DBMI Data Portal

Data and computing resources from the
Department of Biomedical Informatics (DBMI)
in the Blavatnik Institute
at Harvard Medical School

data concept image

Data Sets

The i2b2 NLP data sets previously released on i2b2.org are now hosted here on the DBMI Data Portal under their new moniker, n2c2 (National NLP Clinical Challenges):

These data sets are the result of annual NLP challenges dating back to 2006, originally organized as part of the i2b2 project (Informatics for Integrating Biology and the Bedside).

Data Challenges

The n2c2 challenge series now continues under the stewardship of DBMI, with data access and challenge participation administered through this data portal and additional information provided through the public n2c2 website.

Our 2022 n2c2 challenge culminated with a workshop at the 2022 AMIA Annual Symposium . Thanks to all who participated! Results of Track 2 on Social Determinants of Health will also be published in a December 2023 special issue of JAMIA .

About Us

The faculty and data scientists of DBMI are working at the nexus of software engineering, biological sciences, and the clinical practice of medicine. Learn more by checking out the DBMI Github repository and this selection of resources from our faculty labs: