Conference paper · 2025 · Open access

PatientDx: Merging Large Language Models for Protecting Data-Privacy in Healthcare

José G. Moreno, Jesús Lovón-Melgarejo, M’rick Robin-Charlet, Christine Damase‐Michel, Lynda Tamine

Workshop on Patient-Oriented Language Processing (CL4Health), 1–11 · Published 1 January 2025 · DOI 10.18653/v1/2025.cl4health-1.1

Open PDFView at the publisherCite this paper

In brief

“PatientDx: Merging Large Language Models for Protecting Data-Privacy in Healthcare” is a 2025 conference paper by José G. Moreno and 4 co-authors, published in Workshop on Patient-Oriented Language Processing (CL4Health). OpenAlex counts 2 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at Workshop on Patient-Oriented Language Processing (CL4Health).

Citations
2
Most cited in
2025 (1)
Field-weighted impact
0.42
References
39
Authors
5

Abstract

Fine-tuning of Large Language Models (LLMs) has become the default practice for improving model performance on a given task.However, performance improvement comes at the cost of training on vast amounts of annotated data which could be sensitive leading to significant data privacy concerns.In particular, the healthcare domain is one of the most sensitive domains exposed to data privacy issues.In this paper, we present PatientDx, a framework of model merging that allows the design of effective LLMs for health-predictive tasks without requiring fine-tuning nor adaptation on patient data.Our proposal is based on recently proposed techniques known as merging of LLMs and aims to optimize a building block merging strategy.PatientDx uses a pivotal model adapted to numerical reasoning and tunes hyperparameters on examples based on a performance metric but without training of the LLM on these data.Experiments using the mortality tasks of the MIMIC-IV dataset show improvements up to 7% in terms of AUROC when compared to initial models.Additionally, we confirm that when compared to fine-tuned models, our proposal is less prone to data leak problems without hurting performance.Finally, we qualitatively show the capabilities of our proposal through a case study.Our best model is publicly available at https://huggingface.co/ Jgmorenof/mistral_merged_0_4.

Cite this paper

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

APA 7

Moreno, J. G., Lovón-Melgarejo, J., Robin-Charlet, M., Damase‐Michel, C., & Tamine, L. (2025). PatientDx: Merging Large Language Models for Protecting Data-Privacy in Healthcare. Workshop on Patient-Oriented Language Processing (CL4Health), 1–11. https://doi.org/10.18653/v1/2025.cl4health-1.1

MLA 9

Moreno, José G., et al. “PatientDx: Merging Large Language Models for Protecting Data-Privacy in Healthcare.” Workshop on Patient-Oriented Language Processing (CL4Health), 2025, pp. 1–11. https://doi.org/10.18653/v1/2025.cl4health-1.1.

Chicago

Moreno, José G., Jesús Lovón-Melgarejo, M’rick Robin-Charlet, Christine Damase‐Michel, and Lynda Tamine. 2025. “PatientDx: Merging Large Language Models for Protecting Data-Privacy in Healthcare.” Workshop on Patient-Oriented Language Processing (CL4Health): 1–11. https://doi.org/10.18653/v1/2025.cl4health-1.1.

Harvard

Moreno, J. G. et al. (2025) ‘PatientDx: Merging Large Language Models for Protecting Data-Privacy in Healthcare’, Workshop on Patient-Oriented Language Processing (CL4Health), pp. 1–11. doi:10.18653/v1/2025.cl4health-1.1.

IEEE

J. G. Moreno, J. Lovón-Melgarejo, M. Robin-Charlet, C. Damase‐Michel, and L. Tamine, “PatientDx: Merging Large Language Models for Protecting Data-Privacy in Healthcare,” Workshop on Patient-Oriented Language Processing (CL4Health), pp. 1–11, 2025, doi: 10.18653/v1/2025.cl4health-1.1.

BibTeX

@inproceedings{moreno2025patientdx,
  title     = {{PatientDx: Merging Large Language Models for Protecting Data-Privacy in Healthcare}},
  author    = {Moreno, José G. and Lovón-Melgarejo, Jesús and Robin-Charlet, M’rick and Damase‐Michel, Christine and Tamine, Lynda},
  booktitle = {Workshop on Patient-Oriented Language Processing (CL4Health)},
  year      = {2025},
  pages     = {1--11},
  doi       = {10.18653/v1/2025.cl4health-1.1},
  url       = {https://doi.org/10.18653/v1/2025.cl4health-1.1}
}

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

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare

  • large language models
  • model merging
  • data privacy
  • health data
  • fine-tuning alternatives
  • data leakage
  • mortality prediction
  • MIMIC-IV

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?

Moreno, J. G., Lovón-Melgarejo, J., Robin-Charlet, M., Damase‐Michel, C., & Tamine, L. (2025). PatientDx: Merging Large Language Models for Protecting Data-Privacy in Healthcare. Workshop on Patient-Oriented Language Processing (CL4Health), 1–11. https://doi.org/10.18653/v1/2025.cl4health-1.1

How many times has this paper been cited?

2 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 Workshop on Patient-Oriented Language Processing (CL4Health): sign in and open the PDF from this page.

Who wrote this paper?

José G. Moreno, Jesús Lovón-Melgarejo, M’rick Robin-Charlet, Christine Damase‐Michel, Lynda Tamine.

What is the DOI of this paper?

10.18653/v1/2025.cl4health-1.1, permanently at https://doi.org/10.18653/v1/2025.cl4health-1.1. 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.