Early event detection (EED) is one of the two main functions of a biosurveillance system. Per Homeland Security Presidential Directive 21 (HSPD-21), biosurveillance is “the process of active data-gathering with appropriate analysis and interpretation of biosphere data that might relate to disease activity and threats to human or animal health… in order to achieve early warning of health threats, early detection of health events, and overall situational awareness of disease activity” [emphasis added] (US Government, 2007).

This chapter opens by describing the mathematical notation and the assumptions that are used followed by a discussion of some important principles for good EED methods design. It then compares and contrasts EED to statistical methods commonly used in public health and epidemiological practice: binary classification and hypothesis testing. The chapter concludes with a discussion of EED performance metrics with a focus on a set of useful metrics and procedures for appropriately evaluating EED performance, either as part of a fielded biosurveillance system or as part of a research effort.