Journal article · 2026 · Open access

Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications

Marziyeh Mohammadi, Mohsen Vejdanihemmat, Mahshad Lotfinia, Mirabela Rusu, Daniel Truhn, Andreas Maier, Soroosh Tayebi Arasteh

npj Digital Medicine, 9(1), 93 · Published 3 January 2026 · DOI 10.1038/s41746-025-02280-z

Open PDFView at the publisherCite this paper

In brief

“Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications” is a 2026 journal article by Marziyeh Mohammadi and 6 co-authors, published in npj Digital Medicine. OpenAlex counts 74 citations as of 19 November 2026, which puts it in the top 1% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at npj Digital Medicine.

Citations
74
Most cited in
2026 (64)
Field-weighted impact
73.90
References
137
Authors
7

Abstract

Differential privacy (DP) is a prominent technique for protecting sensitive patient data in medical deep learning (DL), yet deploying it without compromising clinical utility or equity remains challenging. This scoping review synthesizes applications of DP in medical DL across centralized and federated settings. A structured search identified 74 eligible studies published through March 2025. Across modalities and tasks, DP, especially via DP-SGD, can maintain clinically acceptable performance under moderate privacy budgets (ϵ ≈ 10), particularly in imaging. However, strict privacy (ϵ ≈ 1) often leads to substantial accuracy loss, with amplified degradation in smaller or heterogeneous datasets. Only a minority of studies evaluate fairness, and several report that DP can widen subgroup performance gaps. Beyond DP-SGD, alternative mechanisms, including generative modeling, local DP, and hybrid federated designs, are emerging, but reporting of privacy parameters remains inconsistent. We identify key gaps in fairness auditing and standardization, and outline priorities for equitable, clinically robust privacy-preserving DL.

Cite this paper

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

APA 7

Mohammadi, M., Vejdanihemmat, M., Lotfinia, M., Rusu, M., Truhn, D., Maier, A., & Arasteh, S. T. (2026). Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications. npj Digital Medicine, 9(1), 93. https://doi.org/10.1038/s41746-025-02280-z

MLA 9

Mohammadi, Marziyeh, et al. “Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications.” npj Digital Medicine, vol. 9, no. 1, 2026, p. 93. https://doi.org/10.1038/s41746-025-02280-z.

Chicago

Mohammadi, Marziyeh, Mohsen Vejdanihemmat, Mahshad Lotfinia, Mirabela Rusu, Daniel Truhn, Andreas Maier, and Soroosh Tayebi Arasteh. 2026. “Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications.” npj Digital Medicine 9 (1): 93. https://doi.org/10.1038/s41746-025-02280-z.

Harvard

Mohammadi, M. et al. (2026) ‘Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications’, npj Digital Medicine, 9(1), p. 93. doi:10.1038/s41746-025-02280-z.

IEEE

M. Mohammadi et al., “Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications,” npj Digital Medicine, vol. 9, no. 1, p. 93, 2026, doi: 10.1038/s41746-025-02280-z.

BibTeX

@article{mohammadi2026differential,
  title     = {{Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications}},
  author    = {Mohammadi, Marziyeh and Vejdanihemmat, Mohsen and Lotfinia, Mahshad and Rusu, Mirabela and Truhn, Daniel and Maier, Andreas and Arasteh, Soroosh Tayebi},
  journal   = {npj Digital Medicine},
  year      = {2026},
  volume    = {9},
  number    = {1},
  pages     = {93},
  doi       = {10.1038/s41746-025-02280-z},
  url       = {https://doi.org/10.1038/s41746-025-02280-z}
}

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
  • DP-SGD
  • federated learning
  • privacy-preserving machine learning
  • patient data privacy
  • fairness
  • algorithmic bias
  • privacy-utility trade-off

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?

Mohammadi, M., Vejdanihemmat, M., Lotfinia, M., Rusu, M., Truhn, D., Maier, A., & Arasteh, S. T. (2026). Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications. npj Digital Medicine, 9(1), 93. https://doi.org/10.1038/s41746-025-02280-z

How many times has this paper been cited?

74 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?

Marziyeh Mohammadi, Mohsen Vejdanihemmat, Mahshad Lotfinia, Mirabela Rusu, Daniel Truhn, Andreas Maier, Soroosh Tayebi Arasteh.

What is the DOI of this paper?

10.1038/s41746-025-02280-z, permanently at https://doi.org/10.1038/s41746-025-02280-z. 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.