Epidemiological analysis of spatially misaligned data: a case of highly pathogenic avian influenza virus outbreak in Nigeria

Abstract

This research is focused on the epidemiological analysis of the transmission of the highly pathogenic avian influenza (HPAI) H5N1 virus outbreak in Nigeria. The data included 145 outbreaks together with the locations of the infected farms and the date of confirmation of infection. In order to investigate the environmental conditions that favoured the transmission and spread of the virus, weather stations were realigned with the locations of the infected farms. The spatial Kolmogorov-Smirnov test for complete spatial randomness rejects the null hypothesis of constant intensity (P < 0·0001). Preliminary exploratory analysis showed an increase in the incidence of H5N1 virus at farms located at high altitude. Results from the Poisson log-linear conditional intensity function identified temperature (-0·9601) and wind speed (0·6239) as the ecological factors that influence the intensity of transmission of the H5N1 virus. The model also includes distance from the first outbreak (-0·9175) with an Akaike's Information Criterion of -103·87. Our analysis using a point process model showed that geographical heterogeneity, seasonal effects, temperature, wind as well as proximity to the first outbreak are very important components of spread and transmission of HPAI H5N1.

Fig. 1

[colour online]. The locations of HPAI H5NI virus-infected farms (black stars) and weather stations (red triangles).

Fig. 2.

Weekly number of cases of HPAI H5N1 since the beginning of the outbreak in Nigeria, January 2006.

Fig. 3.

Cases of HPAI H5N1 virus outbreak in Nigeria in 2006.

Fig. 4.

Box plots of the predicted weather variables.

Fig. 5

[colour online]. K-inhomogeneous functions using different edge corrections: theoretical Poisson, border-corrected estimate, translation-corrected estimate, and Ripley's isotropic correction estimate.

Fig. 6

[colour online]. HPAI H5N1 risk map from Poisson point process model with log-linear intensity. The intensity of the transmission of the virus (i.e. the number of outbreaks per unit area) is indicated by different colours with values ranging from 0 to 8.

Fig. 7

[colour online]. Habitat suitability index (0–100%) for HPAI H5N1 virus outbreak in Nigeria using the predicted weather data as environmental covariates.