A utilização de uma rede neural artificial para previsão da incidência da malária no município de Cantá, estado de Roraima / Use of an artificial neural network to predict the incidence of malaria in the city of Cantá, state of Roraima

INTRODUÇÃO: A malária é uma doença endêmica na Amazônia Legal Brasileira, apresentando riscos diferentes para cada região. O Município de Cantá, no Estado de Roraima, apresentou para todo o período estudado, um dos maiores índices parasitários anuais do Brasil, com valor sempre maior que 50. O presente estudo visa à utilização de uma rede neural artificial para previsão da incidência da malária nesse município, a fim de auxiliar os coordenadores de saúde no planejamento e gestão dos recursos. MÉTODOS: Os dados foram coletados no site do Ministério da Saúde, SIVEP - Malária entre 2003 e 2009. Estruturou-se uma rede neural artificial com três neurônios na camada de entrada, duas camadas intermediárias e uma camada de saída com um neurônio. A função de ativação foi à sigmoide. No treinamento, utilizou-se o método backpropagation, com taxa de aprendizado de 0,05 e momentum 0,01. O critério de parada foi atingir 20.000 ciclos ou uma meta de 0,001. Os dados de 2003 a 2008 foram utilizados para treinamento e validação. Comparam-se os resultados com os de um modelo de regressão logística. RESULTADOS: Os resultados para todos os períodos previstos mostraram-se que as redes neurais artificiais obtiveram um menor erro quadrático médio e erro absoluto quando comparado com o modelo de regressão para o ano de 2009. CONCLUSÕES: A rede neural artificial se mostrou adequada para um sistema de previsão de malária no município estudado, determinando com pequenos erros absolutos os valores preditivos, quando comparados ao modelo de regressão logística e aos valores reais.

INTRODUCTION: Malaria is endemic in the Brazilian Amazon region, with different risks for each region. The City of Cantá, State of Roraima, presented one of the largest annual parasite indices in Brazil for the entire study period, with a value always greater than 50. The present study aimed to use an artificial neural network to predict the incidence of malaria in this city in order to assist health coordinators in planning and managing resources. METHODS: Data were collected on the website of the Ministry of Health, SIVEP - Malaria between 2003 and 2009. An artificial neural network was structured with three neurons in the input layer, two intermediate layers and an output layer with one neuron. A sigmoid activation function was used. In training, the backpropagation method was used, with a learning rate of 0.05 and momentum of 0.01. The stopping criterion was to reach 20,000 cycles or a target of 0.001. The data from 2003 to 2008 were used for training and validation. The results were compared with those from a logistic regression model. RESULTS: The results for all periods provided showed that the artificial neural network had a smaller mean square error and absolute error compared with the regression model for the year 2009. CONCLUSIONS: The artificial neural network proved to be adequate for a malaria forecasting system in the city studied, determining smaller predictive values with absolute errors compared to the logistic regression model and the actual values.

Seasonal dynamics of Aedes aegypti (Diptera: Culicidae) in the northernmost state of Brazil: a likely port-of-entry for dengue virus 4

Roraima is the northernmost state of Brazil, bordering both Venezuela and Guyana. Appropriate climate and vector conditions for dengue transmission together with its proximity to countries where all four dengue serotypes circulate make this state, particularly the capital Boa Vista, strategically important for dengue surveillance in Brazil. Nonetheless, few studies have addressed the population dynamics of Aedes aegypti in Boa Vista. In this study, we report temporal and spatial variations in Ae. aegypti population density using ovitraps in two highly populated neighbourhoods; Centro and Tancredo Neves. In three out of six surveys, Ae. aegypti was present in more than 80 percent of the sites visited. High presence levels of this mosquito suggest ubiquitous human exposure to the vector, at least during part of the year. The highest infestation rates occurred during the peak of the rainy seasons, but a large presence was also observed during the early dry season (although with more variation among years). Spatial distribution of positive houses changed from a sparse and local pattern to a very dense pattern during the dry-wet season transition. These results suggest that the risk of dengue transmission and the potential for the new serotype invasions are high for most of the year.

Affinity and diversity indices for anopheline immature forms

As for the entire Amazon Region, malaria continues to be a major health public problem in Roraima that presented an Annual Parasitic Index of 85.4 in 2005, the highest in Brazil. Information on anopheline breeding sites is an essential component in malaria control strategies. Aiming to contribute to the limited knowledge on anopheline immature forms in Roraima, collections and breeding site observations were performed in 10 breeding sites around the capital city Boa Vista. Collections were carried out in the rainy and dry season periods between April 2004 and January 2005. Breeding sites comprised natural and artificial water reservoirs. A total of 623 immature forms were collected belonging to Anopheles albitarsis s.l., An.triannulatus s.l., An. nuneztovari/dunhami, An. braziliensis, An. evansae, An. oswaldoi s.l., An. strodei and An. darlingi. An. albitarsis and An. braziliensis were the most frequently found species. Eight larvae of An. darlingi were found in only one breeding site located in the forest. An. triannulatus/An. nuneztovari and An. albitarsis/An. braziliensis were the pairs of species that mostly occurred together. Both pair of species displayed the highest affinity index what might indicate a high compatibility for the same breeding conditions and/or a synergistic co-occurrence. Species diversity index was higher for the dry season.

Como para toda a Amazônia, a malária representa um importante problema de saúde pública em Roraima. Roraima apresentou um índice parasitário anual de 85,4 em 2005, o maior do Brasil. O conhecimento dos criadouros de anofelinos constitui-se num componente primordial nas estratégias de controle da malária. No intuito de contribuir para o limitado conhecimento dos criadouros de anofelinos em Roraima, coleções de imaturos e observações dos criadouros foram realizadas no entorno da capital Boa Vista. As coletas foram feitas nas estações seca e chuvosa entre abril de 2004 e janeiro de 2005. Os criadouros observados foram reservatórios de água naturais e artificiais. Um total de 623 formas imaturas foram coletadas pertencentes às espécies An. albitarsis s.l., An.triannulatus s.l., An. nuneztovari/dunhami, An. braziliensis, An. evansae, An. oswaldoi s.l., An. strodei e An. darlingi. An. braziliensis e An. albitarsis foram as espécies mais freqüentemente encontradas. Oito larvas de An. darlingi foram encontradas em apenas um criadouro na floresta. An. triannulatus/An. nuneztovari e An. albitarsis/An. braziliensis foram os pares de espécies de maior co-ocorrência. Ambos pares de espécies apresentaram o maior índice de afinidade o que pode indicar compatibilidade para as mesmas condições prevalentes nos criadouros e/ou sinergismo. O índice de diversidade de espécies foi maior para a estação seca.

An ecoregional classification for the state of Roraima, Brazil: the importance of landscape in malaria biology

Understanding the different background landscapes in which malaria transmission occurs is fundamental to understanding malaria epidemiology and to designing effective local malaria control programs. Geology, geomorphology, vegetation, climate, land use, and anopheline distribution were used as a basis for an ecological classification of the state of Roraima, Brazil, in the northern Amazon Basin, focused on the natural history of malaria and transmission. We used unsupervised maximum likelihood classification, principal components analysis, and weighted overlay with equal contribution analyses to fine-scale thematic maps that resulted in clustered regions. We used ecological niche modeling techniques to develop a fine-scale picture of malaria vector distributions in the state. Eight ecoregions were identified and malaria-related aspects are discussed based on this classification, including 5 types of dense tropical rain forest and 3 types of savannah. Ecoregions formed by dense tropical rain forest were named as montane (ecoregion I), submontane (II), plateau (III), lowland (IV), and alluvial (V). Ecoregions formed by savannah were divided into steppe (VI, campos de Roraima), savannah (VII, cerrado), and wetland (VIII, campinarana). Such ecoregional mappings are important tools in integrated malaria control programs that aim to identify specific characteristics of malaria transmission, classify transmission risk, and define priority areas and appropriate interventions. For some areas, extension of these approaches to still-finer resolutions will provide an improved picture of malaria transmission patterns.

Associations between dengue and combinations of weather factors in a city in the Brazilian Amazon

OBJECTIVES: Dengue has become the most important endemic disease in Brazil. The Amazonian state of Roraima has one of the highest incidence rates of dengue in the country. The objective of this study was to determine whether significant temporal relationships exist between the number of reported dengue cases and short-term climate measures for the city of Boa Vista, the capital of Roraima. If such relationships exist, that suggests that it may be possible to predict dengue case numbers based on antecedent climate, thus helping develop a climate-based dengue early-warning system for Boa Vista. METHODS: Seasonal Pearson product-moment correlations were developed between 3-week running averages of daily numbers of reported dengue cases for September 1998-December 2001 and certain meteorological variables (thermal, hydroclimatic, wind, atmospheric pressure, and humidity) up to 25 weeks before. Two-sample t tests were also applied to test for statistically significant differences between samples of daily dengue cases with above-average values and samples with below-average values for three-variable meteorological combinations. These multivariate combinations consisted of the three climate measures that together explained the greatest portion of the variance in the number of dengue cases for the particular season. RESULTS: The strength of the individual averaged correlations varied from weak to moderate. The correlations differed according to the period of the year, the particular climatic variable, and the lag period between the climate indicator and the number of dengue cases. The seasonal correlations in our study showed far stronger relationships than had daily, full-year measures reported in previous studies. Two-sample t tests of multivariate meteorological combinations of atmospheric pressure, wind, and humidity values showed statistically significant differences in the number of reported dengue cases. CONCLUSIONS: Relationships between...

A Triatoma maculata ( Hemiptera, Reduviidae, Triatominae ) population from Roraima, Amazon region, Brazil, has some bionomic characteristics of a potential Chagas disease vector

A doença de Chagas é de rara ocorrência na Região Amazônica Brasileira, onde contudo as condições para o estabelecimento de ciclos domésticos existem. Um estudo previamente realizado em áreas de colonização agrícola no Estado de Roraima, mostrou a possibilidade de ciclos autóctones de transmissão virem a ocorrer uma vez que todos os elementos estavam lá presentes, indivíduos infectados por Trypanosoma cruzi, espécies de triatomíneos anteriormente descritas como infectadas por T. cruzi na Região Amazônica de países fronteiriços e, ambientes domiciliares e peri-domiciliares favoráveis à colonização de triatomíneos. Triatoma maculata foi a espécie mais frequentemente encontrada, tendo sido coletada em galinheiros no peridomicílio e esporadicamente nos domicílios. Visando investigar a potencialidade de T. maculata como espécie vetora na área, algumas características bionômicas foram estudadas em condições de laboratório incluindo freqüência de alimentação, tempo de defecação pós-prandial, tempo de jejum voluntário na pré- e na pós-ecdise, período inter-mudas, períodos de pré-oviposição e de oviposição, índice de oviposição, período de incubação, viabilidade dos ovos, índices de longevidade e de mortalidade. Os resultados mostraram que a população de T. maculata da Colônia Agrícola do Passarão deve ser considerada vetora em potencial do T. cruzi uma vez que mostrou capacidade de infestar ecótopos artificiais no peridomicílio, de se alimentar com freqüência durante o período ninfal, de possuir um ciclo de desenvolvimento relativamente curto com 2,9 gerações/ano, de possuir hábitos ecléticos de alimentação, de defecar imediatamente após a hematofagia quando ainda no hospedeiro e devido ao fato de ter sido previamente encontrada infectada por T. cruzi.

On the possibility of autochthonous Chagas disease in Roraima, Amazon region, Brazil, 2000-2001

A doença de Chagas foi quase inteiramente erradicada das zonas áridas do Brasil Central e Nordeste, onde ciclos autóctones de transmissão praticamente inexistem. Contudo, na última década a doença vem sendo registrada na Região Amazônica. Objetivando investigar a possibilidade da ocorrência de ciclos autóctones de transmissão em áreas de colonização agrícola no Estado de Roraima, foram realizadas coletas de triatomíneos e estudos de sua biologia (a ser mostrado em outro artigo), sorologia (imunofluorescência, hemaglutinação, ELISA) e pesquisa parasitológica (xenodiagnóstico, PCR) entre moradores de Rorainópolis, do Projeto Passarão e da Comunidade da Ilha. Candidatos a doação sanguínea do Hemocentro de Boa Vista também foram avaliados. Foram coletados Triatoma maculata, Rhodnius pictipes, Rhodnius robustus e Panstrongylus geniculatus em palmeiras-buriti Mauritia flexuosa, em anexos peridomiciliares e em domicílios. Nenhum triatomíneo foi encontrado naturalmente infectado. A presença de anticorpos anti-Trypanosoma cruzi foi verificada em 25 indivíduos (1,4% de um total de 1821), 20 dos quais migrantes, todos adultos >15 anos. Apenas dois indivíduos migrantes tiveram mais de dois exames sorológicos positivos (um ainda com xenodiagnóstico positivo e o outro com PCR positivo), estando seguramente infectados. Os resultados mostram que apesar de não ser endêmica, há a presença de todos os elos da cadeia de transmissão da doença de Chagas em Roraima que permitem a sua instalação na ausência de vigilância.

Preliminary assays indicate that Antonia ovata (Loganiaceae) and Derris amazonica (Papilionaceae), ichthyotoxic plants used for fishing in Roraima, Brazil, have an insecticide effect on Lutzomyia longipalpis (Diptera: Psychodidae: Phlebotominae)

Laboratory-reared Lutzomyia longipalpis (Lutz and Neiva 1912) was tested with extracts of two ichthyotoxic plants, known as timbós, used as fishing poison in the Amazon. Phlebotomines, L. longipalpis, and plants, Antonia ovata and Derris amazonica, were collected in the Raposa-Serra do Sol Indian Reserve, a focus of visceral leishmaniasis in the State of Roraima, Brazil. Extracts were prepared from dried leaves of A. ovata and roots of D. amazonica that were percolated in water, filtered and dried out at 50°C. The solid extract obtained was diluted in water at 150, 200 and 250 mg/ml. The solution was blotted in filter paper placed at the bottom of cylindric glass tubes containing sand flies. For each plant extract and dilution, two series of triplicates with 5 male and 5 female specimens of L. longipalpis were used. Mortality was recorded every 2 h during 72 h of exposure. At 72 h the mortality was as high as 80 percent for extracts of A. ovata (LD50 = 233 mg/ ml), and 100 percent for D. amazonica (LD50 = 212 mg/ ml) whereas in the control groups maximum mortality never surpassed 13 percent. Preliminary assays indicated that A. ovata and D. amazonica displayed significant insecticide effect against L. longipalpis

Aspects related to productivity for four generations of a Lutzomyia longipalpis laboratory colony

A closed colony of Lutzomyia longipalpis was established with specimens collected in the Raposa - Serra do Sol indian reservoir, one of the main foci of visceral leishmaniasis in the State of Roraima, Brazil. Biological observations were made on four generations of a L. longipalpis colony with emphasis on productivity. Aspects studied were the number of laid and retained eggs, and the number of adults (male and female) per generation. During the four generations the percentage of engorged females that laid eggs varied from 64.2 (third generation-F3) to 90.3 (second generation-F2). The mean number of eggs laid per female varied from 23.6 (F3) to 39. 9 (first generation-F1). The maximum number of eggs laid per female varied from 84 (F3) to 124 (F1). The mean number of retained eggs per female was 12.7 (parental generation-P and F1) to 22.1 (F2). The number of females exceeded the number of males in all generations. However, significant difference for male/female ratio was found only for F3. Fecundity rates were between 42.1 (F3) and 58.3 (F2). From a total of 439 blood-fed females, 355 females laid 12,257 eggs that yield 5,354 adults (2,525 males and 2,829 females) in four generations. F2 presented maximum productivity and fecundity rates.