Use of the scan statistic on disaggregated province-based data: Foot-and-mouth disease in Iran

The spatial scan statistic was applied to density-smoothed data that approximated the spatial distribution within the area and reduced the potential bias produced when location data have been aggregated for large areas. The method is illustrated, using data on the location of foot-and-mouth disease (FMD) outbreaks in Iran. Data examined were 4477 FMD outbreaks reported on a per province basis between June 1996 and September 2003. A kernel density of the outbreak locations was estimated, using a fixed radius and the centroid of each province as the designated location of all cases reported for the province. The radius that produced a density map with the highest correlation with expert opinion was 4°(latitude/longitude). Livestock density was used as a proxy for the underlying population at risk of acquiring FMD. Livestock and outbreak density maps were overlain to obtain the number of outbreaks and livestock in each of 15,599 cells covering the mapped surface of the country. A spatial scan statistic was applied to the density-smoothed data assuming that the outbreaks had a Poisson distribution. Results were compared with those obtained using a spatial scan statistic on provincially aggregated data. Application of the spatial scan statistic on the density-smoothed data allowed identification of clusters (P < 0.01) related more to the actual geographic distribution of cases (expert opinion) and of animals at risk, than to the distribution of the provinces. Significant clusters of FMD were identified that coincided with roads, neighboring countries, and high-density population areas, suggesting that the region may represent a route for cross-continent transmission of FMD.