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

Predicting patient mortality is an important and challenging problem in thehealthcare domain, especially for intensive care unit (ICU) patients.Electronic health notes serve as a rich source for learning patientrepresentations, that can facilitate effective risk assessment. However, alarge portion of clinical notes are unstructured and also contain domainspecific terminologies, from which we need to extract structured information.In this paper, we introduce an embedding framework to learnsemantically-plausible distributed representations of clinical notes thatexploits the semantic correspondence between the unstructured texts and theircorresponding structured knowledge, known as semantic frame, in a hierarchicalfashion. Our approach integrates text modeling and semantic correspondencelearning into a single model that comprises 1) an unstructured embedding modulethat makes use of self-similarity matrix representations in order to injectstructural regularities of different segments inherent in clinical texts topromote local coherence, 2) a structured embedding module to embed the semanticframes (e.g., UMLS semantic types) with deep ConvNet and 3) a hierarchicalsemantic correspondence module that embeds by enhancing the interactionsbetween text-semantic frame embedding pairs at multiple levels (i.e., words,sentence, note). Evaluations on multiple embedding benchmarks on post dischargeintensive care patient mortality prediction tasks demonstrate its effectivenesscompared to approaches that do not exploit the semantic interactions betweenstructured and unstructured information present in clinical notes.

Hierarchical Semantic Correspondence Learning for Post-Discharge Patient Mortality Prediction