Cluster Detection

Methods for locating spatial clusters of diseases are typically variations of the circular scan statistic method. They restrict the number of potential clusters by considering all circular, rectangular, or elliptical regions, and then apply a likelihood ratio test to evaluate the statistical significance of each potential cluster. Because disease outbreaks may have variable shapes, there has been recent interest in developing methods to detect irregularly-shaped clusters. Starting with a neighborhood graph of the administrative regions in the study area, certain sub-graphs are evaluated. These include all connected subgraphs within a circular window and sub-graphs of the minimum spanning tree of a weighted neighborhood graph formed by deleting one edge. These methods restrict the maximum cluster size or identify large clusters having greater likelihood ratios than true clusters in the data, suggesting a limitation of using the likelihood ratio to detect arbitrarily-shaped clusters.

Objective

A method for detecting spatial clusters of diseases of any shape based on the Euclidean minimum spanning tree is described and compared to the circular scan statistic.

To propose a new spatial scan statistic that has higher ability of pinpointing the true cluster.

This paper describes a methodology for detecting irregular space-time cluster using the space time permutation scan statistic. The methodology includes sequential Monte Carlo simulation and distribution approximation to estimate the error type I.

This paper proposes a new scan statistic which detects disease clusters more accurately than that based on the likelihood ratio.

The use of spatially-based methods and algorithms in epidemiology and surveillance presents privacy challenges for researchers and public health agencies. We describe a novel method for anonymizing individuals in public health datasets, by transposing their spatial locations through a process informed by the underlying population density. Further, we measure the impact of blurring patient locations on detection of spatial clustering as measured by the SaTScan purely-spatial Bernoulli scanning statistic.

We present a new method for multivariate outbreak detection, the ìnonparametric scan statisticî (NPSS). NPSS enables fast and accurate detection of emerging space-time clusters using multiple disparate data streams, including nontraditional data sources where standard parametric model assumptions are incorrect.

This paper describes a comparison between two statistics ñ SaTScan and FleXScan, applying to a data of absentees in primary school in Japan.

We sought to compare ambulatory care (AC) and emergency department (ED) data for the detection of clusters of lower gastrointestinal illness, using AC and ED data and AC+ED data combined, from two geographically separate health plans participating in the National Bioterrorism Syndromic Surveillance Demonstration Program [1].

This paper develops a new Bayesian method for cluster detection, the ìBayesian spatial scan statistic,î and compares this method to the standard (frequen-tist) scan statistic approach on the task of prospective disease surveillance.

There is a great deal of interest in spatial patterns of infant mortality. However, small numbers can make spatial patterns difficult to discern and may mask areas of persistently high risk. This study investigates the spatial pattern of birthweight and gestation, two primary risk factors for infant mortality, using normal-distribution methods available in SaTScan and for which data is available in much greater quantity.