Predicting Levels of Influenza Incidence

Anna L. Buczak, Liane Ramac-thomas, Erhan Guven, Yevgeniy Elbert, Steven Babin, Benjamin Baugher, Sheri Lewis


Advanced techniques in fuzzy association rule data mining and integrating evidence from multiple sources are used to predict levels of influenza incidence several weeks in advance and display results on a map in order to help public health professionals prepare mitigation measures. This approach exploits the complicated relationships between disease incidence and measurable environmental, biological, and sociological variables that were found to have associations with the disease in other studies. Predictions were compared with data not used in model development in order to avoid exaggerated values of performance. The positive and negative predictive values were 0.941 and 0.935, respectively.

Full Text:



Online Journal of Public Health Informatics * ISSN 1947-2579 *