Big Data Resources & Tools

Child health researchers have access to a number of big data sets through affiliations with Emory University, Children's Healthcare of Atlanta and Georgia Tech. These resources can be used together both to determine feasibility of a clinical research project and to answer research questions.

Emory University's service catalog describes in depth its resources. For project feasibility and data mining projects, i2b2 is available. Emory i2b2 lets you query Emory Healthcare electronic health record data for patient counts and aggregate information. For more information, check out Emory i2b2's page. This resource is available to all who have an Emory NetID or Emory Healthcare login, and support is available at all stages.

Children’s Healthcare of Atlanta has resources for project feasibility and data collection, mining, analysis, and statistical projects.  These resources are accessible to CHOA-affiliated researchers. For questions about availability of use to you, please email

  • Advanced Analytics & Outcomes:  The Advanced Analytics & Outcomes team provides services to collect, extract, mine, and analyze EPIC, HR, and other CHOA-sourced data.  Extraction also includes clinical chart review extraction by a nurse.  To get started, submit a Data request here or email
  • REDCap: REDCap is a data collection tool used for support of online or offline data capture for clinical research studies and operations since 2013. Submit a request here to get started.

Georgia Tech researchers offer research partnerships to examine large data sets, including a Medicaid dataset. Due to restrictions on access to the Medicaid data, collaboration is encouraged for research success. Contact Leanne West about initiating partnerships.

  • OHDSI and OMOP: Observational Health Data Science and Informatics and Observational Medical Outcomes Partnership resources available to examine CHOA data. Contact Richard Starr to get started.
  • Medicaid data: in collaboration with CHOA, GT has purchased a large set of Medicaid data, available for a variaty of research projects. Contact Nicoleta Serban to start a collaboration.