.org/10.71465/fbg549.

Chicago

Lopez, Susan and Joseph Hill. 2025. “Privacy-Aware Clinical NLP with Differentially Private Fine-Tuning of Large Language Models.” Frontiers in Biotechnology and Genetics 2 (1): 61–68. https://doi.org/10.71465/fbg549.

Harvard

Lopez, S. and Hill, J. (2025) ‘Privacy-Aware Clinical NLP with Differentially Private Fine-Tuning of Large Language Models’, Frontiers in Biotechnology and Genetics, 2(1), pp. 61–68. doi:10.71465/fbg549.

IEEE

S. Lopez and J. Hill, “Privacy-Aware Clinical NLP with Differentially Private Fine-Tuning of Large Language Models,” Frontiers in Biotechnology and Genetics, vol. 2, no. 1, pp. 61–68, 2025, doi: 10.71465/fbg549.

BibTeX

@article{lopez2025privacy,
  title     = {{Privacy-Aware Clinical NLP with Differentially Private Fine-Tuning of Large Language Models}},
  author    = {Lopez, Susan and Hill, Joseph},
  journal   = {Frontiers in Biotechnology and Genetics},
  year      = {2025},
  volume    = {2},
  number    = {1},
  pages     = {61--68},
  doi       = {10.71465/fbg549},
  url       = {https://doi.org/10.71465/fbg549}
}

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

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • differential privacy
  • large language models
  • clinical natural language processing
  • low-rank adaptation
  • LoRa
  • DP-SGD
  • membership inference attacks
  • reconstruction attacks

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Lopez, S., & Hill, J. (2025). Privacy-Aware Clinical NLP with Differentially Private Fine-Tuning of Large Language Models. Frontiers in Biotechnology and Genetics, 2(1), 61–68. https://doi.org/10.71465/fbg549

How many times has this paper been cited?

0 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 Frontiers in Biotechnology and Genetics: sign in and open the PDF from this page.

Who wrote this paper?

Susan Lopez, Joseph Hill.

What is the DOI of this paper?

10.71465/fbg549, permanently at https://doi.org/10.71465/fbg549. 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.