Simulation for assessing statistical methods of biologic terrorism surveillance

Abstract

Introduction: Multiple systems have been developed that use surveillance of health-care encounters to provide early warning of a terrorist attack. Limited practical experience and the absence of adequate theoretical assessments have precluded determining which alarm-generating algorithms should be preferred. In the absence of practical and theoretical results, choosing a particular statistical algorithm can be difficult. One way to evaluate algorithms is through simulation.

Objectives: This report describes conceptual features of an example simulation based on the dispersal of anthrax spores and presents results based on the example simulation.

Methods: A simulation was implemented based on the dispersal of anthrax spores from a crop-dusting plane. Simulated cases were then included into an observed data stream. Detection approaches included SaTScan trade mark and small area regression and testing (SMART) scores. An evaluation metric was developed for comparison of results. In addition, a simulation of a separate data stream was added; and then separate and combined surveillance data were compared.

Results: In the simulation in which a single data stream was used, the two statistical approaches were substantially similar in performance. The combined surveillance based on two data streams is superior to surveillance based on either stream separately.

Conclusion: The other potential uses of such a system are considered. These uses include the comparison of different data sources (e.g., outpatient versus emergency department and evaluating the impact of potential changes to the surveillance system, and increasing the population under surveillance). Simulation is a valuable technique for evaluating and planning for syndromic surveillance.