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

Electronic health records (EHR) offer unprecedented opportunities forin-depth clinical phenotyping and prediction of clinical outcomes. Combiningmultiple data sources is crucial to generate a complete picture of diseaseprevalence, incidence and trajectories. The standard approach to combiningclinical data involves collating clinical terms across different terminologysystems using curated maps, which are often inaccurate and/or incomplete. Here,we propose sEHR-CE, a novel framework based on transformers to enableintegrated phenotyping and analyses of heterogeneous clinical datasets withoutrelying on these mappings. We unify clinical terminologies using textualdescriptors of concepts, and represent individuals' EHR as sections of text. Wethen fine-tune pre-trained language models to predict disease phenotypes moreaccurately than non-text and single terminology approaches. We validate ourapproach using primary and secondary care data from the UK Biobank, alarge-scale research study. Finally, we illustrate in a type 2 diabetes usecase how sEHR-CE identifies individuals without diagnosis that share clinicalcharacteristics with patients.

sEHR-CE: Language modelling of structured EHR data for efficient and generalizable patient cohort expansion