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 Record (EHR) data, while rich in information, often suffersfrom sparsity, posing significant challenges in predictive modeling.Traditional imputation methods inadequately distinguish between real andimputed data, leading to potential inaccuracies in models. Addressing this, weintroduce PRISM, a novel approach that indirectly imputes data throughprototype representations of similar patients, thus ensuring denser and moreaccurate embeddings. PRISM innovates further with a feature confidence learnermodule, which evaluates the reliability of each feature in light of missingdata. Additionally, it incorporates a novel patient similarity metric thataccounts for feature confidence, avoiding overreliance on imprecise imputedvalues. Our extensive experiments on the MIMIC-III and MIMIC-IV datasetsdemonstrate PRISM's superior performance in predicting in-hospital mortalityand 30-day readmission tasks, showcasing its effectiveness in handling EHR datasparsity. For the sake of reproducibility and further research, we have madethe code publicly available at https://github.com/yhzhu99/PRISM.

PRISM: Leveraging Prototype Patient Representations with Feature-Missing-Aware Calibration for EHR Data Sparsity Mitigation