The Natural Language Processing / Information Extraction Program (NLP/IE)

About Us

The Natural Language Processing/Information Extraction (NLP/IE) Program is a team of investigators, postdoctoral researchers, developers, and students working together since 2009 advancing capabilities to process, extract, and encode information from unstructured biomedical and clinical texts, including clinical notes from the electronic health record and biomedical literature. Current active areas of NLP/IE research for our group include redundancy detection in clinical texts; biomedical semantic similarity and relatedness measures; acronym, abbreviation, and symbol disambiguation; semantic role labeling; automated monitoring of adverse drug events; literature-based discovery for drug repurposing; algorithms to extract phenotyping; tools for interoperability and integration of NLP systems; and specialized modules for different types of clinical texts.

Our Goal

Advance and leverage NLP/IE methods to improve healthcare across the spectrum of healthcare and research applications.

Our Resources

Our group has developed several NLP/IE resources including an open-source biomedical and clinical NLP/IE pipeline application, BioMedICUS (BioMedical Information Collection and Understanding System); an NLP ensemble tool with best in practice systems (NLP-ADAPT); and an NLP tool tailored self service for clinical and translational researchers (NLP-PIER). Several of our NLP/IE resources related to our projects are publicly available for other researchers.

Our Collaborators

University of Minnesota: 
Institute for Health Informatics, Clinical and Translational Science Institute, Center for Learning Health System Sciences, Medical School, Data Science Program

External Collaborators:
M Health Fairview, VA Hospital, Mayo Clinic, University of Texas at Houston, Duke University, University of California San Francisco, N3C / CD2H national consortium, OHDSI national consortium

Example Applied Research Use Cases with NLP/IE

Surgical Site Infection and other Surgical Complications, Cancer Phenotyping, Familial History, Social Determinants of Health, Stressors, Operative Note Intraoperative Events, Drug Repurposing for Alzheimer’s Disease, Dietary Supplements Survillance, Conversational Agent, Sentiment Analysis around use of Digital Technology, Portability and Fairness of NLP, Deep Transformer Networks