Detection of spatial disease clusters with LISA functions

Abstract

Detection of disease clusters is an important tool in epidemiology that can help to identify risk factors associated with the disease and in understanding its etiology. In this article we propose a method for the detection of spatial clusters where the locations of a set of cases and a set of controls are available. The method is based on local indicators of spatial association functions (LISA functions), particularly on the development of a local version of the product density, which is a second-order characteristic of spatial point processes. The behavior of the method is evaluated and compared with Kulldorff's spatial scan statistic by means of a simulation study. It is shown that the LISA method yields high sensitivity and specificity when it is used to detect simulated clusters of different sizes and shapes. It also performs better than the spatial scan statistic when they are used to detect clusters of irregular shape; however, it presents relatively high type I error in situations where the number of cases is high. Both methods are applied for detecting spatial clusters of kidney disease in the city of Valencia, Spain, in the year 2008.

Notifiable Sexually Transmitted Infections in China: Epidemiologic Trends and Spatial Changing Patterns

“…In like vein, the value of local Moran's I is also a number from −1 to 1 and the value can be explained exactly in the same way as that of the global Moran's I. The function of local Moran's I lies in the detection of spatial clusters, which helps to reveal the spatial-temporal changing patterns of STIs across the past 10 years [25].…”

Evaluation of diagnostics for hierarchical spatial statistical models

“…However, in most cases the diagnostic will misclassify some locations. There is potentially a strong parallel here between spatial-model diagnostics and medical diagnostics (e.g., Moraga and Montes 2011;van Smeden et al 2014), where a diagnostic test is used to identify unusual values (e.g., Pepe and Thompson 2000;Sackett and Haynes 2002). Two summary statistics that are routinely used to assess the performance of medical diagnostics are Sensitivity and Specificity (e.g., Akobeng 2007;Enøe et al 2000;Hui and Zhou 1998).…”

“…Here, local statistics can be powerful diagnostics (see Fotheringham 2009;Fotheringham and Brunsdon 1999, for a review of local analysis), although they can be computationally expensive. Examples include the local indicators of spatial association (LISA) (Anselin 1995;Getis and Ord 1992;Moraga and Montes 2011;Ord and Getis 1995), LICD, a LISA equivalent for categorical data (Boots 2003), the structural similarity index (SSM) (Robertson et al 2014;Wang et al 2004), the Sstatistic (Karlström and Ceccato 2002), the local spatial heteroskedasticity statistic (LOSH) (Ord and Getis 2012;Xu et al 2014) and local diagnostics based on the spatial scan statistic for identifying clusters (Kulldorff et al 2006;Read et al 2013). …”

SpatialEpiApp : A Shiny web application for the analysis of spatial and spatio-temporal disease data

“…This information is crucial to prevent and control a variety of health conditions such as chronic and infectious diseases, injuries, or health-related behaviors (Thacker and A C C E P T E D M A N U S C R I P T Berkelman, 1988;Lawson and Kleinman, 2005). There is a wide range of spatial and spatio-temporal methods and software that can be applied as a surveillance tool, and these are useful for highlighting areas at high risk (Moraga et al, 2015), detecting disease clusters (Moraga and Montes, 2011), assessing spatial variations in temporal trends (Moraga and Kulldorff, 2016), early detection of epidemics (Stelling et al, 2010), assessing disease risk in relation to a putative source (Wakefield and Morris, 2001), and identifying disease risk factors (Hagan et al, 2016).…”