Refinement of a Population-Based Bayesian Network for Fusion of Health Surveillance Data

Authors

  • Howard Burkom Johns Hopkins Applied Physics Laboratory, Laurel, MD
  • Yevgeniy Elbert Johns Hopkins Applied Physics Laboratory, Laurel, MD
  • Liane Ramac-Thomas Johns Hopkins Applied Physics Laboratory, Laurel, MD
  • Christopher Cuellar Johns Hopkins Applied Physics Laboratory, Laurel, MD
  • Vivian Hung Johns Hopkins Applied Physics Laboratory, Laurel, MD

DOI:

https://doi.org/10.5210/ojphi.v5i1.4413

Abstract

The project was to refine a prototype population-based Bayes Network module for live implementation in the U.S. Department of Defense ESSENCE system to combine syndromic and clinical evidence sources to monitor health at hundreds of military care facilities. Evidence types included outpatient data records, laboratory tests, and filled prescription records. The multi-level approach included expanded data queries, data-sensitive algorithm selection, improved transformation of algorithm outputs to alert states, and hierarchical Bayesian Network training. Algorithmic and network thresholds were adjusted with stochastic optimization using 24 documented outbreak datasets.

Author Biography

Howard Burkom, Johns Hopkins Applied Physics Laboratory, Laurel, MD

Howard Burkom is a project manager and researcher within the disease surveillance initiative of the Johns Hopkins Applied Physics Laboratory. He is also a statistical consultant to the Biosense team at CDC, collaborating on system improvements and with health departments on public health applications. An elected member of the ISDS Board Of Directors for 7 years, He has worked exclusively in biosurveillance since 2000, adapting analytic methods from various scientific disciplines for disease monitoring systems.

Downloads

Published

2013-03-23

How to Cite

Burkom, H., Elbert, Y., Ramac-Thomas, L., Cuellar, C., & Hung, V. (2013). Refinement of a Population-Based Bayesian Network for Fusion of Health Surveillance Data. Online Journal of Public Health Informatics, 5(1). https://doi.org/10.5210/ojphi.v5i1.4413

Issue

Section

Oral Presentations: Analytical Methods - Bayesian