Format

Send to:

Choose Destination
See comment in PubMed Commons below
AMIA Jt Summits Transl Sci Proc. 2013 Mar 18;2013:203-7. eCollection 2013.

Semantic ETL into i2b2 with Eureka!

Author information

  • 1Center for Comprehensive Informatics, Emory University, Atlanta, GA.

Abstract

Clinical phenotyping is an emerging research information systems capability. Research uses of electronic health record (EHR) data may require the ability to identify clinical co-morbidities and complications. Such phenotypes may not be represented directly as discrete data elements, but rather as frequency, sequential and temporal patterns in billing and clinical data. These patterns' complexity suggests the need for a robust yet flexible extract, transform and load (ETL) process that can compute them. This capability should be accessible to investigators with limited ability to engage an IT department in data management. We have developed such a system, Eureka! Clinical Analytics. It extracts data from an Excel spreadsheet, computes a broad set of phenotypes of common interest, and loads both raw and computed data into an i2b2 project. A web-based user interface allows executing and monitoring ETL processes. Eureka! is deployed at our institution and is available for deployment in the cloud.

PMID:
24303265
[PubMed]
PMCID:
PMC3845783
Free PMC Article
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for PubMed Central
    Loading ...
    Write to the Help Desk