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

Health conditions among patients in intensive care units (ICUs) are monitoredvia electronic health records (EHRs), composed of numerical time series andlengthy clinical note sequences, both taken at irregular time intervals.Dealing with such irregularity in every modality, and integrating irregularityinto multimodal representations to improve medical predictions, is achallenging problem. Our method first addresses irregularity in each singlemodality by (1) modeling irregular time series by dynamically incorporatinghand-crafted imputation embeddings into learned interpolation embeddings via agating mechanism, and (2) casting a series of clinical note representations asmultivariate irregular time series and tackling irregularity via a timeattention mechanism. We further integrate irregularity in multimodal fusionwith an interleaved attention mechanism across temporal steps. To the best ofour knowledge, this is the first work to thoroughly model irregularity inmultimodalities for improving medical predictions. Our proposed methods for twomedical prediction tasks consistently outperforms state-of-the-art (SOTA)baselines in each single modality and multimodal fusion scenarios.Specifically, we observe relative improvements of 6.5\%, 3.6\%, and 4.3\% in F1for time series, clinical notes, and multimodal fusion, respectively. Theseresults demonstrate the effectiveness of our methods and the importance ofconsidering irregularity in multimodal EHRs.

Improving Medical Predictions by Irregular Multimodal Electronic Health Records Modeling