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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Accurate mortality prediction allows Intensive Care Units (ICUs) toadequately benchmark clinical practice and identify patients with unexpectedoutcomes. Traditionally, simple statistical models have been used to assesspatient death risk, many times with sub-optimal performance. On the other handdeep learning holds promise to positively impact clinical practice byleveraging medical data to assist diagnosis and prediction, including mortalityprediction. However, as the question of whether powerful Deep Learning modelsattend correlations backed by sound medical knowledge when generatingpredictions remains open, additional interpretability tools are needed tofoster trust and encourage the use of AI by clinicians. In this work we show aDeep Learning model trained on MIMIC-III to predict mortality using raw nursingnotes, together with visual explanations for word importance. Our model reachesa ROC of 0.8629 (+/-0.0058), outperforming the traditional SAPS-II score andproviding enhanced interpretability when compared with similar Deep Learningapproaches.

ISeeU2: Visually Interpretable ICU mortality prediction using deep learning and free-text medical notes