GeMTeX’s De-Identification in Action: Lessons Learned & Devil’s Details
Year: 2025
Type: book-chapter
Abstract: 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.
DOI: 10.3233/shti251406
Authors: Christina Lohr, Jakob Faller, Andrea Riedel, Hung Manh Nguyen, Markus Wolfien, Justin Hofenbitzer, Luise Modersohn, Jutta Romberg, Fabian Prasser, Jazia Omeirat, Yutong Wen, Oksana Galusch, Udo Hahn, Marvin Seiferling, Christoph Dieterich, Peter Klügl, Franz Matthies, Janina Kind, Martin Boeker, Markus Löffler, Frank Meineke
Institutions: Leipzig University, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Technische Universität Dresden, Center for Scalable Data Analytics and Artificial Intelligence, TUM Klinikum, Technical University of Munich, Berlin Institute of Health at Charité - Universitätsmedizin Berlin, Charité – Universitätsmedizin Berlin, Essen University Hospital, University Hospital Leipzig, Heidelberg University, University Hospital Heidelberg, Averbis (Germany)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4413956458