A CUSUM framework for detection of space–time disease clusters using scan statistics

Abstract

Several methods for timely detection of emerging clusters of diseases have recently been proposed. We focus our attention on one of the most popular types of method; a scan statistic. Different ways of constructing space-time scan statistics based on surveillance theory are presented. We bridge the ideas from space-time disease surveillance, public health surveillance and industrial quality control and show that previously suggested space-time scan statistics methods can be fitted into a general CUSUM framework. Crucial differences between the methods studied are due to different assumptions about the spatial process. An example is the specification of the spatial regions of interest for a possible cluster, another is the increased rate to be detected within a cluster. We evaluate the detection ability of the methods considering the possibility of a cluster emerging at any time during the surveillance period. The methods are applied to the detection of an increased incidence of Tularemia in Sweden.

A comparison of CUSUM, EWMA, and temporal scan statistics for detection of increases in poisson rates

“…The rate 0 = 1.4 is the same baseline rate used for the spatiotemporal application in Sonesson 44 . Next, we decided to target shift sizes * 1 = 1.75, 2.1, 2.45, and 2.8, respectively, 25, 50, 75, and 100% larger than 0 .…”

“…Hence, the CUSUM chart can also be thought of as the scan statistic method with a variable window size for online monitoring 44 .…”

Multivariate outbreak detection

“…Spatial clustering of adverse health events is discussed for example by Kulldorff (2001), Rogerson (2001), Lawson and Rodeiro (2004), Marshall et al (2007) and Sonesson (2007). However, in some situations, such as in the case of influenza in Sweden, the outbreak pattern is not characterized by clustering.…”

A Spatio-Temporal Methodology for Real-Time Biosurveillance

“…Other spatio-temporal approaches include Sonesson (2007) who applies a CUSUM methodology to scan statistics and Rogerson and Yamada (2004) who apply CUSUM methods to the spatial distribution of cases. Diggle et al (2004) use a spatio-temporal Cox point process methodology based on the counts in subregions.…”