The role of pre-emptive culling in the control of foot-and-mouth disease

Abstract

The 2001 foot-and-mouth disease epidemic was controlled by culling of infectious premises and pre-emptive culling intended to limit the spread of disease. Of the control strategies adopted, routine culling of farms that were contiguous to infected premises caused the most controversy. Here we perform a retrospective analysis of the culling of contiguous premises as performed in 2001 and a simulation study of the effects of this policy on reducing the number of farms affected by disease. Our simulation results support previous studies and show that a national policy of contiguous premises (CPs) culling leads to fewer farms losing livestock. The optimal national policy for controlling the 2001 epidemic is found to be the targeting of all contiguous premises, whereas for localized outbreaks in high animal density regions, more extensive fixed radius ring culling is optimal. Analysis of the 2001 data suggests that the lowest-risk CPs were generally prioritized for culling, however, even in this case, the policy is predicted to be effective. A sensitivity analysis and the development of a spatially heterogeneous policy show that the optimal culling level depends upon the basic reproductive ratio of the infection and the width of the dispersal kernel. These analyses highlight an important and probably quite general result: optimal control is highly dependent upon the distance over which the pathogen can be transmitted, the transmission rate of infection and local demography where the disease is introduced.

Figure 1.

(a) Temporal pattern of IPs in the five DCCs with the greatest number of IPs (and in the rest of the UK), (b) non-IP to IP ratio and (c) pre-emptive cull to IP ratio, for these DCCs during the three phases of the epidemic. (b,c) The dashed lines show the non-IP to IP ratio and the pre-emptive cull to IP ratio respectively for the whole country, averaged over the entire epidemic. Blue bar, phase 1; green bar, phase 2; brown bar, phase 3.

Figure 2.

(a) Number of farms losing livestock, (b) number of cattle culled and (c) number of sheep culled for the various cull categories used during the 2001 FMD epidemic. ‘At-risk’ culls include all farms culled in the DCS categories: traditional dangerous contacts (DCs), CPs and others. The right-hand axis in each figure shows the percentage of the total population in the UK of farms, cattle and sheep respectively culled in each category. (d) Cattle-to-sheep ratio on IPs, ‘at-risk’ culls and 3 km/local culls for individual DCCs. The cattle : sheep ratio for all farms within the 10 km surveillance zone (SZ) of all IPs in each DCC is also shown (navy blue bar, IPs; sky blue bar, ‘at-risk’; yellow bar, 3 km + local; brown bar, census 10 km SZ). (e) The number of cattle and the number of sheep in each DCC on IPs, ‘at-risk’ culls, 3 km/local culls and in the 10 km SZ of all IPs (brown bar, cattle IPs; red bar, sheep IPs; green bar, cattle ‘at-risk’; light green bar, sheep ‘at-risk’; indigo bar, cattle 3 km + local; navy blue bar, sheep 3 km + local; dark green bar, cattle census 10 km SZ; sky blue bar, sheep census 10 km SZ).

Figure 3.

Graph showing the difference in epidemic impact between a strategy of IP and DC culling alone and a strategy of culling all CPs. The colour scale shows the number of farms ‘saved’ when all CPs are culled. The white line indicates where the two strategies result in the same overall average epidemic impact. The white box shows the point at which K_h and K_w take the values used for the 2001 epidemic.

Figure 4.

(a) Graph showing the effect of CP culling for epidemics seeded in each county of the UK. The colour scale shows the optimal CP : IP ratio that must be achieved to minimize the epidemic impact. (b) Mean optimal CP : IP ratio (black line) for epidemics seeded in each county against the mean R₀ values averaged across farms in each county. The black dots show the raw data for each county. (c) Optimal CP : IP ratio in Cumbria as the DC : IP ratio varies (blue line). Ninety five per cent confidence intervals on the mean are also shown (black lines).