EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY-NC 4.0

Privacy-by-Design with Federated Learning will drive future Rare Disease Research

Simon Süwer, Md Shihab Ullah iD, Niklas Probul iD, Andreas Maier iD, Jan Baumbach

Journal of Neuromuscular Diseases · 2026-01 · 13 (1) · 6-19

DOI: 10.1177/22143602241296276 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Journal of Neuromuscular Diseases, online erschienen am 08.12.2024. Verfasst von Simon Süwer und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Computational Systems Biology, University of Hamburg, Hamburg, Germany. Hauptthemen laut MEDLINE: Rare Diseases, Machine Learning, Biomedical Research, Privacy. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 167 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Up to 6% of the global population is estimated to be affected by one of about 10,000 distinct rare diseases (RDs). RDs are, to this day, often not understood, and thus, patients are heavily underserved. Most RD studies are chronically underfunded, and research faces inherent difficulties in analyzing scarce data. Furthermore, the creation and analysis of representative datasets are often constrained by stringent data protection regulations, such as the EU General Data Protection Regulation. This review examines the potential of federated learning (FL) as a privacy-by-design approach to training machine learning on distributed datasets while ensuring data privacy by maintaining the local patient data and only sharing model parameters, which is particularly beneficial in the context of sensitive data that cannot be collected in a centralized manner. FL enhances model accuracy by leveraging diverse datasets without compromising data privacy. This is particularly relevant in rare diseases, where heterogeneity and small sample sizes impede the development of robust models. FL further has the potential to enable the discovery of novel biomarkers, enhance patient stratification, and facilitate the development of personalized treatment plans. This review illustrates how FL can facilitate large-scale, cross-institutional collaboration, thereby enabling the development of more accurate and generalizable models for improved diagnosis and treatment of rare diseases. However, challenges such as non-independently distributed data and significant computational and bandwidth requirements still need to be addressed. Future research must focus on applying FL technology for rare disease datasets while exploring standardized protocols for cross-border collaborations that can ultimately pave the way for a new era of privacy-preserving and distributed data-driven rare disease research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Rare DiseasesMachine LearningBiomedical ResearchPrivacyHumansFederated Learning

Stichwörter der Autor:innen

artificial intelligencedata protectionfederated learningpersonalized medicinerare diseases

Autor:innen und Institutionen

  • Institute for Computational Systems Biology, University of Hamburg, Hamburg, Germany.
  • Computational Biomedicine Lab, Department of Mathematics and Computer Science, University of Southern Denmark, Odense, Denmark.

ORCID-Profile: Md Shihab Ullah, Niklas Probul, Andreas Maier

Zitieren

APA

Süwer, S., Ullah, M. S., Probul, N., Maier, A., & Baumbach, J. (2026). Privacy-by-Design with Federated Learning will drive future Rare Disease Research. Journal of Neuromuscular Diseases, 13(1), 6-19. https://doi.org/10.1177/22143602241296276

Vancouver

Süwer S, Ullah MS, Probul N, Maier A, Baumbach J. Privacy-by-Design with Federated Learning will drive future Rare Disease Research. Journal of Neuromuscular Diseases. 2026;13(1):6-19. doi:10.1177/22143602241296276

BibTeX
@article{Swer2026,
  author = {Süwer, Simon and Ullah, Md Shihab and Probul, Niklas and Maier, Andreas and Baumbach, Jan},
  title = {Privacy-by-Design with Federated Learning will drive future Rare Disease Research},
  journal = {Journal of Neuromuscular Diseases},
  year = {2026},
  volume = {13},
  number = {1},
  pages = {6--19},
  doi = {10.1177/22143602241296276}
}
Kostenlos starten →