@article{Nieto_Malone_Bavia_2006, title={Ecological niche modeling for visceral leishmaniasis in the state of Bahia, Brazil, using genetic algorithm for rule-set prediction and growing degree day-water budget analysis}, volume={1}, url={https://www.geospatialhealth.net/gh/article/view/286}, DOI={10.4081/gh.2006.286}, abstractNote={Two predictive models were developed within a geographic information system using Genetic Algorithm Rule-Set Prediction (GARP) and the growing degree day (GDD)-water budget (WB) concept to predict the distribution and potential risk of visceral leishmaniasis (VL) in the State of Bahia, Brazil. The objective was to define the environmental suitability of the disease as well as to obtain a deeper understanding of the eco-epidemiology of VL by associating environmental and climatic variables with disease prevalence. Both the GARP model and the GDDWB model, using different analysis approaches and with the same human prevalence database, predicted similar distribution and abundance patterns for the <em>Lutzomyia longipalpis-Leishmania</em> chagasi system in Bahia. High and moderate prevalence sites for VL were significantly related to areas of high and moderate risk prediction by: (i) the area predicted by the GARP model, depending on the number of pixels that overlapped among eleven annual model years, and (ii) the number of potential generations per year that could be completed by the <em>Lu. longipalpis-L. chagasi</em> system by GDD-WB analysis. When applied to the ecological zones of Bahia, both the GARP and the GDD-WB prediction models suggest that the highest VL risk is in the interior region of the state, characterized by a semi-arid and hot climate known as Caatinga, while the risk in the Bahia interior forest and the Cerrado ecological regions is lower. The Bahia coastal forest was predicted to be a low-risk area due to the unsuitable conditions for the vector and VL transmission.}, number={1}, journal={Geospatial Health}, author={Nieto, Prixia and Malone, John B. and Bavia, Maria E.}, year={2006}, month={Nov.}, pages={115–126} }