Data Mining for Recognizing Patterns in Foodborne Disease Outbreaks
*Sigurdur Olafsson, Iowa State University Department of Industrial and Manufacturing Systems Engineering 

Keywords: Foodborne disease outbreaks, surveillance databases, data mining, classification, association rule mining, attribute selection

This presentation features three data mining methods, attribute selection, decision tree learning, and association rule discovery, to extract previously unknown and meaningful patterns concerning foodborne disease outbreaks, applied to study the four most common outbreak etiologies in 2006, Salmonella enteritidis, Salmonella typhimurium, Escherichia coli, and Norovirus. The analysis reveals various patterns relating each of these outbreak types to specific foods and consumption locations. Discovery of patterns in foodborne disease outbreak data is useful in determination and implementation of suitable intervention techniques. In particular, custom intervention techniques including specific training methods can be tailored to train individuals in hygienic food handling, preparation, and consumption practices.