Reliable generation of privacy-preserving synthetic electronic health record time series via diffusion models
The proposed diffusion model-based method can reliably and efficiently generate synthetic EHR time series, which facilitates the downstream medical data analysis. Our numerical results show the superiority of the proposed method over all other existing methods.
Authors
- Bernie Chen
- Anru R. Zhang (ORCID: https://orcid.org/0000-0002-8721-5252)
- Muhang Tian
- Shiyi Jiang (ORCID: https://orcid.org/0000-0001-6979-3334)
- Allan Guo
Institutions
- Duke University (US)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2024-08-12
- DOI
- https://doi.org/10.1093/jamia/ocae229
- Citations
- 16
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 5.56
Funders
- National Science Foundation
- National Institutes of Health