Space-time prospective surveillance based on Knox local statistics

Abstract

We studied a surveillance system to prospectively monitor the emergence of space-time clusters in point pattern of disease events. Its aim is to detect a cluster as soon as possible after its emergence, and it is also desired to keep the rate of false alarms at a controlled level. The method is a modification from a previous proposal based on a local version of the Knox statistic and which examined a retrospective surveillance scenario, looking for the earliest time in the past that change could have been deemed to occur. We modify this method to take into account the prospective case, being able then to fix the serious difficulties found by other authors. We evaluated the surveillance system in several scenarios, including without and with emerging clusters, checking distributional assumptions, and assessing performance impacts of different emergence times, shapes, extent, and intensity of the emerging clusters. Our conclusion is that the space-time surveillance system based on local Knox statistics is very efficient in its statistical properties, and it is appealing to epidemiologists and public health officials because it is simple to use and easily understandable. This makes it a promising candidate to practical use by public health official agencies.

Keywords: disease mapping; disease surveillance; prospective space-time surveillance; prospective surveillance; space-time clustering; spatial statistics.