Multi-Institution Project Aims To Convert EHR Data Into Phenotypes

December 5, 2014 in News

Researchers at four institutions are working to convert electronic health record data into phenotypes focused on diseases and other specific health traits, Health Data Management reports.

Project Details

The four-year, $2.1 million project is funded by the National Science Foundation.

Institutions involved in the project include:

  • The Georgia Institute of Technology;
  • Northwestern University;
  • The University of Texas at Austin; and
  • Vanderbilt University.

Initial EHR data for the project will be provided by Vanderbilt University, which also will validate the newly created phenotypes.

Data analytics teams from the Georgia Institute of Technology and the University of Texas at Austin will develop the algorithms and methods needed to convert the EHR data into phenotypes. At which point, the phenotypes will be refined and adapted alongside data from Northwestern University so that they can be used across multiple organizations.

Project Goals

According to Health Data Management, the project will focus on three applications, including:

  • Developing predictive models for health studies; and
  • Creating a system to accurately identify patients for clinical research.

The project will allow researchers to study multiple phenotypes simultaneously and help them analyze patient health factors displayed by those with Type 2 diabetes.

In addition, the researchers will work to develop a massive open online course curriculum for health analytics (Goth, Health Data Management, 12/4).

Be the first to like.
VN:F [1.9.22_1171]
Rating: 0.0/5 (0 votes cast)

Article source: http://feedproxy.google.com/~r/Ihealthbeat/~3/KBUAF5YJirA/multi-institution-project-aims-to-convert-ehr-data-into-phenotypes

Be Sociable, Share!
Bookmark and Share

Leave a reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>