English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The digitization of medical records ushered in a new era of big data toclinical science, and with it the possibility that data could be shared, tomultiply insights beyond what investigators could abstract from paper records.The need to share individual-level medical data to accelerate innovation inprecision medicine continues to grow, and has never been more urgent, asscientists grapple with the COVID-19 pandemic. However, enthusiasm for the useof big data has been tempered by a fully appropriate concern for patientautonomy and privacy. That is, the ability to extract private or confidentialinformation about an individual, in practice, renders it difficult to sharedata, since significant infrastructure and data governance must be establishedbefore data can be shared. Although HIPAA provided de-identification as anapproved mechanism for data sharing, linkage attacks were identified as a majorvulnerability. A variety of mechanisms have been established to avoid leakingprivate information, such as field suppression or abstraction, strictlylimiting the amount of information that can be shared, or employingmathematical techniques such as differential privacy. Another approach, whichwe focus on here, is creating synthetic data that mimics the underlying data.For synthetic data to be a useful mechanism in support of medical innovationand a proxy for real-world evidence, one must demonstrate two properties of thesynthetic dataset: (1) any analysis on the real data must be matched byanalysis of the synthetic data (statistical fidelity) and (2) the syntheticdata must preserve privacy, with minimal risk of re-identification (privacyguarantee). In this paper we propose a framework for quantifying thestatistical fidelity and privacy preservation properties of synthetic datasetsand demonstrate these metrics for synthetic data generated by Syntegratechnology.

Fidelity and Privacy of Synthetic Medical Data