Emerging disease clusters must be detected in a timely manner so that necessary remedial action can be taken to prevent the spread of an outbreak. The Exponentially Weighted Moving Average method (EWMA) is a particularly popular method, and has been utilized for disease surveillance in the United States.
A spatio-temporal EWMA statistic is proposed for on-line disease surveillance over multiple geographic regions. To capture spatial association, disease counts of neighboring regions are pooled together, similar to a method originally proposed by Raubertas for a different control chart. Also to increase statistical power in testing multiple EWMA statistics simultaneously, false discovery rate (FDR) is used instead of the traditional family-wise error rate (FWER).
Objective
To propose a computationally simple and a fast algorithm to detect disease outbreaks in multiple regions