The Activity Monitoring Operating Characteristic (AMOC) curve is a useful and popular method for assessing the performance of algorithms that detect outbreaks of disease [1]. As it is typically applied in biosurveillance, the AMOC curve plots the expected time to detection (since the outbreak began) as a function of the false alert rate. An ideal algorithm has zero false alerts and a detection time of zero. An al-ternative, conceptually equivalent version of the AMOC curve plots (T – detection_time) as a function of the false alert rate, where T is a maximum mean-ingful detection time. We focus on this version.
Objective
We introduce a new measure for evaluating alerting algorithms, which is a generalization of the AMOC curve [1]. For a given rate of false positives alerts, the new measure estimates the time between when an alert is raised and when clinicians are expected to detect the outbreak on their own. We call this measure the Expected Warning Time (EWT).