An evaluation model for syndromic surveillance: assessing the performance of a temporal algorithm

Abstract

Introduction: Syndromic surveillance offers the potential to rapidly detect outbreaks resulting from terrorism. Despite considerable experience with implementing syndromic surveillance, limited evidence exists to describe the performance of syndromic surveillance systems in detecting outbreaks.

Objectives: To describe a model for simulating cases that might result from exposure to inhalational anthrax and then use the model to evaluate the ability of syndromic surveillance to detect an outbreak of inhalational anthrax after an aerosol release.

Methods: Disease progression and health-care use were simulated for persons infected with anthrax. Simulated cases were then superimposed on authentic surveillance data to create test data sets. A temporal outbreak detection algorithm was applied to each test data set, and sensitivity and timeliness of outbreak detection were calculated by using syndromic surveillance.

Results: The earliest detection using a temporal algorithm was 2 days after a release. Earlier detection tended to occur when more persons were infected, and performance worsened as the proportion of persons seeking care in the prodromal disease state declined. A shorter median incubation state led to earlier detection, as soon as 1 day after release when the incubation state was < or =5 days.

Conclusion: Syndromic surveillance of a respiratory syndrome using a temporal detection algorithm tended to detect an anthrax attack within 3-4 days after exposure if >10,000 persons were infected. The performance of surveillance (i.e., timeliness and sensitivity) worsened as the number of persons infected decreased.