Robust privacy amidst innovation with large language models through a critical assessment of the risks
This study shows that keyword-based methods can create synthetic clinical notes that protect privacy while retaining data usability, potentially improving clinical data sharing. The use of dummy PHIs to counter privacy attacks may offer better utility and privacy than traditional de-identification.
Authors
- Atiquer Rahman Sarkar (ORCID: https://orcid.org/0000-0002-6909-2930)
- Xiaoqian Jiang (ORCID: https://orcid.org/0000-0001-9933-2205)
- Yao-Shun Chuang (ORCID: https://orcid.org/0000-0001-9582-9222)
- Y. C. Hsu (ORCID: https://orcid.org/0000-0002-2386-7892)
- Noman Mohammed (ORCID: https://orcid.org/0000-0001-8547-9951)
Institutions
- University of Manitoba (CA)
- The University of Texas Health Science Center at Houston (US)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2025-02-13
- DOI
- https://doi.org/10.1093/jamia/ocaf037
- Citations
- 2
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 4.96
Funders
- National Science Foundation
- Cancer Prevention and Research Institute of Texas
- University of Texas Health Science Center at Houston
- National Institutes of Health
- Natural Sciences and Engineering Research Council of Canada