Culex pipiens distribution in Tunisia: Identification of suitable areas through Random Forest and MaxEnt approaches

Abstract

Background Tunisia has experienced several West Nile virus (WNV) outbreaks since 1997. Yet, there is limited information on the spatial distribution of the main WNV mosquito vector Culex pipiens suitability at the national level. Objectives In the present study, our aim was to predict and evaluate the potential and current distribution of Cx. pipiens in Tunisia. Methods To this end, two species distribution models were used, i.e. MaxEnt and Random Forest. Occurrence records for Cx. pipiens were obtained from adult and larvae sampled in Tunisia from 2014 to 2017. Climatic and human factors were used as predictors to model the Cx. pipiens geographical distribution. Mean decrease accuracy and mean decrease Gini indices were calculated to evaluate the importance of the impact of different environmental and human variables on the probability distribution of Cx. pipiens. Results Suitable habitats were mainly distributed next to oases, in the north and eastern part of the country. The most important predictor was the population density in both models. The study found out that the governorates of Monastir, Nabeul, Manouba, Ariana, Bizerte, Gabes, Medenine and Kairouan are at highest epidemic risk. Conclusions The potential distribution of Cx. pipiens coincides geographically with the observed distribution of the disease in humans in Tunisia. Our study has the potential for driving control effort in the fight against West Nile vector in Tunisia.

The historical ecological background of West Nile virus in Portugal provides One Health opportunities into the future

“…The estimated WNV ecological suitability per freguesia of each ML model was combined to inform a metalearner model (Generalized Linear Model with negative weights) for a final estimation of local WNV ecological suitability per freguesia . For ML modelling classification of WNV present and pseudo-absent, we considered a conservative threshold of 0.5 (similar to previous studies 44,45 ). When performing machine learning with BRT and RF approaches, a balanced training dataset is recommended in terms of all possible classes for classification (in this case, present and pseudo-absent) 46 .…”

“…We considered a conservative threshold of 0.5 (like in previous similar studies 20,21 ) for classification (i.e. pseudo-absent classification was considered below 0.5 and present classification above 0.5).…”

Ecological Niche Modelling Approaches: Challenges and Applications in Vector-Borne Diseases

“…As far as we know, this is what occurs with a large amount of the studies dealing with VBDs. As these kinds of studies are usually performed with public health purposes at regional or local scales, they often rely on regional/national datasets collected by administrations or NGOs whose range of action is defined by restricted geographical or political borders (i.e., country or even provinces' administrations) (e.g., [67][68][69]80,[83][84][85][86][87][88][89][90][91][92][93][94][95][96]98,99,101,[104][105][106][107][108][112][113][114][115][116][117]). The concern resides in the fact that ENM built with occurrence data restricted to artificial boundaries might consider only a subset of the environmental conditions experienced by a species across its entire range (i.e., "spatial niche truncation" [118]); therefore, providing an incomplete description of the environmental limits [109] and underestimating the environmental conditions that the species can withstand [111] (see an example in Figure 2).…”

“…Despite the sampling bias and the consequent non-independence of occurrences needing to be accounted for, a good number of the VBDs studies published in the last three years omitted declaring any procedure for dealing with the sampling bias [67,68,[80][81][82][83][84][85][86]88,89,91,[94][95][96]98,101,104,108,113,124,142].…”

“…Despite the choice of algorithms or estimation frameworks, model calibration is a key process in which variable selection and model settings are fine-tuned to obtain the best model performance [64,155]. Unfortunately, in spite of the recommendations for maximizing reproducibility of ENMs [64,156], the information concerning model calibration is lacking in a high number of studies dealing with VBDs [80,[82][83][84][85][86]88,89,91,92,96,98,107,112,113,124].…”