The BioMedical Information Collection and Understanding System (BioMedICUS) is a system for large-scale text analysis and processing of biomedical and clinical reports. The system is being developed by the Natural Language Processing and Information Extraction Program at the University of Minnesota Institute for Health Informatics.

This is a collaborative project that aims to serve biomedical and clinical researchers, allowing for customization with different texts.

Project Goals

To see what tasks the system supports, look at Components and Outputs. If you are looking for a jumping-in point, see Installation.


RTF Reader

BioMedICUS has an RTF Reader, which has the ability to read and process notes that are encoding in RTF. In addition, BioMedICUS uses RTF formatting information downstream to improve other components.

Acronym Detection

Included in the standard pipeline is an acronym detector, which has the ability to detect and expand acronyms to their equivalent long forms.

Concept Detection

BioMedICUS includes a fast concept detector which labels instances of UMLS Metathesaurus concepts in text.


For downloads see the releases page on GitHub. We also make more comprehensive models that require you to have a UMLS license available here.


Our wiki on GitHub contains information about installation, configuration, use, and development of BioMedICUS.

Contact and Support

For issues or enhancement requests, feel free to submit to the Issues tab on GitHub.

BioMedICUS has a gitter chat for contacting developers with questions, suggestions or feedback.

About Us

BioMedICUS is developed by the University of Minnesota Institute for Health Informatics NLP/IE Group with assistance from the Open Health Natural Language Processing (OHNLP) Consortium.

Other Resources


NLP/IE Group Resources


Funding for this work was provided by:

The following people have made code contributions not represented in the commit history: