i2b2: Informatics for Integrating Biology & the Bedside - A National Center for Biomedical Computing

i2b2 (Informatics for Integrating Biology and the Bedside) is an NIH-funded National Center for Biomedical Computing based at Partners HealthCare System. The i2b2 Center is developing a scalable informatics framework that will enable clinical researchers to use existing clinical data for discovery research and, when combined with IRB-approved genomic data, facilitate the design of targeted therapies for individual patients with diseases having genetic origins. This platform currently enjoys wide international adoption by the CTSA network, academic health centers, and industry.  i2b2 is funded as a cooperative agreement with the National Institutes of Health.

    Current DBPs
        Autoimmune/CV Diseases
        Diabetes/CV Diseases
    Past DBPs
        Airways Diseases
        Type 2 Diabetes Mellitus
        Huntington's Disease
        Major Depressive Disorder
        Rheumatoid Arthritis
      Computational Tools
      De-Identification Demo
      NLP Research Data Sets
      NLP Shared Tasks
      Academic Users' Group
      Publication Data



       ***i2b2 Installations Worldwide***


      July 10-11, 2014

      Joseph Martin Conference Facility at Harvard Medical School

      77 Avenue Louis Pasteur

      Boston, MA  02115

      E-registration available soon

      *** i2b2 NLP DATA SET #5 (from 2011 Challenge) ***

      Now available for research purposes

      A complete set of annotated and unannotated, deidentified patient discharge summaries from the First, Second (Obesity),Third (Medication) and Fourth Shared Tasks for Challenges in NLP for Clincial Data are now available to the community for research purposes. Check it out at our NLP Data Sets page . Please note you must register AND submit a DUA for access.

      *** Publications In the News ***

      Ananthakrishnan AN, Gainer VS, Perez RG, Cai T, Cheng SC, Savova G, Chen P, Szolovits P, Xia Z, DeJager PL, Shaw SY, Churchill S, Karlson EW, Kohane IS, Perlis RH, Plenge RM, Murphy SN, Liao KP.  Psychiatric co-morbidity is associated with increased risk of surgery in Crohn's Disease.  Aliment Pharmacol Ther. 2013 Feb;37(4)445-54.  PMC3552092.

      Ananthakrishnan AN, Gainer VS, Perez RG, Cai T, Cheng SC, Savova G, Chen P, Szolovits P, Xia Z, DeJager PL, Shaw SY, Churchill S, Karlson EW, Kohane IS, Plenge RM, Murphy SN, Liao KP. Improving Case Definition of Crohn's Disease and Ulcerative Colitis in Electronic Medical Records Using Natural Language Processing: A Novel Informatics Approach.  Inflamm Bowel Dis. 2013 Jun;19(7):1411-1420.  PMC3665760.

      Chen L, Karlson E, Canhao H, Miller T, Dliogach D, Chen P, Guzman R, Cai T., Weinblatt M, Shadick N, Plenge R, Savova G.  Automatic prediction of rheumatoid arthritis disease activity from the electronic medical records.  PlosOne.  2013;8(8):e69932.  PMC3745469.

      Masys DR, Harris PA, Fearn PA, Kohane IS.  Designing a public square for research computing.  Sci Transl Med. 2012 Aug 29;4(149):149fs32.  PMC3725749.

      McMurry AJ, Murphy SN, MacFadden D, Weber G, Simons WW, Orechia J, Bickel J, Wattanasin N, Gilbert C, Trevvett P, Churchill S, Kohane IS.  SHRINE: enabling nationally scalable multi-site disease studies.   PLoS One.  2013;8(3):55811.  PMC3591385.

      *** i2b2 ROADMAP for 2013 ***

      Release 1.7 = “Temporal Query enabled i2b2”

      Now available at our Software Page.

      Version 1.7 of the i2b2 software features two important innovations. The first is the introduction of temporal queries, an implementation of the temporal theory development from Core 1. This will allow the definition of events from collections of observations, and then the ordering of those events to occur in specific sequences with a specified number of intervening hours or days. The second innovation is support for the identity management cell which will enable the maintenance of protected health information in a separate area of the i2b2 Hive. The workflows that begin with unencrypted, fully identified notes or other kinds of identified data will be able to produce de-identified data at various levels. Depending on the transformation chosen, de-identified data may also be linked back to its original identified data.

      Release i2b2-CT = “Clinical-Trial enabled i2b2”

      In the summer of 2014 we are planning on the release of a version of i2b2 which represents a bundle of Community Supported i2b2 Plug-ins and Tools. This version will specifically support the end to end use case for the discovery of a set of patients for a clinical trial. Current plug-ins and features will be enhanced and new features added from the i2b2 community to provide increasingly focused selection capabilities to narrow down to a final, well qualified patient set. The process of advancing the levels of approval by data use agreements and institutional review boards will be supported to allow the recruitment process to proceed with the maximal respect for patient privacy and confidentiality.


      Contact | Sitemap | Search
      ©2014 Partners Healthcare