Journal article · 2026 · Open access

Toward federated large language models in medicine: a parameter-efficient framework for privacy-preserving, multi-institutional adaptation

Anran Li, Yuanyuan Chen, Wenjun Long, Yu Yin, Yan Hu, Hyunjae Kim, Weipeng Zhou, Yujia Zhou, Hongyi Peng, Yang Ren, Xuguang Ai, Zhenyue Qin and 7 more

npj Digital Medicine · Published 15 August 2026 · DOI 10.1038/s41746-026-03064-9

Open PDFView at the publisherCite this paper

In brief

“Toward federated large language models in medicine: a parameter-efficient framework for privacy-preserving, multi-institutional adaptation” is a 2026 journal article by Anran Li and 18 co-authors, published in npj Digital Medicine. 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-ND licence: the full text is free to read at npj Digital Medicine.

Citations
5
Most cited in
2026 (5)
Field-weighted impact
5.36
References
83
Authors
19

Abstract

Large language models (LLMs) are increasingly adapted for medical applications, but most are trained using data from a single institution because privacy and governance constraints prevent multi-institutional data sharing. As a result, these models often generalize poorly across heterogeneous healthcare systems. We address this gap by introducing Fed-MedLoRA and Fed-MedLoRA + , a parameter-efficient federated framework for collaborative LLM adaptation across healthcare institutions. Fed-MedLoRA transmits only low-rank adapters rather than full model weights, reducing communication overhead. We also evaluate a privacy-preserving variant that applies Gaussian perturbation to transmitted adapter updates. Fed-MedLoRA+ further incorporates adaptive aggregation to better address cross-site heterogeneity in patient populations, annotation practices, and disease distributions. We evaluate the framework on clinical information extraction across five independent patient cohorts totaling 42,198 entities and 41,570 relations, and compare it with zero-shot and fine-tuned LLMs, domain-specific BERT models, and federated baselines. Across all settings, the proposed methods consistently improve extraction performance and generalize better to heterogeneous cohorts. In a real-world case study using clinical notes from the Yale New Haven Health System, the framework demonstrates strong performance under low-resource new-site deployment. These results suggest that federated, parameter-efficient LLM adaptation is feasible, scalable, and effective for multi-institutional clinical deployment.

Cite this paper

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

APA 7

Li, A., Chen, Y., Long, W., Yin, Y., Hu, Y., Kim, H., Zhou, W., Zhou, Y., Peng, H., Ren, Y., Ai, X., Qin, Z., Hu, M., Li, X., Yu, H., Tham, Y. C., Ohno-Machado, L., Xu, H., & Chen, Q. (2026). Toward federated large language models in medicine: a parameter-efficient framework for privacy-preserving, multi-institutional adaptation. npj Digital Medicine. https://doi.org/10.1038/s41746-026-03064-9

MLA 9

Li, Anran, et al. “Toward federated large language models in medicine: a parameter-efficient framework for privacy-preserving, multi-institutional adaptation.” npj Digital Medicine, 2026. https://doi.org/10.1038/s41746-026-03064-9.

Chicago

Li, Anran, Yuanyuan Chen, Wenjun Long, Yu Yin, Yan Hu, Hyunjae Kim, Weipeng Zhou, et al. 2026. “Toward federated large language models in medicine: a parameter-efficient framework for privacy-preserving, multi-institutional adaptation.” npj Digital Medicine. https://doi.org/10.1038/s41746-026-03064-9.

Harvard

Li, A. et al. (2026) ‘Toward federated large language models in medicine: a parameter-efficient framework for privacy-preserving, multi-institutional adaptation’, npj Digital Medicine. doi:10.1038/s41746-026-03064-9.

IEEE

A. Li et al., “Toward federated large language models in medicine: a parameter-efficient framework for privacy-preserving, multi-institutional adaptation,” npj Digital Medicine, 2026, doi: 10.1038/s41746-026-03064-9.

BibTeX

@article{li2026toward,
  title     = {{Toward federated large language models in medicine: a parameter-efficient framework for privacy-preserving, multi-institutional adaptation}},
  author    = {Li, Anran and Chen, Yuanyuan and Long, Wenjun and Yin, Yu and Hu, Yan and Kim, Hyunjae and Zhou, Weipeng and Zhou, Yujia and Peng, Hongyi and Ren, Yang and Ai, Xuguang and Qin, Zhenyue and Hu, Ming and Li, Xiaoxiao and Yu, Han and Tham, Yih Chung and Ohno-Machado, Lucila and Xu, Hua and Chen, Qingyu},
  journal   = {npj Digital Medicine},
  year      = {2026},
  doi       = {10.1038/s41746-026-03064-9},
  url       = {https://doi.org/10.1038/s41746-026-03064-9}
}

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

  • federated learning
  • large language models
  • parameter-efficient fine-tuning
  • LoRA adapters
  • multi-institutional data sharing
  • privacy-preserving federated learning
  • Gaussian perturbation
  • adaptive aggregation

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?

Li, A., Chen, Y., Long, W., Yin, Y., Hu, Y., Kim, H., Zhou, W., Zhou, Y., Peng, H., Ren, Y., Ai, X., Qin, Z., Hu, M., Li, X., Yu, H., Tham, Y. C., Ohno-Machado, L., Xu, H., & Chen, Q. (2026). Toward federated large language models in medicine: a parameter-efficient framework for privacy-preserving, multi-institutional adaptation. npj Digital Medicine. https://doi.org/10.1038/s41746-026-03064-9

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 npj Digital Medicine: sign in and open the PDF from this page.

Who wrote this paper?

Anran Li, Yuanyuan Chen, Wenjun Long, Yu Yin, Yan Hu, Hyunjae Kim, Weipeng Zhou, Yujia Zhou, Hongyi Peng, Yang Ren, Xuguang Ai, Zhenyue Qin and 7 more.

What is the DOI of this paper?

10.1038/s41746-026-03064-9, permanently at https://doi.org/10.1038/s41746-026-03064-9. 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.