Controllable Synthetic Clinical Note Generation with Privacy Guarantees

In the field of machine learning, domain-specific annotated data is an invaluable resource for training effective models. However, in the medical domain, this data often includes Personal Health Information (PHI), raising significant privacy concerns. The stringent regulations surrounding PHI limit...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Baumel, Tal, Andre Manoel, Jones, Daniel, Su, Shize, Inan, Huseyin, Aaron, Bornstein, Sim, Robert
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 12.09.2024
Subjects
Cloning
Controllability
Datasets
Ethical standards
Machine learning
Medical research
Performance evaluation
Performance prediction
Prediction models
Privacy
Online AccessGet full text

Cover

More Information
Summary:In the field of machine learning, domain-specific annotated data is an invaluable resource for training effective models. However, in the medical domain, this data often includes Personal Health Information (PHI), raising significant privacy concerns. The stringent regulations surrounding PHI limit the availability and sharing of medical datasets, which poses a substantial challenge for researchers and practitioners aiming to develop advanced machine learning models. In this paper, we introduce a novel method to "clone" datasets containing PHI. Our approach ensures that the cloned datasets retain the essential characteristics and utility of the original data without compromising patient privacy. By leveraging differential-privacy techniques and a novel fine-tuning task, our method produces datasets that are free from identifiable information while preserving the statistical properties necessary for model training. We conduct utility testing to evaluate the performance of machine learning models trained on the cloned datasets. The results demonstrate that our cloned datasets not only uphold privacy standards but also enhance model performance compared to those trained on traditional anonymized datasets. This work offers a viable solution for the ethical and effective utilization of sensitive medical data in machine learning, facilitating progress in medical research and the development of robust predictive models.
ISSN:2331-8422