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

Electronic Health Records (EHRs) exhibit a high amount of missing data due tovariations of patient conditions and treatment needs. Imputation of missingvalues has been considered an effective approach to deal with this challenge.Existing work separates imputation method and prediction model as twoindependent parts of an EHR-based machine learning system. We propose anintegrated end-to-end approach by utilizing a Compound Density Network (CDNet)that allows the imputation method and prediction model to be tuned togetherwithin a single framework. CDNet consists of a Gated recurrent unit (GRU), aMixture Density Network (MDN), and a Regularized Attention Network (RAN). TheGRU is used as a latent variable model to model EHR data. The MDN is designedto sample latent variables generated by GRU. The RAN serves as a regularizerfor less reliable imputed values. The architecture of CDNet enables GRU and MDNto iteratively leverage the output of each other to impute missing values,leading to a more accurate and robust prediction. We validate CDNet on themortality prediction task on the MIMIC-III dataset. Our model outperformsstate-of-the-art models by significant margins. We also empirically show thatregularizing imputed values is a key factor for superior predictionperformance. Analysis of prediction uncertainty shows that our model cancapture both aleatoric and epistemic uncertainties, which offers model users abetter understanding of the model results.

Compound Density Networks for Risk Prediction using Electronic Health Records