General Project Information

Biomedical Information Collection and Understanding System (BiomedICUS) leverages open source solutions for text analysis and provides new analytic tools for processing and analyzing text of clinical reports. The system is being developed by the biomedical NLP group at the University of Minnesota. This is a collaborative project that currently includes the Institute for Health Informatics, College of Pharmacy and the Computer Science Department at the University of Minnesota.

Objective

Develop a modularized NLP system customized specifically for processing clinical text in order to support educational and research initiatives at the University of Minnesota and the larger NLP community. The BiomedICUS project is intended to provide a basic platform that can be used for students and researchers interested in biomedical NLP to learn not only how to deploy these applications for processing large collections of text but also how to participate in the development of new biomedical NLP modules and applications.

Development Platform

BiomedICUS currently relies on the Apache Unstructured Information Management Architecture (UIMA) application development platform, as well as open-source UIMAFit and ClearTK packages.