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

Learning to represent free text is a core task in many clinical machinelearning (ML) applications, as clinical text contains observations and plansnot otherwise available for inference. State-of-the-art methods use largelanguage models developed with immense computational resources and trainingdata; however, applying these models is challenging because of the highlyvarying syntax and vocabulary in clinical free text. Structured informationsuch as International Classification of Disease (ICD) codes often succinctlyabstracts the most important facts of a clinical encounter and yields goodperformance, but is often not as available as clinical text in real-worldscenarios. We propose a \textbf{multi-view learning framework} that jointlylearns from codes and text to combine the availability and forward-lookingnature of text and better performance of ICD codes. The learned text embeddingscan be used as inputs to predictive algorithms independent of the ICD codesduring inference. Our approach uses a Graph Neural Network (GNN) to process ICDcodes, and Bi-LSTM to process text. We apply Deep Canonical CorrelationAnalysis (DCCA) to enforce the two views to learn a similar representation ofeach patient. In experiments using planned surgical procedure text, our modeloutperforms BERT models fine-tuned to clinical data, and in experiments usingdiverse text in MIMIC-III, our model is competitive to a fine-tuned BERT at atiny fraction of its computational effort.

A Multi-View Joint Learning Framework for Embedding Clinical Codes and Text Using Graph Neural Networks