The EpiAnalyst extension for ArcView® GIS is a productivity tool and resource kit for spatial-epidemiologic research. The extension contains spatial cluster analysis software from the National Cancer Institute (NCI), has a link to the CrimeStat spatial analysis software, and includes the Spatial Data Modeller extension. The EpiAnalyst also includes software from The University of Iowa that allows you to perform the computations that are required to make smoothed maps of disease rates and  tests of statistical significance. The extension interfaces with the latest version of Epi Info 2002 from the Centers of Disease Control and Prevention (CDC) and other software from PHRL.  The EpiAnalyst is a bridge between epidemiology and GIS. The EpiAnalyst extension for ArcView GIS is an ongoing project that will have future versions. Functionality will be added over time in order to create a more seamless health-GIS; an interface between epidemiology, spatial analysis, and biostatistics.

• The EpiAnalyst has a link to SaTScan. The National Cancer Institute (NCI) developed SaTScan to analyze spatial, temporal and space-time point data using the spatial, temporal, or space-time scan statistic.  It was designed for any of the following interrelated purposes:

1. To evaluate reported spatial or space-time disease clusters, to see if they are statistically significant.
2. To test whether a disease is randomly distributed over space or over time or over space and time.
3. To perform geographical surveillance of disease, to detect areas of significantly high or low rates. 

SaTScan uses either a Poisson based model, where the number of events in an area is Poisson distributed under the null hypothesis, or a Bernoulli model, with 0/1 event data such as cases and controls.  The program adjusts for the underlying inhomogeneity of a background population.  With the Poisson model it can also adjust for any number of categorical covariates provided by the user.  

• The EpiAnalyst has a link to CrimeStat, developed under a grant from the National Institute of Justice (NIJ). The spatial statistics in CrimeStat are subdivided into four categories. First, there are statistics for describing the spatial distribution of incidents, such as the mean center, center of minimum distance, standard deviational ellipse, Moran's I spatial autocorrelation index, or angular mean. Second, there are statistics for describing properties of distances between incidents including nearest neighbor analysis, linear nearest neighbor analysis, and Ripley's K statistic. Third, there are three routines for conducting 'hot spot' analysis - hierarchical nearest neighbor clustering, K-means clustering, and local Moran statistics. Fourth, and finally, there is a single-variable kernel density estimation routine for producing a surface or contour estimate of the density of incidents and a dual-variable kernel density estimation routine for comparing the density of incidents to the density of an underlying baseline.

• DMAP (Disease Mapping and Analysis Program) is incorporated into the EpiAnalyst. The University of Iowa, Geography Department, developed DMAP. DMAP project was to provide users with a fast, easy, and simple means of creating maps of disease rates and statistical significance. The ArcView Spatial Analyst* provides the routines for interpolating grid point values (disease rates and significance rates) and creating continuous surface (contour) maps. A more seamless interface  for DMAP is due for release later this year.

• Arc-SDM (Spatial Data Modeller)  provides the ability to conduct weights of evidence modelling, tools for logistic regression, fuzzy logic and neural network analysis. The ultimate aim of all these methods is to combine two or more evidential themes to generate a response theme. In the situation of disease investigation the response theme is a map that predicts favorable locations for disease occurrences, defined by a set of historical and or current disease cases.

Weights of evidence modelling is a quantitative method for combining evidence in support of a hypothesis. Weights are estimated from the measured association between known occurrences and the values on the maps to be used as predictors. Arc-SDM uses the ArcView Spatial Analyst* extension in the calculations required for the Weights of Evidence model.

• The EpiAnalyst extension for ArcView GIS has a customized Graphical User Interface (GUI) that allows greater ease of use and simplified file sharing for Epi Info 2002.

• The EpiAnalyst also has productivity tools that help increase the efficiency of the health-GIS worker such as a utility to find duplicate records.

• The EpiAnalyst also has spatial analysis functions such as:

  • Spatial Join 

  • Areal Interpolation 

  • Thiessen Polygons

*Available separately (not included in the EpiAnalyst)