An Investigation of Memorization Risk in Healthcare Foundation Models
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Zero shot health trajectory prediction using transformernpj Digital Medicine, 2024
- A Survey of Privacy Attacks in Machine LearningACM Computing Surveys, 2023
- How Much Do Language Models Copy From Their Training Data? Evaluating Linguistic Novelty in Text Generation Using RAVENTransactions of the Association for Computational Linguistics, 2023
- Health system-scale language models are all-purpose prediction enginesNature, 2023
- Foundation models for generalist medical artificial intelligenceNature, 2023
- MIMIC-IV, a freely accessible electronic health record datasetScientific Data, 2023
- Membership Inference Attacks Against Machine Learning Models via Prediction SensitivityIEEE Transactions on Dependable and Secure Computing, 2022
- Med-BERT: pretrained contextualized embeddings on large-scale structured electronic health records for disease predictionnpj Digital Medicine, 2021
- BEHRT: Transformer for Electronic Health RecordsScientific Reports, 2020
- Identifying Personal Genomes by Surname InferenceScience, 2013