Spatio-temporal analysis of American Tegumentary Leishmaniasis incidences in the Brazilian state of Amazonas: 2011 to 2022.

This study aimed to conduct a spatio-temporal analysis of tegumentary leishmaniasis occurrences in the Amazonas state, Brazil. An ecological study encompassing time series and spatial analysis was performed, exploring the geographic distribution and temporal trends of American Tegumentary Leishmaniasis (ATL) in Amazonas between 2011 and 2022. Secondary data extracted from the Department of Informatics of the Unified Health System (DATASUS) were utilized for this analysis. The study evaluated the relationship between disease cases and environmental/climatic variables (deforestation, temperature, precipitation, and relative humidity). Over the study period, 19,730 cases of tegumentary leishmaniasis were recorded, averaging an incidence of 41.4/100,000 inhabitants across the 62 municipalities of Amazonas state. Disease intensity varied with seasons. Generally, Amazonas state displayed a declining trend in ATL cases. However, certain municipalities, notably Rio Preto da Eva and Presidente Figueiredo, exhibited high incidence rates, while Canutama, Envira, Eirunepé, and Pauini municipalities demand closer attention due to their demonstrated increasing temporal trend of ATL cases. The analysis indicated a correlation between the number of ATL cases reported and relative humidity as well as precipitation. These findings underscore the significance of tegumentary leishmaniasis as a public health issue in the region and emphasize the necessity for public initiatives aimed at preventing this endemic illness.

Prediction of malaria using deep learning models: A case study on city clusters in the state of Amazonas, Brazil, from 2003 to 2018.

BACKGROUND: Malaria is curable. Nonetheless, over 229 million cases of malaria were recorded in 2019, along with 409,000 deaths. Although over 42 million Brazilians are at risk of contracting malaria, 99% percent of all malaria cases in Brazil are located in or around the Amazon rainforest. Despite declining cases and deaths, malaria remains a major public health issue in Brazil. Accurate spatiotemporal prediction of malaria propagation may enable improved resource allocation to support efforts to eradicate the disease. METHODS: In response to calls for novel research on malaria elimination strategies that suit local conditions, in this study, we propose machine learning (ML) and deep learning (DL) models to predict the probability of malaria cases in the state of Amazonas. Using a dataset of approximately 6 million records (January 2003 to December 2018), we applied k-means clustering to group cities based on their similarity of malaria incidence. We evaluated random forest, long-short term memory (LSTM) and dated recurrent unit (GRU) models and compared their performance. RESULTS: The LSTM architecture achieved better performance in clusters with less variability in the number of cases, whereas the GRU presents better results in clusters with high variability. Although Diebold-Mariano testing suggested that both the LSTM and GRU performed comparably, GRU can be trained significantly faster, which could prove advantageous in practice. CONCLUSIONS: All models showed satisfactory accuracy and strong performance in predicting new cases of malaria, and each could serve as a supplemental tool to support regional policies and strategies.

Prediction of malaria using deep learning models: A case study on city clusters in the state of Amazonas, Brazil, from 2003 to 2018

ABSTRACT Background: Malaria is curable. Nonetheless, over 229 million cases of malaria were recorded in 2019, along with 409,000 deaths. Although over 42 million Brazilians are at risk of contracting malaria, 99% percent of all malaria cases in Brazil are located in or around the Amazon rainforest. Despite declining cases and deaths, malaria remains a major public health issue in Brazil. Accurate spatiotemporal prediction of malaria propagation may enable improved resource allocation to support efforts to eradicate the disease. Methods: In response to calls for novel research on malaria elimination strategies that suit local conditions, in this study, we propose machine learning (ML) and deep learning (DL) models to predict the probability of malaria cases in the state of Amazonas. Using a dataset of approximately 6 million records (January 2003 to December 2018), we applied k-means clustering to group cities based on their similarity of malaria incidence. We evaluated random forest, long-short term memory (LSTM) and dated recurrent unit (GRU) models and compared their performance. Results: The LSTM architecture achieved better performance in clusters with less variability in the number of cases, whereas the GRU presents better results in clusters with high variability. Although Diebold-Mariano testing suggested that both the LSTM and GRU performed comparably, GRU can be trained significantly faster, which could prove advantageous in practice. Conclusions: All models showed satisfactory accuracy and strong performance in predicting new cases of malaria, and each could serve as a supplemental tool to support regional policies and strategies.

The risk of malaria infection for travelers visiting the Brazilian Amazonian region: A mathematical modeling approach.

BACKGROUND: Human mobility between malaria endemic and malaria-free areas can hinder control and elimination efforts in the Amazon basin, maintaining Plasmodium circulation and introduction to new areas. METHODS: The analysis begins by estimating the incidence of malaria in areas of interest. Then, the risk of infection as a function of the duration of stay after t0 was calculated as the number of infected travelers over the number of arrived travelers. Differential equations were employed to estimate the risk of nonimmune travelers acquiring malaria in Amazonian municipalities. Risk was calculated as a result of the force of the infection in terms of local dynamics per time of arrival and duration of visit. RESULTS: Maximum risk occurred at the peak or at the end of the rainy season and it was nonlinearly (exponentially) correlated with the fraction of infected mosquitoes. Relationship between the risk of malaria and duration of visit was linear and positively correlated. Relationship between the risk of malaria and the time of arrival in the municipality was dependent on local effects of seasonality. CONCLUSIONS: The risk of nonimmune travelers acquiring malaria is not negligible and can maintain regional circulation of parasites, propagating introductions in areas where malaria has been eliminated.

Malaria in the State of Amazonas: a typical Brazilian tropical disease influenced by waves of economic development.

In Brazil, more than 99% of malaria cases are reported in the Amazon, and the State of Amazonas accounts for 40% of this total. However, the accumulated experience and challenges in controlling malaria in this region in recent decades have not been reported. Throughout the first economic cycle during the rubber boom (1879 to 1912), malaria was recorded in the entire state, with the highest incidence in the villages near the Madeira River in the Southern part of the State of Amazonas. In the 1970s, during the second economic development cycle, the economy turned to the industrial sector and demanded a large labor force, resulting in a large migratory influx to the capital Manaus. Over time, a gradual increase in malaria transmission was observed in peri-urban areas. In the 1990s, the stimulation of agroforestry, particularly fish farming, led to the formation of permanent Anopheline breeding sites and increased malaria in settlements. The estimation of environmental impacts and the planning of measures to mitigate them, as seen in the construction of the Coari-Manaus gas pipeline, proved effective. Considering the changes occurred since the Amsterdam Conference in 1992, disease control has been based on early diagnosis and treatment, but the development of parasites that are resistant to major antimalarial drugs in Brazilian Amazon has posed a new challenge. Despite the decreased lethality and the gradual decrease in the number of malaria cases, disease elimination, which should be associated with government programs for economic development in the region, continues to be a challenge.

Malaria in the State of Amazonas: a typical Brazilian tropical disease influenced by waves of economic development

In Brazil, more than 99% of malaria cases are reported in the Amazon, and the State of Amazonas accounts for 40% of this total. However, the accumulated experience and challenges in controlling malaria in this region in recent decades have not been reported. Throughout the first economic cycle during the rubber boom (1879 to 1912), malaria was recorded in the entire state, with the highest incidence in the villages near the Madeira River in the Southern part of the State of Amazonas. In the 1970s, during the second economic development cycle, the economy turned to the industrial sector and demanded a large labor force, resulting in a large migratory influx to the capital Manaus. Over time, a gradual increase in malaria transmission was observed in peri-urban areas. In the 1990s, the stimulation of agroforestry, particularly fish farming, led to the formation of permanent Anopheline breeding sites and increased malaria in settlements. The estimation of environmental impacts and the planning of measures to mitigate them, as seen in the construction of the Coari-Manaus gas pipeline, proved effective. Considering the changes occurred since the Amsterdam Conference in 1992, disease control has been based on early diagnosis and treatment, but the development of parasites that are resistant to major antimalarial drugs in Brazilian Amazon has posed a new challenge. Despite the decreased lethality and the gradual decrease in the number of malaria cases, disease elimination, which should be associated with government programs for economic development in the region, continues to be a challenge.

Phlebotomine sandflies (Diptera: Psychodidae) from Lábrea, state of Amazonas, Brazil, with a description of Evandromyia (Aldamyia) apurinan Shimabukuro, Figueira & Silva, sp. nov.

An entomological survey was conducted from July-December 2009 and September-December 2010, as part of the epidemiological monitoring of American cutaneous leishmaniasis (ACL) in the municipality of Lábrea, state of Amazonas (AM), Brazil. Sandflies were collected using CDC light traps installed in intra and peridomiciliary locations, as well as the border of forested areas around houses where autochthonous cases of ACL were recorded. A total of 510 sandflies belonging to 26 species were collected. The most abundant species was Nyssomyia antunesi (44.5%) followed by Evandromyia walkeri (10.6%) and Micropygomyia rorotaensis (9.8%). Here we also describe Evandromyia (Aldamyia) apurinan sp. nov. and report new records for Trichophoromyia flochi and Evandromyia sipani in AM and Brazil, respectively. Our results describe the composition of the sandfly fauna in the south of AM and suggest Ny. antunesi as the putative vector in the transmission of Leishmania in this area of the Amazon Region.

Phlebotomine sandflies (Diptera: Psychodidae) from Lábrea, state of Amazonas, Brazil, with a description of Evandromyia (Aldamyia) apurinan Shimabukuro, Figueira & Silva, sp. nov.

An entomological survey was conducted from July-December 2009 and September-December 2010, as part of the epidemiological monitoring of American cutaneous leishmaniasis (ACL) in the municipality of Lábrea, state of Amazonas (AM), Brazil. Sandflies were collected using CDC light traps installed in intra and peridomiciliary locations, as well as the border of forested areas around houses where autochthonous cases of ACL were recorded. A total of 510 sandflies belonging to 26 species were collected. The most abundant species was Nyssomyia antunesi (44.5%) followed by Evandromyia walkeri (10.6%) and Micropygomyia rorotaensis (9.8%). Here we also describe Evandromyia (Aldamyia) apurinan sp. nov. and report new records for Trichophoromyia flochi and Evandromyia sipani in AM and Brazil, respectively. Our results describe the composition of the sandfly fauna in the south of AM and suggest Ny. antunesi as the putative vector in the transmission of Leishmania in this area of the Amazon Region.