Geographic and Network Surveillance via Scan Statistics for Critical Area Detection

Patil, G. P.; Taillie, C.

doi:10.1214/ss/1081443229

Cited by 65 publications

(52 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One alternative form of scanning is to allow an adaptive scanning where the shape of the clusters to scan depend on the data. In [37], it is suggested to scan a subset of all connected regions consisting of the ones most strongly indicating a cluster. This is motivated by the necessity to decrease the computational burden for large complex cases.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

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

Sonesson

2007

Statistics in Medicine

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

“…This is motivated by the necessity to decrease the computational burden for large complex cases. However in [37] this is only done for a fixed sample situation. It is not immediately clear how to apply it in the surveillance case, when we have data from several different time points.…”

Section: Discussionmentioning

confidence: 99%

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

Sonesson

2007

Statistics in Medicine

View full text Add to dashboard Cite

show abstract

“…A brief review of scan statistics and their applications to ecological studies and environmental sciences is available by Patil and Taillie. 18 The Poisson model is applicable in this study of colorectal cancer because the analysis involved small numbers of cases against larger population denominators, as is often the case with cancer. This is particularly true for the state of Texas, where in 2003 the ageadjusted mortality rate for colorectal cancer was estimated at 26.1 per 100,000 for males and 17.4 per 100,000 for females.…”

Section: Methodsmentioning

confidence: 99%

Surveillance of the Colorectal Cancer Disparities Among Demographic Subgroups: A Spatial Analysis

Hsu

Más²,

Hickey³

et al. 2006

Southern Medical Journal

View full text Add to dashboard Cite

Objective: The literature suggests that colorectal cancer mortality in Texas is distributed inhomogeneously among specific demographic subgroups and in certain geographic regions over an extended period. To understand the extent of the demographic and geographic disparities, the present study examined colorectal cancer mortality in 15 demographic groups in Texas counties between 1990 and 2001. Methods:The Spatial Scan Statistic was used to assess the standardized mortality ratio, duration and age-adjusted rates of excess mortality, and their respective p-values for testing the null hypothesis of homogeneity of geographic and temporal distribution. Results:The study confirmed the excess mortality in some Texas counties found in the literature, identified 13 additional excess mortality regions, and found 4 health regions with persistent excess mortality involving several population subgroups. Conclusion:Health disparities of colorectal cancer mortality continue to exist in Texas demographic subpopulations. Health education and intervention programs should be directed to the at-risk subpopulations in the identified regions.Key Words: colorectal cancer, health disparities, public health informatics, Geographic Information Systems, spatial analysis. I n 2005, an estimated 56,290 deaths from colorectal cancer were expected in the United States, sustaining colorectal cancer as the third leading cause of cancer-related deaths among Americans.1 Recent studies suggest that screening is effective in decreasing colorectal cancer in both incidence and mortality by early detection and removal of precancerous lesions or polyps, and enhancing survival rates among colorectal cancer patients.2 Colorectal cancer is one of the most preventable types of cancer when detected at an early stage. However, while the 5-year survival rate for colorectal cancer is around 90% for those cases detected at an early stage, only about 37% of colorectal cancers were diagnosed at an early stage in 2004. 4 At the state level, between 1989 and 1998, the age-adjusted mortality rate for colorectal cancer in Texas actually increased by more than 20%.3 To target prevention and intervention efforts, it is important to understand the contributing risk factors for colorectal cancer affecting demographic groups living in different geographic regions. Key Points• Colorectal cancer mortality in Texas was found to be distributed inhomogeneously among specific demographic subgroups and in certain geographic regions over an extended period.• The study confirmed the excess mortality in some Texas counties reported in the literature, identified 13 additional excess mortality regions, and found 4 health regions with persistent excess mortality involving several population subgroups.• Health disparities in colorectal cancer mortality continue to exist in Texas demographic subpopulations.Health education and intervention programs should be enhanced to address the at-risk subpopulations in the identified regions.

show abstract

“…Hence, while we will describe the subsequent theory in the framework of the space-time scan statistic, everything applies to the purely spatial and purely temporal scan statistics as well. Other shapes of the scanning window than circles and cylinders are also possible [2,23,24,25], but again, the principles for dealing with multiple data sets is the same.…”

Section: The Univariate Scan Statisticmentioning

confidence: 99%

Multivariate scan statistics for disease surveillance

Kulldorff

Mostashari

Duczmal

et al. 2007

Statistics in Medicine

191

138

View full text Add to dashboard Cite

In disease surveillance, there are often many different data sets or data groupings for which we wish to do surveillance. If each data set is analyzed separately rather than combined, the statistical power to detect an outbreak that is present in all data sets may suffer due to low numbers in each. On the other hand, if the data sets are added by taking the sum of the counts, then a signal that is primarily present in one data set may be hidden due to random noise in the other data sets.In this paper, we present an extention of the spatial and space-time scan statistic that simultaneously incorporates multiple data sets into a single likelihood function, so that a signal is generated whether it occurs in only one or in multiple data sets. This is done by defining the combined log likelihood as the sum of the individual log likelihoods for those data sets for which the observed case count is more than the expected.Using data from the National Bioterrorism Syndromic Surveillance Demonstration Project, we illustrate the new method using physician telephone calls, regular physician visits and urgent care visits by Harvard Pilgrim Health Care members cared for by Harvard Vanguard Medical Associates, a large multi-specialty group practice in Massachusetts. For upper and lower gastrointestinal illness, there were on

show abstract

Geographic and Network Surveillance via Scan Statistics for Critical Area Detection

Cited by 65 publications

References 32 publications

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

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

Surveillance of the Colorectal Cancer Disparities Among Demographic Subgroups: A Spatial Analysis

Multivariate scan statistics for disease surveillance

Contact Info

Product

Resources

About