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

Background: Widespread adoption of electronic health records (EHRs) hasenabled secondary use of EHR data for clinical research and healthcaredelivery. Natural language processing (NLP) techniques have shown promise intheir capability to extract the embedded information in unstructured clinicaldata, and information retrieval (IR) techniques provide flexible and scalablesolutions that can augment the NLP systems for retrieving and ranking relevantrecords. Methods: In this paper, we present the implementation of CohortRetrieval Enhanced by Analysis of Text from EHRs (CREATE), a cohort retrievalsystem that can execute textual cohort selection queries on both structured andunstructured EHR data. CREATE is a proof-of-concept system that leverages acombination of structured queries and IR techniques on NLP results to improvecohort retrieval performance while adopting the Observational Medical OutcomesPartnership (OMOP) Common Data Model (CDM) to enhance model portability. TheNLP component empowered by cTAKES is used to extract CDM concepts from textualqueries. We design a hierarchical index in Elasticsearch to support CDM conceptsearch utilizing IR techniques and frameworks. Results: Our case study on 5cohort identification queries evaluated using the IR metric, P@5 (Precision at5) at both the patient-level and document-level, demonstrates that CREATEachieves an average P@5 of 0.90, which outperforms systems using onlystructured data or only unstructured data with average P@5s of 0.54 and 0.74,respectively.

CREATE: Cohort Retrieval Enhanced by Analysis of Text from Electronic Health Records using OMOP Common Data Model