Spatial Variation in Risk for Highly Pathogenic Avian Influenza Subtype H5N6 Viral Infections in South Korea: Poultry Population-Based Case-Control Study

Abstract

Given the substantial economic damage caused by the continual circulation of highly pathogenic avian influenza (HPAI) outbreaks since 2003, identifying high-risk locations associated with HPAI infections is essential. In this study, using affected and unaffected poultry farms' locations during an HPAI H5N6 epidemic in South Korea, we identified places where clusters of HPAI cases were found. Hotspots were defined as regions having clusters of HPAI cases. With the help of the statistical computer program R, a kernel density estimate and a spatial scan statistic were employed for this purpose. A kernel density estimate and detection of significant clusters through a spatial scan statistic both showed that districts in the Chungcheongbuk-do, Jeollabuk-do, and Jeollanam-do provinces are more vulnerable to HPAI outbreaks. Prior to the migration season, high-risk districts should implement particular biosecurity measures. High biosecurity measures, as well as improving the cleanliness of the poultry environment, would undoubtedly aid in the prevention of HPAIV transmission to poultry farms in these high-risk regions of South Korea.

Keywords: clusters; highly pathogenic avian influenza; hotspots; kernel density estimate; spatial scan statistic.

Figure 1

Distribution of highly pathogenic avian influenza cases (denoted by blue dots) and controls (denoted by red dots) across the country (South Korea).

Figure 2

Kernel density plots displaying the density of case farms (top left) by kernel density estimation based on multiple bandwidths of 0.02 (top right), 0.1 (middle left), and automated bandwidth selection by cross validation (middle right). Risk estimate (bottom left) and relative risk estimate (bottom right) with colored scale bar on the right denoting intensity of risk from blue to yellow, with a relative unit of measurement used to represent the proportion of risk value.

Figure 3

Depicts high risk locations on the map of South Korea (Ballatore, Bertolotto & Wilson, 2013). Kernel density risk estimate (A) and relative risk estimate (B) of being a case relative to being a control. Note: Chungcheongbuk-do, Chungcheongnam-do, Gyeonggi-do, and Jeollabuk-do provinces showed high risk of HPAI H5N6 epidemic.

Figure 4

Ripley’s K function for point process pattern and deviation from complete spatial randomness. Panel (A) shows that the actual measured value of K is higher than the theoretically determined anticipated value at all ranges tested, demonstrating significant clustering. Panel (B) shows the grey zone as a randomization envelope. Across all distances, actual observed values (K) are much higher than the envelope of predicted K values, indicating significant clustering and divergence from complete spatial randomness. Panel (C) shows the actual observed values for cases. Panel (D) shows the actual observed values for controls. Panel (E) shows differences in actual observed values for cases and actual observed values for controls. Panel (F) shows “difference in K function”, denoting that actual observed value of K function is, again, above the grey zone of randomization. Dark grey is minimum/maximum while light grey is the confidence envelope indicating deviation from complete spatial randomness.

Figure 5

Spatial clusters for the highly pathogenic avian influenza H5N6 epidemic (represented by different colors) detected in the provinces of Chungcheongbuk-do, Chungcheongnam-do, Jeollabuk-do and Gyeonggi-do: (A) radius of cluster window showing that clusters 1, 2, and 3 were, respectively, higher than cluster 4 and 5; (B) total population (number of poultry farms) was higher in cluster 1 followed by clusters 2, 3, 4, and 5; (C) showing that the observed number of cases was highest in cluster 1, followed by clusters 2, 3, 4, and 5, respectively; (D) showing the expected number of cases in all clusters; (E) showing that the standardized mortality ratio was highest in cluster 4, followed by clusters 5, 2, 3, and 1; (F) showing relative risk in all significant clusters. Relative risk of cases was higher in cluster 4, followed by clusters 5, 2, 1, and 3; (G) showing the highest proportion of cases in cluster 4, followed by clusters 5, 2, 3 and 1; (H) showing that the likelihood ratio was highest in cluster 1, followed by cluster 2, and clusters 3, 4 and 5. See Table 1.