EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

The SURROGATOR Framework for Context-Aware Surrogation of Privacy Sensitive Information in Medical Text

Christina Lohr, Marvin Seiferling, Philipp Wiesenbach, Jakob Faller, Christoph Dieterich

Studies in Health Technology and Informatics · 21.05.2026

DOI: 10.3233/shti260440 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Christina Lohr und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Medical Informatics, Statistics and Epidemiology (IMISE), University Leipzig, Germany. Hauptthemen laut MEDLINE: Confidentiality, Natural Language Processing, Electronic Health Records, Computer Security. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Clinical text cannot be shared freely due to data protection regulations. This paper introduces SURROGATOR, an open-source framework that replaces personal identifiable information with fictitious, high-fidelity synthetic surrogates to maintain text utility for human and artificial intelligence. We focus on the automated replacement of names, dates, and locations. Evaluation on a synthetic clinical corpus demonstrated high data utility, with named entity recognition performance remaining en par with the original text (F1-score of 0.70 vs. 0.73). Furthermore, a re-identification attack using a large language model resulted in an accuracy of 50.8%, which is equivalent to random chance. We conclude that SURROGATOR effectively balances patient privacy and data utility, providing a robust solution for the secure sharing of clinical documents in medical research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ConfidentialityNatural Language ProcessingElectronic Health RecordsComputer SecurityHumansArtificial IntelligenceLarge Language Models

Stichwörter der Autor:innen

De-IdentificationNatural Language ProcessingPatient Data Privacy

Autor:innen und Institutionen

  • Institute for Medical Informatics, Statistics and Epidemiology (IMISE), University Leipzig, Germany.
  • Klaus Tschira Institute for Integrative Computational Cardiology, University Hospital Heidelberg, Germany.
  • Medical Center for Information and Communication Technology, University Hospital Erlangen, Germany.
  • Partner Site Heidelberg/Mannheim, German Centre for Cardiovascular Research (DZHK), Heidelberg, Germany.

Zitieren

APA

Lohr, C., Seiferling, M., Wiesenbach, P., Faller, J., & Dieterich, C. (2026). The SURROGATOR Framework for Context-Aware Surrogation of Privacy Sensitive Information in Medical Text. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260440

Vancouver

Lohr C, Seiferling M, Wiesenbach P, Faller J, Dieterich C. The SURROGATOR Framework for Context-Aware Surrogation of Privacy Sensitive Information in Medical Text. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260440

BibTeX
@article{Lohr2026,
  author = {Lohr, Christina and Seiferling, Marvin and Wiesenbach, Philipp and Faller, Jakob and Dieterich, Christoph},
  title = {The SURROGATOR Framework for Context-Aware Surrogation of Privacy Sensitive Information in Medical Text},
  journal = {Studies in Health Technology and Informatics},
  year = {2026},
  doi = {10.3233/shti260440}
}
Kostenlos starten →