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

Determining phenotypes of diseases can have considerable benefits forin-hospital patient care and to drug development. The structure of highdimensional data sets such as electronic health records are often representedthrough an embedding of the data, with clustering methods used to group data ofsimilar structure. If subgroups are known to exist within data, supervisedmethods may be used to influence the clusters discovered. We propose to extenddeep embedded clustering to a semi-supervised deep embedded clusteringalgorithm to stratify subgroups through known labels in the data. In this workwe apply deep semi-supervised embedded clustering to determine data-drivenpatient subgroups of heart failure from the electronic health records of 4,487heart failure and control patients. We find clinically relevant clusters froman embedded space derived from heterogeneous data. The proposed algorithm canpotentially find new undiagnosed subgroups of patients that have differentoutcomes, and, therefore, lead to improved treatments.

Deep Semi-Supervised Embedded Clustering (DSEC) for Stratification of Heart Failure Patients