Rule-Based Complex Event Processing for Food Safety and Public Health

The challenge for public health officials is to detect an emerging foodborne disease outbreak from a large set of simple and isolated, domainspecific events. These events can be extracted from a large number of distinct information systems such as surveillance and laboratory reporting systems from health care providers, real-time complaint hotlines from consumers, and inspection reporting systems from regulatory agencies. In this paper we formalize a foodborne disease outbreak as a complex event and apply an event-driven rulebased engine to the problem of detecting emerging events. We define an evidence set as a set of simple events that are linked symptomatically, spatially and temporally. A weighted metric is used to compute the strength of the evidence set as a basis for response by public health officials.