A flexible spatial scan statistic with a restricted likelihood ratio for detecting disease clusters

Abstract

Spatial scan statistics are widely used tools for detection of disease clusters. Especially, the circular spatial scan statistic proposed by Kulldorff (1997) has been utilized in a wide variety of epidemiological studies and disease surveillance. However, as it cannot detect noncircular, irregularly shaped clusters, many authors have proposed different spatial scan statistics, including the elliptic version of Kulldorff's scan statistic. The flexible spatial scan statistic proposed by Tango and Takahashi (2005) has also been used for detecting irregularly shaped clusters. However, this method sets a feasible limitation of a maximum of 30 nearest neighbors for searching candidate clusters because of heavy computational load. In this paper, we show a flexible spatial scan statistic implemented with a restricted likelihood ratio proposed by Tango (2008) to (1) eliminate the limitation of 30 nearest neighbors and (2) to have surprisingly much less computational time than the original flexible spatial scan statistic. As a side effect, it is shown to be able to detect clusters with any shape reasonably well as the relative risk of the cluster becomes large via Monte Carlo simulation. We illustrate the proposed spatial scan statistic with data on mortality from cerebrovascular disease in the Tokyo Metropolitan area, Japan.

The daily incidence of out-of-hospital cardiac arrest unexpectedly increases around New Year's Day in Japan

“…To detect a time period within which the incidence of OHCA became higher than expected, we adopted a cluster detection test widely used in spatial epidemiology contexts that To examine whether the incidence of OHCA cases showed any particular temporal clustering, we calculated flexible scan statistics implemented with the restricted likelihood ratio 28 . This was an improved version of Kulldorff's analysis.…”

Breast Cancer Clustering in Kanagawa, Japan: A Geographic Analysis

“…To identify the disease clusters and their statistic with are restricted likelihood ratio (Tango and Takahashi, 2005Takahashi, , 2012Tango, 2008). We assumed the number of deaths or incidence to be Poisson distributed in each municipality.…”

A Spatial Study of the Location of Superfund Sites and Associated Cancer Risk

“…The software FlexScan uses a flexible spatial scan statistic developed by Kunihiko Takahashi and Toshiro Tango, which finds smoothly shaped clusters, rather than only circular or elliptical clusters, by examining geographical areas adjacent to each other (Tango and Takahaski 2012). Unlike SaTScan TM , FlexScan is limited to spatial analysis only (i.e., not temporal) and it does not allow for a cluster analysis when the response variable is continuous (Takahashi, Yokoyama, and Tango 2015).…”