Syndromic surveillance requires acquiring and analyzing data that might suggest early epidemics in a community, long before there's categorical evidence of unusual infection. These data are often heterogeneous and noisy, and public health analysts must interpret them with a combination of analytic methods. Syndromic surveillance thus involves integrating data, configuring problem-solving strategies, and mapping integrated data to appropriate methods. The knowledge-based systems community has studied these tasks for years. We present a software architecture that supports knowledge-based data integration and problem solving, thereby facilitating many syndromic surveillance aspects. Central to our approach, a set of reference ontologies supports semantic integration, and a parallelizable blackboard architecture implements invocation of appropriate problem-solving methods and reasoning control. We demonstrate our approach with BioStorm, an experimental system that offers an end-to-end solution to syndromic surveillance.

This article is part of a special issue on Homeland Security.