An Accessible Approach for Fusion of Environmental and Human Health Data for Disease Surveillance

This presentation will describe the subtasks and associated obstacles to combining disparate evidence from health surveillance data streams and environmental sensors for prospective monitoring of public health threats. An approach to this combined monitoring will be presented along with examples from a recent project at the Johns Hopkins Applied Physics Laboratory in collaboration with the U.S. Environmental Protection Agency. The project objective is to build a module for the Electronic Surveillance System for the Early Notification of Community-based Epidemics (ESSENCE) to include water quality data with health indicator data for the early detection of waterborne disease outbreaks.

The basic question in the fused surveillance application is “What is the likelihood of the public health threat of interest given recent information from available sources of evidence?” This question will be analyzed by analogy to estimation of positive predictive value customary in classical epidemiology, and a solution framework will be presented using Bayesian Networks (BN). An overview of the BN approach will present advantages, disadvantages, and required adaptations needed for a fused surveillance capability that is scalable and robust relative to the practical data environment. Elements of the art of developing networks appropriate to this environment will be discussed with examples.

The presentation will also discuss the developer-client relationship in fused surveillance systems, including elicitation of expert domain knowledge and the essential roles of the data provider and system user.