作者: Christian Sonesson
DOI: 10.1002/SIM.2898
关键词: Disease surveillance 、 Data mining 、 Statistics 、 Computer science 、 Public health surveillance 、 Focus (optics) 、 Space time 、 Cluster (physics) 、 CUSUM 、 Scan statistic 、 Process (computing)
摘要: Several methods for timely detection of emerging clusters diseases have recently been proposed. We focus our attention on one the most popular types method; a scan statistic. Different ways constructing space-time statistics based surveillance theory are presented. bridge ideas from disease surveillance, public health and industrial quality control show that previously suggested can be fitted into general CUSUM framework. Crucial differences between studied due to different assumptions about spatial process. An example is specification regions interest possible cluster, another increased rate detected within cluster. evaluate ability considering possibility cluster at any time during period. The applied an incidence Tularemia in Sweden.