Serving the enterprise and beyond with informatics for integrating biology and the bedside (i2b2)

Abstract

Informatics for Integrating Biology and the Bedside (i2b2) is one of seven projects sponsored by the NIH Roadmap National Centers for Biomedical Computing (http://www.ncbcs.org). Its mission is to provide clinical investigators with the tools necessary to integrate medical record and clinical research data in the genomics age, a software suite to construct and integrate the modern clinical research chart. i2b2 software may be used by an enterprise's research community to find sets of interesting patients from electronic patient medical record data, while preserving patient privacy through a query tool interface. Project-specific mini-databases ("data marts") can be created from these sets to make highly detailed data available on these specific patients to the investigators on the i2b2 platform, as reviewed and restricted by the Institutional Review Board. The current version of this software has been released into the public domain and is available at the URL: http://www.i2b2.org/software.

Figure 1

The i2b2 web client is used as the interface for the enterprise users to construct queries. Patient attributes are dragged from the “Terms” panels into the “Query Tool” panels, and the patient sets that result after running the query which can be accessed and reused from the “Previous Queries” panels.

Figure 2

Sequential process for creating a project's data mart. The patient sets that were created in the query tool can be used in many places where the request is formulated, seen in the broken line boxes. The patient attribute terms from the i2b2 web client are used in the double line boxes to define the data that will be in the data mart.

Figure 3

The i2b2 Eclipse Workbench is generally used as the interface for working with specific project databases. It offers views for exporting and importing data to the project database, as well as views focused on specialized analysis. The i2b2 software architecture is built with multiple “plug-in” points. The i2b2 web client, the Java i2b2 Workbench, and the (server-side) data repository cell all have open architectures for additional software plug-in functionality.

Figure 4

All patient data is held in the Star Schema of the data repository. The tables are represented by each box, and the columns are represented by the rows of the box. Columns that are underlined are part of the primary key of the table. Columns that are in bold must always be filled. Columns with an asterisk next to them enhance the usability of the data repository but are not required. Further information on the data model and its use is available from the i2b2 website.