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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Privacy is a major concern in sharing human subject data to researchers forsecondary analyses. A simple binary consent (opt-in or not) may significantlyreduce the amount of sharable data, since many patients might only be concernedabout a few sensitive medical conditions rather than the entire medicalrecords. We propose event-level privacy protection, and develop a featureablation method to protect event-level privacy in electronic medical records.Using a list of 13 sensitive diagnoses, we evaluate the feasibility and theefficacy of the proposed method. As feature ablation progresses, theidentifiability of a sensitive medical condition decreases with varying speedson different diseases. We find that these sensitive diagnoses can be dividedinto 3 categories: (1) 5 diseases have fast declining identifiability (AUCbelow 0.6 with less than 400 features excluded); (2) 7 diseases withprogressively declining identifiability (AUC below 0.7 with between 200 and 700features excluded); and (3) 1 disease with slowly declining identifiability(AUC above 0.7 with 1000 features excluded). The fact that the majority (12 outof 13) of the sensitive diseases fall into the first two categories suggeststhe potential of the proposed feature ablation method as a solution forevent-level record privacy protection.

Are My EHRs Private Enough? -Event-level Privacy Protection