Abstract
<p><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Calibri","sans-serif""><span style="color:black">Modern </span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Trebuchet MS","sans-serif""><span style="color:black">biosurveillance</span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Calibri","sans-serif""><span style="color:black"> relies on multiple sources of both pre-diagnostic and diagnostic </span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Trebuchet MS","sans-serif""><span style="color:black">data</span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Calibri","sans-serif""><span style="color:black">, up-dated daily, to discover disease outbreaks. Intrinsic to this effort are two assumptions: (1) the </span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Trebuchet MS","sans-serif""><span style="color:black">data </span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Calibri","sans-serif""><span style="color:black">being analyzed contain early indicators of a disease outbreak and (2) the outbreaks to be detected are not known a priori. However, in addition to outbreak indicators, syndromic </span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Trebuchet MS","sans-serif""><span style="color:black">data </span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Calibri","sans-serif""><span style="color:black">streams include such factors as day-of-week effects, seasonal effects, autocorrelation, and global trends. These explainable factors obscure unexplained outbreak events and their presence in the </span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Trebuchet MS","sans-serif""><span style="color:black">data</span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Calibri","sans-serif""><span style="color:black"> violates standard control chart assumptions. </span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Trebuchet MS","sans-serif""><span style="color:black">Monitoring </span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Calibri","sans-serif""><span style="color:black">tools such as Shewhart, CuSum, and EWMA control charts will alert largely based on these explainable factors instead of on outbreaks. The goal of this paper is twofold: First, to describe a set of tools </span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Trebuchet MS","sans-serif""><span style="color:black">for</span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Calibri","sans-serif""><span style="color:black"> identifying explainable patterns such as temporal dependence, and second, to survey and examine several </span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Trebuchet MS","sans-serif""><span style="color:black">data</span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Calibri","sans-serif""><span style="color:black"> preconditioning methods that significantly reduce these explainable factors, yielding </span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Trebuchet MS","sans-serif""><span style="color:black">data</span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Calibri","sans-serif""><span style="color:black"> better suited </span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Trebuchet MS","sans-serif""><span style="color:black">for</span></span></span></span> <span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Trebuchet MS","sans-serif""><span style="color:black">monitoring</span></span></span></span><span lang="EN-US" style="font-size:12.0pt"><span style="background:white"><span style="font-family:"Calibri","sans-serif""><span style="color:black"> using the popular control charts.</span></span></span></span></p>