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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Synthetic electronic health records (EHRs) that are both realistic andpreserve privacy can serve as an alternative to real EHRs for machine learning(ML) modeling and statistical analysis. However, generating high-fidelity andgranular electronic health record (EHR) data in its original,highly-dimensional form poses challenges for existing methods due to thecomplexities inherent in high-dimensional data. In this paper, we proposeHierarchical Autoregressive Language mOdel (HALO) for generating longitudinalhigh-dimensional EHR, which preserve the statistical properties of real EHR andcan be used to train accurate ML models without privacy concerns. Our HALOmethod, designed as a hierarchical autoregressive model, generates aprobability density function of medical codes, clinical visits, and patientrecords, allowing for the generation of realistic EHR data in its original,unaggregated form without the need for variable selection or aggregation.Additionally, our model also produces high-quality continuous variables in alongitudinal and probabilistic manner. We conducted extensive experiments anddemonstrate that HALO can generate high-fidelity EHR data with high-dimensionaldisease code probabilities (d > 10,000), disease co-occurrence probabilitieswithin visits (d > 1,000,000), and conditional probabilities across consecutivevisits (d > 5,000,000) and achieve above 0.9 R2 correlation in comparison toreal EHR data. This performance then enables downstream ML models trained onits synthetic data to achieve comparable accuracy to models trained on realdata (0.938 AUROC with HALO data vs. 0.943 with real data). Finally, using acombination of real and synthetic data enhances the accuracy of ML modelsbeyond that achieved by using only real EHR data.

Synthesize High-dimensional Longitudinal Electronic Health Records via Hierarchical Autoregressive Language Model