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

Observational data in medicine arise as a result of the complex interactionbetween patients and the healthcare system. The sampling process is oftenhighly irregular and itself constitutes an informative process. When using suchdata to develop prediction models, this phenomenon is often ignored, leading tosub-optimal performance and generalisability of models when practices evolve.We propose a multi-task recurrent neural network which models three clinicalpresence dimensions -- namely the longitudinal, the inter-observation and themissingness processes -- in parallel to the survival outcome. On a predictiontask using MIMIC III laboratory tests, explicit modelling of these threeprocesses showed improved performance in comparison to state-of-the-artpredictive models (C-index at 1 day horizon: 0.878). More importantly, theproposed approach was more robust to change in the clinical presence setting,demonstrated by performance comparison between patients admitted on weekdaysand weekends. This analysis demonstrates the importance of studying andleveraging clinical presence to improve performance and create moretransportable clinical models.

DeepJoint: Robust Survival Modelling Under Clinical Presence Shift