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/

Zendy Plus

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

Zendy Tools

Zendy Open

Phenotyping electronic health records (EHR) focuses on defining meaningfulpatient groups (e.g., heart failure group and diabetes group) and identifyingthe temporal evolution of patients in those groups. Tensor factorization hasbeen an effective tool for phenotyping. Most of the existing works assumeeither a static patient representation with aggregate data or only modeltemporal data. However, real EHR data contain both temporal (e.g., longitudinalclinical visits) and static information (e.g., patient demographics), which aredifficult to model simultaneously. In this paper, we propose Temporal AndStatic TEnsor factorization (TASTE) that jointly models both static andtemporal information to extract phenotypes. TASTE combines the PARAFAC2 modelwith non-negative matrix factorization to model a temporal and a static tensor.To fit the proposed model, we transform the original problem into simpler oneswhich are optimally solved in an alternating fashion. For each of thesub-problems, our proposed mathematical reformulations lead to efficientsub-problem solvers. Comprehensive experiments on large EHR data from a heartfailure (HF) study confirmed that TASTE is up to 14x faster than severalbaselines and the resulting phenotypes were confirmed to be clinicallymeaningful by a cardiologist. Using 80 phenotypes extracted by TASTE, a simplelogistic regression can achieve the same level of area under the curve (AUC)for HF prediction compared to a deep learning model using recurrent neuralnetworks (RNN) with 345 features.

TASTE: Temporal and Static Tensor Factorization for Phenotyping Electronic Health Records