Prompt Engineering Strategies for Context-Aware Medical Text Anonymization Using LLMs: Insights from the GraSCCo Corpus
Introduction: The anonymization of clinical texts remains an ongoing challenge for enabling secondary use of healthcare data. With the increasing capabilities of large language models (LLMs) like ChatGPT-4.0, new opportunities arise for automating de-identification tasks [ref:1], [ref:2]. [for full text, please go to the a.m. URL]
Authors
- Markus Wolfien (ORCID: https://orcid.org/0000-0002-1887-4772)
- Hung Manh Nguyen
- Martin Sedlmayr
- Florin Teschner
Institutions
- German Research Centre for Artificial Intelligence (DE)
- University Hospital Carl Gustav Carus (DE)
Publication Details
- Journal
- German Medical Science (German Research Foundation)
- Published
- 2026-04-01
- DOI
- https://doi.org/10.3205/25gmds210
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00