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

Making the most use of abundant information in electronic health records(EHR) is rapidly becoming an important topic in the medical domain. Recent workpresented a promising framework that embeds entire features in raw EHR dataregardless of its form and medical code standards. The framework, however, onlyfocuses on encoding EHR with minimal preprocessing and fails to consider how tolearn efficient EHR representation in terms of computation and memory usage. Inthis paper, we search for a versatile encoder not only reducing the large datainto a manageable size but also well preserving the core information ofpatients to perform diverse clinical tasks. We found that hierarchicallystructured Convolutional Neural Network (CNN) often outperforms thestate-of-the-art model on diverse tasks such as reconstruction, prediction, andgeneration, even with fewer parameters and less training time. Moreover, itturns out that making use of the inherent hierarchy of EHR data can boost theperformance of any kind of backbone models and clinical tasks performed.Through extensive experiments, we present concrete evidence to generalize ourresearch findings into real-world practice. We give a clear guideline onbuilding the encoder based on the research findings captured while exploringnumerous settings.

Rediscovery of CNN's Versatility for Text-based Encoding of Raw Electronic Health Records