GeMTeX’s De-Identification in Action: Lessons Learned & Devil’s Details
Studies in Health Technology and Informatics · 2025
DOI: 10.3233/shti251406 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Christina Lohr und 20 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Medical Informatics, Statistics, and Epidemiology, Leipzig University, Leipzig, Germany. Hauptthemen laut MEDLINE: Electronic Health Records, Data Anonymization, Natural Language Processing, Confidentiality. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Introduction
In 2024, the GeMTeX project launched the largest ever de-identification campaign for German-language clinical reports, and, as a pilot study, published GraSCCoPHI, the first de-identified German-language gold standard corpus of synthetic discharge summaries.
Methods
GeMTeX’s de-identification workflow is described here – including annotation tool management and, pre-annotation experience, such as assembling and training annotation groups and the evolution of guidelines.
Results
We present the project’s progress in the first year with respect to de-identification efforts and the challenges we faced during the rollout at six hospital sites in four German states. The refinement of the annotation guidelines became an ongoing process, often with unforeseen hurdles to overcome as we moved from testing to production. From our current internal interim corpus (9,000 documents with about 20 million tokens), we are publishing the first quantitative insights, such as the average amount of identifiable information per document, a list of confounding factors we did not anticipate at the beginning of the project, and three key lessons learned.
Conclusion
We note that the unforeseen hurdles behave like the Pareto principle and fall into the set of less than 20% of the annotations.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute for Medical Informatics, Statistics, and Epidemiology, Leipzig University, Leipzig, Germany.
- GeMTeX Consortium of the German Medical Informatics Initiative.
- Erlangen University Hospital, Medical Center for Information and Communication Technology, Erlangen, Germany.
- Friedrich-Alexander-Universität Erlangen-Nürnberg, Medical Informatics, Erlangen, Germany.
- Institute for Medical Informatics and Biometry, Faculty of Medicine Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany.
- Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI), Dresden, Germany.
Zitieren
APA
Lohr, C., Faller, J., Riedel, A., Nguyen, H. M., Wolfien, M., Hofenbitzer, J., Modersohn, L., Romberg, J., Prasser, F., Omeirat, J., Wen, Y., Galusch, O., Hahn, U., Seiferling, M., Dieterich, C., Klügl, P., Matthies, F., Kind, J., Boeker, M., …, & Meineke, F. (2025). GeMTeX’s De-Identification in Action: Lessons Learned & Devil’s Details. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti251406
Vancouver
Lohr C, Faller J, Riedel A, Nguyen HM, Wolfien M, Hofenbitzer J, et al. GeMTeX’s De-Identification in Action: Lessons Learned & Devil’s Details. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti251406
BibTeX
@article{Lohr2025,
author = {Lohr, Christina and Faller, Jakob and Riedel, Andrea and Nguyen, Hung Manh and Wolfien, Markus and Hofenbitzer, Justin and Modersohn, Luise and Romberg, Jutta and Prasser, Fabian and Omeirat, Jazia and Wen, Yutong and Galusch, Oksana and Hahn, Udo and Seiferling, Marvin and Dieterich, Christoph and Klügl, Peter and Matthies, Franz and Kind, Janina and Boeker, Martin and Löffler, Markus and Meineke, Frank},
title = {GeMTeX’s De-Identification in Action: Lessons Learned & Devil’s Details},
journal = {Studies in Health Technology and Informatics},
year = {2025},
doi = {10.3233/shti251406}
}
EUVIMED