Discovering and Describing New De-Identified Cohorts of Patients with i2b2 Framework

The Mount Sinai Scientific Computing and Data Science team has launched training resources via PEAK to take researchers step-by-step through the i2b2 (Informatics for Integrating Biology & the Bedside) program, preparing them to take advantage of this cost-effective and efficient way to identify patients for many types of clinical and translational research. The i2b2 framework was developed through NIH funding to make research cohort discovery possible through the integration, standardization, and analysis of heterogeneous data from electronic health record systems. The implementation of i2b2 at the Mount Sinai Health System is supported by ConduITS, the Institutes for Translational Sciences and Mount Sinai’s CTSA (an NIH|NCATS Clinical and Translational Science Award).

To access the training on PEAK, simply click here, or head over to, sign in and search for “i2b2.” It’s also available through clicking on Online Courses, navigating to Research and clicking on the i2b2 Tutorial.

With an easy to use, drag-and-drop interface, i2b2 enables researchers to query a repository of patient information gathered from multiple sources throughout the Mount Sinai Health System, including electronic medical records, lab results, and demographic data. Using de-identified data, investigators can determine potential cohorts of interest for later obtaining identified or limited data sets with Institutional Review Board (IRB) approval. For more information about the IRB approval process, contact

This web-based tool works on Windows and Mac, on multiple browsers (Firefox, Internet Explorer, Safari, and Google Chrome) within the Mount Sinai network (on campus or via VPN). Data is uploaded from the Mount Sinai Data Warehouse on a regular basis, but only de-identified data can be accessed through the web client. Mount Sinai researchers can perform queries at

Please email with questions or comments.