Dr. Serguei Pakhomov
Mayo Clinic
Rochester, Minnesota

Applications of Natural Language Processing in Medical Informatics  
Research and Clinical Practice at the Mayo Clinic   

I will outline some key issues in Medical Informatics research and  
medical terminology development. It will be focused on the specific 
issues we are dealing with at the Mayo lab: automatic term extraction,  
automatic classification and indexing of clinical documents. I will 
describe how clinical data is represented in unrestricted text of clinical 
notes and some of the challenges it poses for NLP including data format, 
access and security. In the second half of the talk I will talk about some 
of the on-going research projects we are working on at Mayo: automatic 
abbreviation/acronym expansion, patient medication status identification, 
and thesaurus creation. I'd also like to touch upon a collaborative  
project we started with the NLP group at the National Library of Medicine  
where we are working on ways of expanding existing ontologies for medical  
domains with empirically derived data.