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

Objective: To compare different deep learning architectures for predictingthe risk of readmission within 30 days of discharge from the intensive careunit (ICU). The interpretability of attention-based models is leveraged todescribe patients-at-risk. Methods: Several deep learning architectures makinguse of attention mechanisms, recurrent layers, neural ordinary differentialequations (ODEs), and medical concept embeddings with time-aware attention weretrained using publicly available electronic medical record data (MIMIC-III)associated with 45,298 ICU stays for 33,150 patients. Bayesian inference wasused to compute the posterior over weights of an attention-based model. Oddsratios associated with an increased risk of readmission were computed forstatic variables. Diagnoses, procedures, medications, and vital signs wereranked according to the associated risk of readmission. Results: A recurrentneural network, with time dynamics of code embeddings computed by neural ODEs,achieved the highest average precision of 0.331 (AUROC: 0.739, F1-Score:0.372). Predictive accuracy was comparable across neural network architectures.Groups of patients at risk included those suffering from infectiouscomplications, with chronic or progressive conditions, and for whom standardmedical care was not suitable. Conclusions: Attention-based networks may bepreferable to recurrent networks if an interpretable model is required, at onlymarginal cost in predictive accuracy.

Benchmarking Deep Learning Architectures for Predicting Readmission to the ICU and Describing Patients-at-Risk