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

The widespread adoption of electronic health records (EHRs) and subsequentincreased availability of longitudinal healthcare data has led to significantadvances in our understanding of health and disease with direct and immediateimpact on the development of new diagnostics and therapeutic treatment options.However, access to EHRs is often restricted due to their perceived sensitivenature and associated legal concerns, and the cohorts therein typically arethose seen at a specific hospital or network of hospitals and therefore notrepresentative of the wider population of patients. Here, we present HealthGen,a new approach for the conditional generation of synthetic EHRs that maintainsan accurate representation of real patient characteristics, temporalinformation and missingness patterns. We demonstrate experimentally thatHealthGen generates synthetic cohorts that are significantly more faithful toreal patient EHRs than the current state-of-the-art, and that augmenting realdata sets with conditionally generated cohorts of underrepresentedsubpopulations of patients can significantly enhance the generalisability ofmodels derived from these data sets to different patient populations. Syntheticconditionally generated EHRs could help increase the accessibility oflongitudinal healthcare data sets and improve the generalisability ofinferences made from these data sets to underrepresented populations.

Conditional Generation of Medical Time Series for Extrapolation to Underrepresented Populations