i2b2 – Informatics for Integrating Biology and the Bedside

What is i2b2?

i2b2 is an NIH-funded National Center for Biomedical Computing (NCBC) based at Partners HealthCare System. The i2b2 NCBC developed a scalable informatics framework that bridges clinical research data and the vast data banks arising from basic science research in order to better understand the genetic bases of complex diseases.  This open-source platform currently enjoys wide international adoption by the CTSA network, academic health centers, and industry.  i2b2 was designed primarily for cohort identification, allowing users to perform an enterprise-wide search on de-identified data from the Clinical Data Warehouse, Health Facts, to determine the existence of a set of patients meeting certain inclusion or exclusion criteria. The i2b2 framework is packaged with a query tool that allows the user to drag-and-drop search terms from a hierarchical ontology into a Venn diagram-like interface. Researchers can perform an initial analysis on the de-identified cohort, and if the results are promising, researchers can request approval from the IRB for the fully identified extract. 

Why i2b2?

  • Enables Augusta University and AUMC to build an informatics infrastructure framework to support the translation of basic medical research into medical practice.
  • Reduces the time researchers spend in the discovery of research cohorts, study feasibility, recruitment of subjects and development of evidence-based protocols.
  • Identifies potential cohorts for clinical trials.
  • Aids in creating new research hypotheses.
  • Performs retrospective data analysis.
  • Gives researchers the ability to formulate complex queries using an understandable user interface and a set of well-defined patient characteristics.
  • Provides potential for funding and/or collaboration.


  • The architecture consists of two major pieces. The first is the back-end infrastructure (the "Hive") that takes care of security, access rights and managing the underlying data repository. The second piece is an application suite of query and mining tools that allows users to ask questions about the data (the workbench).
  • Provides a reliable and secure way to access clinical data without compromising patient privacy. 
  • Protects patient identities by returning aggregate numbers of patients that satisfy a user-defined query.
  • Web-based, easy to use, and HIPAA compliant.

Structure and Functionality:

The i2b2 environment is loaded with clinical data from December 2009, and a process has been developed to add new data from the clinical data warehouse on a daily basis.  A set of web-based tools have been developed that allows registered users to query the warehouse. Once executed, the query will return the aggregate number or set of patients meeting the specified criteria. 

i2b2 Current Plans and Process:

Upon request, Research Development Services (RDS) will run a database query for researchers based on no more than 3 Facts (diagnosis, demographics, laboratory, medications and procedures). To request a search email: jhayman@augusta.edu

Click here for a list of workbench ontologies for your query request.

Researchers who have completed a training class or web-based tutorial and verified CITI training, can register for access to i2b2 for de-identified searches. Once an account has been set up, researchers can perform their own queries in the de-identified database. Visit the Training website (http://www.augusta.edu/ocis/i2b2training.html) for more information. 

Future Plans:

  • Access to additional five years of historical data. 
  • Exploration of product enhancements that will allow additional Augusta University databases, such as the Cancer Registry, tumor bank and bio-repositories.
  • Collaboration and access to other i2b2 databases through Shared Health Research Information Network (SHRINE).

As implementation of the warehouse progresses, this page will be updated to provide information on included data sources, current projects and tools under development. 


If you have questions or requests, please contact Joy Hayman (i2b2_CTSRDS@augusta.edu or 1-6247).