EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Enabling Privacy-Preserving Federated Learning in Healthcare: The FLAME Architecture and Policy Framework

Marius de Arruda Botelho Herr, Peter Placzek, Hammam Abu Attieh, Bruce Schultz, David Hieber, Alexander Röhl, Mehrshad Jaberansary, Alexander Twrdik, Paul Brassel, Max Schaible, Mehmed Halilovic, Fabian Prasser und 2 weitere

Studies in Health Technology and Informatics · 21.05.2026

DOI: 10.3233/shti260485 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Marius de Arruda Botelho Herr und 13 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Bioinformatics and Medical Informatics (IBMI), University Tübingen, Tübingen, Germany. Hauptthemen laut MEDLINE: Federated Learning, Confidentiality, Computer Security, Electronic Health Records. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated Learning enables collaborative AI development in healthcare without sharing patient data, addressing privacy and regulatory constraints like GDPR and HIPAA. We present FLAME, an open-source platform developed within the German PrivateAIM project, designed to ensure privacy-compliant and auditable federated analytics. FLAME uses a hub-and-node architecture, integrating privacy-enhancing technologies with a dynamic policy framework that specifies permissions and conditions for data access and algorithm execution. This framework allows distributed policy evaluation and enforcement across institutions. Initial deployments at German university hospitals demonstrated FLAME’s capability to conduct federated analyses on clinical and genomic data with model performance comparable to centralized approaches. The system offers fine-grained access control, audit logging, and minimal overhead. FLAME provides a scalable foundation for secure, privacy-preserving AI in medicine, bridging legal, technical, and organizational requirements for multi-institutional collaboration.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Federated LearningConfidentialityComputer SecurityElectronic Health RecordsGermanyHumans

Stichwörter der Autor:innen

Distributed MLFederated LearningPrivacy Preserving ML

Autor:innen und Institutionen

  • Institute of Bioinformatics and Medical Informatics (IBMI), University Tübingen, Tübingen, Germany.
  • Berlin Institute of Health at Charité - Universitätsmedizin Berlin, Germany.
  • Institute for Biomedical Informatics (BI-K), Faculty of Medicine, University of Cologne, Cologne, Germany.
  • University of Leipzig Medical Center, Medical Informatics Center, Dept. Medical Data Science, Leipzig, Germany.

Zitieren

APA

de Arruda Botelho Herr, M., Placzek, P., Abu Attieh, H., Schultz, B., Hieber, D., Röhl, A., Jaberansary, M., Twrdik, A., Brassel, P., Schaible, M., Halilovic, M., Prasser, F., Kirsten, T., & Kohlbacher, O. (2026). Enabling Privacy-Preserving Federated Learning in Healthcare: The FLAME Architecture and Policy Framework. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260485

Vancouver

de Arruda Botelho Herr M, Placzek P, Abu Attieh H, Schultz B, Hieber D, Röhl A, et al. Enabling Privacy-Preserving Federated Learning in Healthcare: The FLAME Architecture and Policy Framework. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260485

BibTeX
@article{deArrudaBotelhoHerr2026,
  author = {de Arruda Botelho Herr, Marius and Placzek, Peter and Abu Attieh, Hammam and Schultz, Bruce and Hieber, David and Röhl, Alexander and Jaberansary, Mehrshad and Twrdik, Alexander and Brassel, Paul and Schaible, Max and Halilovic, Mehmed and Prasser, Fabian and Kirsten, Toralf and Kohlbacher, Oliver},
  title = {Enabling Privacy-Preserving Federated Learning in Healthcare: The FLAME Architecture and Policy Framework},
  journal = {Studies in Health Technology and Informatics},
  year = {2026},
  doi = {10.3233/shti260485}
}
Kostenlos starten →