Spatiotemporal biosurveillance with spatial clusters: control limit approximation and impact of spatial correlation

Multivariate CUSUM charts formed over spatial clusters have been used over the last several years to detect emerging disease clusters in spatiotemporal biosurveillance. The control limits for the CUSUM charts are typically calibrated by trial-and-error simulation, but this task can be time-consuming and challenging when the monitoring area is large. This article introduces an analytical method that approximates the control limits and average run length when spatial correlation is not strong. In addition, the practical range of the scan radius in which the approximation method works well is investigated. Also studied is how the outbreak radius and spatial correlation impact the scheme’s outbreak detection performance with respect to two metrics: detection delay and identification accuracy. Experimental results show that the approximation method performs well, making the design of the multivariate CUSUM chart convenient; and higher spatial correlation does not always yield faster detection but often facilitates accurate identification of outbreak clusters.

[1]  L C Hutwagner,et al.  A simulation model for assessing aberration detection methods used in public health surveillance for systems with limited baselines , 2005, Statistics in medicine.

[2]  William H. Woodall,et al.  The Use of Control Charts in Health-Care and Public-Health Surveillance , 2006 .

[3]  George C. Runger,et al.  Comparison of multivariate CUSUM charts , 1990 .

[4]  E. S. Page.  Cumulative Sum Charts , 1961 .

[5]  Seoung Bum Kim,et al.  A comparison of CUSUM, EWMA, and temporal scan statistics for detection of increases in poisson rates , 2010, Qual. Reliab. Eng. Int..

[6]  Christian Sonesson,et al.  A CUSUM framework for detection of space–time disease clusters using scan statistics , 2007, Statistics in medicine.

[7]  David Bock,et al.  A review and discussion of prospective statistical surveillance in public health , 2003 .

[8]  Andrew B. Lawson,et al.  Statistical Methods in Spatial Epidemiology , 2001 .

[9]  ClusteringRonald E. GangnonDepartment.  Bayesian Dete tion and Modeling of Spatial Disease , 2007 .

[10]  Fred Spiring,et al.  Introduction to Statistical Quality Control , 2007, Technometrics.

[11]  T Tango,et al.  A class of tests for detecting 'general' and 'focused' clustering of rare diseases. , 1995, Statistics in medicine.

[12]  J. Healy.  A note on multivariate CUSUM procedures , 1987 .

[13]  W. Woodall,et al.  Multivariate CUSUM Quality- Control Procedures , 1985 .

[14]  Yiliang Zhu,et al.  Initial evaluation of the early aberration reporting system--Florida. , 2005, MMWR supplements.

[15]  P A Rogerson,et al.  Surveillance systems for monitoring the development of spatial patterns. , 1997, Statistics in medicine.

[16]  Kwok-Leung Tsui,et al.  A review and comparison of likelihood-based charting methods , 2012 .

[17]  R. Crosier.  Multivariate generalizations of cumulative sum quality-control schemes , 1988 .

[18]  Peter A. Rogerson,et al.  Formulas for the Design of CUSUM Quality Control Charts , 2006 .

[19]  K. Stout.  Cumulative Sum Charts , 1985 .

[20]  H. A. David.  ON THE APPLICATION TO STATISTICS OF AN ELEMENTARY THEOREM IN PROBABILITY , 1956 .

[21]  E. S. Page.  CONTINUOUS INSPECTION SCHEMES , 1954 .

[22]  M. Clayton,et al.  A weighted average likelihood ratio test for spatial clustering of disease , 2001, Statistics in medicine.

[23]  Peter A Rogerson,et al.  Approaches to syndromic surveillance when data consist of small regional counts. , 2004, MMWR supplements.

[24]  Kwok-Leung Tsui,et al.  A Review of Healthcare, Public Health, and Syndromic Surveillance , 2008 .

[25]  James M. Lucas,et al.  Exponentially weighted moving average control schemes: Properties and enhancements , 1990 .

[26]  Wei Jiang,et al.  Spatiotemporal surveillance methods in the presence of spatial correlation , 2011, Statistics in medicine.

[27]  James R. Wilson,et al.  A distribution-free tabular CUSUM chart for autocorrelated data , 2007 .

[28]  Peter A Rogerson,et al.  Monitoring change in spatial patterns of disease: comparing univariate and multivariate cumulative sum approaches , 2004, Statistics in medicine.

[29]  Ronald D Fricker,et al.  Comparing syndromic surveillance detection methods: EARS' versus a CUSUM‐based methodology , 2008, Statistics in medicine.

[30]  Douglas C. Montgomery,et al.  Using Control Charts to Monitor Process and Product Quality Profiles , 2004 .

[31]  M K Clayton,et al.  Bayesian Detection and Modeling of Spatial Disease Clustering , 2000, Biometrics.