A bird's eye view: using geographic analysis to evaluate the representativeness of corvid indicators for West Nile virus surveillance

Abstract

Background: The objective of this evaluation was to determine whether reports of dead corvid sightings and submissions of dead corvids for West Nile virus testing were representative of true corvid mortality in British Columbia in 2004, a year with no West Nile virus activity, in order to ensure the system was accurately describing corvid mortality rather than reflecting regional differences in surveillance methods.

Results: Local Health Areas reported 0-159 (median = 3) dead corvid sightings and 0-209 (median = 5) submissions for West Nile virus testing. The expected numbers of dead corvid sightings and submissions for testing from each Local Health Area were 0-232 (median = 3) and 0-258 (median = 4), respectively. Twelve Local Health Areas reported significantly fewer sightings than expected; 21 reported significantly more. Eleven Local Health Areas submitted significantly fewer corvids than expected; 26 submitted significantly more.

Conclusion: Some Local Health Areas were over-represented and others under-represented in terms of corvid West Nile virus surveillance indicators. Recommendations were made to improve the representativeness of corvid surveillance data. Geographic analysis can be used to evaluate the representativeness of surveillance systems and result in improvements to surveillance.

Figure 1

Dead corvid sightings and carcasses tested for West Nile virus versus expected, by Local Health Area.

Figure 2

Relative corvid abundance by species in British Columbia from the North American breeding bird survey.

Figure 3

Formulas used to calculate the expected values for corvid indicators in each Local Health Area. LHA = Local Health Area; A = Geographic area; CD = Relative corvid density; HD = Human population density; WNv = West Nile virus.