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

The widespread availability of electronic health records (EHRs) promises tousher in the era of personalized medicine. However, the problem of extractinguseful clinical representations from longitudinal EHR data remains challenging.In this paper, we explore deep neural network models with learned medicalfeature embedding to deal with the problems of high dimensionality andtemporality. Specifically, we use a multi-layer convolutional neural network(CNN) to parameterize the model and is thus able to capture complex non-linearlongitudinal evolution of EHRs. Our model can effectively capture local/shorttemporal dependency in EHRs, which is beneficial for risk prediction. Toaccount for high dimensionality, we use the embedding medical features in theCNN model which hold the natural medical concepts. Our initial experimentsproduce promising results and demonstrate the effectiveness of both the medicalfeature embedding and the proposed convolutional neural network in riskprediction on cohorts of congestive heart failure and diabetes patientscompared with several strong baselines.

Exploiting Convolutional Neural Network for Risk Prediction with Medical Feature Embedding