|
|
|||||||||
|
Persons using assistive technology might not be able to fully access information in this file. For assistance, please send e-mail to: mmwrq@cdc.gov. Type 508 Accommodation and the title of the report in the subject line of e-mail. Semantic Approach to Public Health Situation Awareness --- Design and MethodologyParsa Mirhaji, S. Lillibridge, R. Richesson, J. Zhang, J. Smith
Corresponding author: Parsa Mirhaji, University of Texas Health Science Center at Houston, Houston, Texas 77030. Telephone: 713-500-3157; Fax: 713-500-0370; E-mail; pmirhaji@uth.tmc.edu. AbstractIntroduction: A public health situation awareness system is proposed that 1) uses explicit representation of surveillance concepts based on the user's cognitive model, and 2) is optimized for efficacy of performance and relevance to the process and task, rather than for ontic accuracy of syndrome definitions. Objectives: The goal of this effort is to develop a prototype knowledge-based system that demonstrates the utility of knowledge-intensive approaches in 1) integrating heterogeneous information (e.g., patient triage data, pharmacy sales data, and school absenteeism data); 2) eliminating the effects of incomplete and poor-quality surveillance data; 3) reducing uncertainty in syndrome and aberration detection; and 4) enabling visualization of complex information structures in surveillance settings, particularly in the context of biologic terrorism preparedness. Methods: For this approach, explicit domain knowledge is the foundation for interpreting public health data, as opposed to conventional systems for which statistical methods are central. The system uses the Resource Definition Framework (i.e., a framework for representing information that enables machines and humans to communicate) and expressive language (i.e., Web Ontology Language [OWL]) to explicate human knowledge into machine-interpretable and computable problem-solving modules that can guide users and computer systems in sifting through relevant data to detect outbreaks. Results: A prototype knowledge-based system for early detection of outbreaks of influenza, which has a complex natural pattern and is a potential agent for biologic terrorism, is being developed. A model has been developed (using OWL ontology language) to enable case detection for respiratory illness syndromes caused by weaponized influenza. A knowledge-based system to integrate relevant health data from nine community hospitals has also been developed. Conclusions: Preliminary data from this effort will evaluate the utility of knowledge-based approaches in information integration, syndrome and aberration detection, information visualization, and cross-domain investigation of root causes of events.
Disclaimer All MMWR HTML versions of articles are electronic conversions from ASCII text into HTML. This conversion may have resulted in character translation or format errors in the HTML version. Users should not rely on this HTML document, but are referred to the electronic PDF version and/or the original MMWR paper copy for the official text, figures, and tables. An original paper copy of this issue can be obtained from the Superintendent of Documents, U.S. Government Printing Office (GPO), Washington, DC 20402-9371; telephone: (202) 512-1800. Contact GPO for current prices. **Questions or messages regarding errors in formatting should be addressed to mmwrq@cdc.gov.Page converted: 9/14/2004 |
|||||||||
This page last reviewed 9/14/2004
|