Wednesday, 5/23/2007
8:00 AM - 9:00 AM
Level: Technical - Advanced

We propose a Semantic Web approach to processing free-form text information such as chief complaints, discharge diagnosis, clinical reports, nurse notes, and triage summaries using formal knowledge representation, Description Logic (DL), and rules reasoning. We have developed a method to explicate formally what is important in non-structured texts (e.g., signs, symptoms, diseases or illnesses, procedures, etc.) with as much context as is possible around those observations (i.e., anatomy, physiological context, chronicity, quantities, qualities, temporal aspects, negation and uncertainty modifiers, presenter, causative context, etc.). The formal representation of NLU output and use of standard vocabulary services (i.e., UMLS) supports integrating clinical text data with the rest of the patient electronic health record (EHR) at query time, multidisciplinary use of unstructured data for research, clinical and public health use, information sharing, and interoperability. Output is a computationally interpretable representation of clinical text data through the Resource Definition Framework (RDF) and is mapped to the UMLS Metathesaurus.

Parsa Mirhaji, M.D. is Assistant Professor of Medicine at the University of Texas Health Science Center at Houston School of Medicine and Adjunct Assistant Professor of Health Information Sciences at the School of Health Information Sciences. Dr. Mirhaji is Director of The Center for Biosecurity and Public Health Informatics Research, where he has developed predictive epidemiology models and detection methodologies for emerging infectious diseases such as avian flu and a reference architecture for situational awareness for public health preparedness (SARA). Dr. Mirhaji has been an acting committee member on the Texas Hospital Preparedness Program at the Texas Department of Health and Human Services and the Texas Institute for Health Policy Research, a selected member of Technology Subcommittee – Health Information Technology Advisory Commission, Texas Department of Health and Human Services, chair of the International Defense and Homeland Security Conference 2003-2006, and chair of the International Conference on Rule Markup Languages for the Semantic Web, 2006.