Predicting Levels of Influenza Incidence

Authors

  • Anna L. Buczak JHU APL, Laurel, MD, United States
  • Liane Ramac-thomas JHU APL, Laurel, MD, United States
  • Erhan Guven JHU APL, Laurel, MD, United States
  • Yevgeniy Elbert JHU APL, Laurel, MD, United States
  • Steven Babin JHU APL, Laurel, MD, United States
  • Benjamin Baugher JHU APL, Laurel, MD, United States
  • Sheri Lewis

DOI:

https://doi.org/10.5210/ojphi.v6i1.5149

Abstract

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.

Author Biography

Anna L. Buczak, JHU APL, Laurel, MD, United States

Dr. Anna L. Buczak is a Project Manager at the Johns Hopkins University APL. She holds a PhD in Applied Artificial Intelligence and an MS and a BS in Computer Science.  Her research interests include machine learning with emphasis on biologically inspired learning methods, data mining and anomaly detection.  The methods she develops perform disease outbreak prediction (dengue, malaria, flu), derive patient care models from medical records, and detect anomalies in data streams, coming from counts recorded by biosurveillance systems, such as ESSENCE.

Downloads

Published

2014-03-09

How to Cite

Buczak, A. L., Ramac-thomas, L., Guven, E., Elbert, Y., Babin, S., Baugher, B., & Lewis, S. (2014). Predicting Levels of Influenza Incidence. Online Journal of Public Health Informatics, 6(1). https://doi.org/10.5210/ojphi.v6i1.5149

Issue

Section

Lightning Talks