Lena Stempfle
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lena Stempfle has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Adibvafa Fallahpour
University of Toronto
1 shared publication - Marzyeh Ghassemi
Massachusetts Institute of Technology, Cambridge, USA
1 shared publication - Sana Tonekaboni
Department University of Toronto Vector Institute University Health Network (UHN) Worcester Polytechnic Institute Computer Science MIT
1 shared publication - Walter Gerych
Worcester Polytechnic Institute
1 shared publication
Latest Publications
- Open Access
An Investigation of Memorization Risk in Healthcare Foundation Models
Foundation models trained on large-scale de-identified electronic health records (EHRs) hold promise for clinical applications. However, their capacity to memorize patient information raises important privacy concerns. In this work, we introduce a suite of black-box evaluation tests to assess privacy-related memorization risks in foundation models trained on structured EHR data. Our framework includes methods for probing memorization at both the embedding and generative levels, and aims to distinguish between model generalization and harmful memorization in clinically relevant settings. We contextualize memorization in terms of its potential to compromise patient privacy, particularly for vulnerable subgroups. We validate our approach on a publicly available EHR foundation model and release an open-source toolkit to facilitate reproducible and collaborative privacy assessments in healthcare AI.
Open AccessAn Investigation of Memorization Risk in Healthcare Foundation Models
Foundation models trained on large-scale de-identified electronic health records (EHRs) hold promise for clinical applications. However, their capacity to memorize patient information raises important privacy concerns. In this work, we introduce a suite of black-box evaluation tests to assess privacy-related memorization risks in foundation models trained on structured EHR data. Our framework includes methods for probing memorization at both the embedding and generative levels, and aims to distinguish between model generalization and harmful memorization in clinically relevant settings. We contextualize memorization in terms of its potential to compromise patient privacy, particularly for vulnerable subgroups. We validate our approach on a publicly available EHR foundation model and release an open-source toolkit to facilitate reproducible and collaborative privacy assessments in healthcare AI.