Enhanced West Nile Virus Circulation in the Emilia-Romagna and Lombardy Regions (Northern Italy) in 2018 Detected by Entomological Surveillance

Abstract

With several human cases reported annually since 2008 and the unapparent risk of infection of blood donors, the West Nile virus (WNV) is emerging as an important health issue in Europe. Italy, as well as other European countries, experienced a recrudescence of the virus circulation in 2018, which led to an increased number of human cases. An integrated surveillance plan was activated in the Emilia-Romagna and Lombardy regions (Northern Italy) since 2008 in order to monitor the intensity and timing of WNV circulation. A fundamental part of this plan consists in entomological surveillance. In 2018, the surveillance plan made it possible to collect 385,293 mosquitoes in 163 stations in the two Regions. In total 269,147 Culex mosquitoes were grouped into 2,337 pools and tested for WNV, which was detected in 232 pools. Circulation started in the central part of the Emilia-Romagna region in the middle of June, about one month before the previous seasons. Circulation suddenly expanded to the rest of the region and reached the Lombardy region in the middle of July. WNV circulated more intensively in the eastern part of the surveyed area, as confirmed by the highest number of human cases. A relationship between the number of mosquitoes collected and the virus incidence emerged, but the data obtained highlighted that the probability of detecting the virus in a given site was less than expected with a higher number of collected mosquitoes. A significant relationship was observed between the temperature recorded one week before the sampling and the number of collected mosquitoes, as well as between the estimated number of WNV-positive mosquitoes and the temperature recorded two weeks before the sampling. The two weeks delay in the influence of temperature on the positive mosquitoes is in line with the time of the virus extrinsic incubation in the mosquito. This finding confirms that temperature is one of the principal drivers in WNV mosquito infection. The surveillance system demonstrated the ability to detect the virus circulation early, particularly in areas where circulation was more intense. This allowed evaluating the effect of mosquito abundance and weather factors on virus circulation.

Keywords: Culex pipiens; West Nile virus; infection rate; one-health; surveillance; temperature.

Figure 1

Map showing the location of traps working throughout the season (circles) and for part of the season (squares), with reference to WNV detections (red), and the reference of the surveyed area on a map of Italy in which the Pianura Padano-Veneta is depicted in gray.

Figure 2

Average of sampled Cx. pipiens mosquitoes (black line) with CI (dashed lines), positive estimated mosquitoes (white, number above the bar) and number of WNND cases (gray, number above the bar) for Emilia-Romagna (A) and Lombardy (B), during the surveillance.

Figure 3

Evaluation of WNV circulation intensity according to number of estimated positive mosquitoes on 1,000 sampled mosquitoes at provincial level (A) and the same on a map (B).

Figure 4

Linear model showing the relationship between the fraction of infected mosquitoes at provincial level, and the incidence of WNND cases in the same province.

Figure 5

Probability of observing a WNV-positive trap as a function of the number of mosquitoes per trap in Lombardy (A) and Emilia-Romagna (C) estimated through observed data (black solid lines: best fit, dashed lines: 95% confidence interval) compared with the null model (white lines: median, gray areas: 95% interval). (B) distribution of the marginal increase in the probability to observe a WNV-positive trap due to an additionally caught mosquito obtained with the null model (M_NULL, gray bars) compared to M_OBS (black line).

Figure 6

Map of the surveyed area with the IDW interpolation of Cx. pipiens females collected between June and August (expressed as natural logarithm) and the hot-spot of WNV circulation (represented by 50% of the KDE of sites with at least one positive pool).

Figure 7

Beta coefficients (black dots) and 95% Confidence intervals (bars) with respect to a 1°C increase in weekly average maximum temperatures in the previous 4 weeks (lag 1–4). Linear regression estimates for the logarithm of the number of sampled Culex pipiens (A); Poisson regression estimates for Infection Rate (B).