Article révisé par les pairs
Résumé : Malaria remains a major public health problem, causing 435,000 deaths in 2017. The objective of this study was to estimate the prediction ability of vector species associated with the prediction power of environmental and socio-economic factors for malaria risk. Logistic regression was used for malaria risk estimation. A Radial Basis Function model was applied for estimating the predictive ability of Anopheles species, environmental and socio-economic factors. The lowest fever prevalence was found where Anopheles melas was dominant. Anopheles coluzzi and Anopheles gambiae were the dominant species where prevalence of malaria was high. Altitude, country and vector species were the best predictive factors. Anopheles arabiensis, An. coluzzi and An. gambiae were most common in urban areas. This study will improve the prediction of malaria risk in targeted areas. We have observed how important it is to adapt health policies according to the dominant malaria vector in a region.