Dengue disease dynamics are modulated by the combined influences of precipitation and landscape: A machine learning approach

Parallel prediction of dengue cases with different risks in Mexico using an artificial neural network model considering meteorological data

In 2022, Mexico registered an increase in dengue cases compared to the previous year. On the other hand, the amount of precipitation reported annually was slightly less than the previous year. Similarly, the minimum-mean-maximum temperatures recorded annually were below the previous year. In the literature, it is possible to find studies focused on the spread of dengue only for some specific regions of Mexico. However, given the increase in the number of cases during 2022 in regions not considered by previously published works, this study covers cases reported in all states of the country. On the other hand, determining a relationship between the dynamics of dengue cases and climatic factors through a computational model can provide relevant information on the transmission of the virus. A multiple-learning computational approach was developed to simulate the number of the different risks of dengue cases according to the classification reported per epidemiological week by considering climatic factors in Mexico. For the development of the model, the data were obtained from the reports published in the Epidemiological Panorama of Dengue in Mexico and in the National Meteorological Service. The classification of non-severe dengue, dengue with warning signs, and severe dengue were modeled in parallel through an artificial neural network model. Five variables were considered to train the model: the monthly average of the minimum, mean, and maximum temperatures, the precipitation, and the number of the epidemiological week. The selection of variables in this work is focused on the spread of the different risks of dengue once the mosquito begins transmitting the virus. Therefore, temperature and precipitation were chosen as climatic factors due to the close relationship between the density of adult mosquitoes and the incidence of the disease. The Levenberg-Marquardt algorithm was applied to fit the coefficients during the learning process. In the results, the ANN model simulated the classification of the different risks of dengue with the following precisions (R2): 0.9684, 0.9721, and 0.8001 for non-severe dengue, with alarm signs and severe, respectively. Applying a correlation matrix and a sensitivity analysis of the ANN model coefficients, both the average minimum temperature and precipitation were relevant to predict the number of dengue cases. Finally, the information discovered in this work can support the decision-making of the Ministry of Health to avoid a syndemic between the increase in dengue cases and other seasonal diseases.

Fine-scale adaptive divergence and population genetic structure of Aedes aegypti in Metropolitan Manila, Philippines

BACKGROUND

The adaptive divergence of Aedes aegypti populations to heterogeneous environments can be a driving force behind the recent expansion of their habitat distribution and outbreaks of dengue disease in urbanized areas. In this study, we investigated the population genomics of Ae. aegypti at a regional scale in Metropolitan Manila, Philippines.

METHODS

We used the Pool-Seq double digestion restriction-site association DNA sequencing (ddRAD-Seq) approach to generate a high number of single nucleotide polymorphisms (SNPs), with the aim to determine local adaptation and compare the population structure with 11 microsatellite markers. A total of 217 Ae. aegypti individuals from seven female and seven male populations collected from Metropolitan Manila were used in the assays.

RESULTS

We detected 65,473 SNPs across the populations, of which 76 were non-neutral SNPs. Of these non-neutral SNPs, the multivariate regression test associated 50 with eight landscape variables (e.g. open space, forest, etc.) and 29 with five climate variables (e.g. air temperature, humidity, etc.) (P-value range 0.005-0.045) in female and male populations separately. Male and female populations exhibited contrasting spatial divergence, with males exhibiting greater divergence than females, most likely reflecting the different dispersal abilities of male and female mosquitoes. In the comparative analysis of the same Ae. aegypti individuals, the pairwise FST values of 11 microsatellite markers were lower than those of the neutral SNPs, indicating that the neutral SNPs generated via pool ddRAD-Seq were more sensitive in terms of detecting genetic differences between populations at fine-spatial scales.

CONCLUSIONS

Overall, our study demonstrates the utility of pool ddRAD-Seq for examining genetic differences in Ae. aegypti populations in areas at fine-spatial scales that could inform vector control programs such as Wolbachia-infected mosquito mass-release programs. This in turn would provide information on mosquito population dispersal patterns and the potential barriers to mosquito movement within and around the release area. In addition, the potential of environmental adaptability observed in Ae. aegypti could help population control efforts.

Joint influence of architectural and spatiotemporal factors on the presence of Aedes aegypti in urban environments

BACKGROUND

Urbanization has led to the proliferation of high-rise buildings, which have substantially influenced the distribution of dengue vectors, such as Aedes aegypti (L.). However, knowledge gaps exist regarding the individual and combined effects of architectural and spatiotemporal factors on dengue vector. This study investigated the interrelationship between Ae. aegypti presence, building architectural features, and spatiotemporal factors in urban environments.

RESULTS

The mosquito Ae. aegypti presence varied by location and seasons, being higher in outdoor environments than in indoor environments. Lingya (Kaohsiung City, Taiwan) had the highest mosquito numbers, particularly in basement and first floor areas. Ae. aegypti was found on multiple floors within buildings, and their presence was greater in summer and autumn. The XGBoost model revealed that height within a building, temperature, humidity, resident density, and rainfall were key factors influencing mosquito presence, whereas openness had a relatively minor impact.

CONCLUSION

To effectively address the problems caused by urbanization, the three-dimensional distribution of Ae. aegypti, including their spatial distribution across heights and areas within the urban environment, must be considered. By incorporating these multiple factors, this approach provides valuable insights for those responsible for urban planning and disease management strategies. Understanding the interplay between architectural features, environmental conditions, and the presence of Ae. aegypti is essential for developing targeted interventions and mitigating the adverse impacts of urbanization on public health. © 2023 Society of Chemical Industry.

Associations between Dengue Incidence, Ecological Factors, and Anthropogenic Factors in Singapore

Singapore experiences endemic dengue. Vector control remains the primary means to reduce transmission due to the lack of available therapeutics. Resource limitations mean that vector-control tools need to be optimized, which can be achieved by studying risk factors related to disease transmission. We developed a statistical modelling framework which can account for a high-resolution and high-dimensional set of covariates to delineate spatio-temporal characteristics that are associated with dengue transmission from 2014 to 2020 in Singapore. We applied the proposed framework to two distinct datasets, stratified based on the primary type of housing within each spatial unit. Generalized additive models reveal non-linear exposure responses between a large range of ecological and anthropogenic factors as well as dengue incidence rates. At values below their mean, lesser mean total daily rainfall (Incidence rate ratio (IRR): 3.75, 95% CI: 1.00-14.05, Mean: 4.40 mm), decreased mean windspeed (IRR: 3.65, 95% CI: 1.87-7.10, Mean: 4.53 km/h), and lower building heights (IRR: 2.62, 95% CI: 1.44-4.77, Mean: 6.5 m) displayed positive associations, while higher than average annual NO2 concentrations (IRR: 0.35, 95% CI: 0.18-0.66, Mean: 13.8 ppb) were estimated to be negatively associated with dengue incidence rates. Our study provides an understanding of associations between ecological and anthropogenic characteristics with dengue transmission. These findings help us understand high-risk areas of dengue transmission, and allows for land-use planning and formulation of vector control policies.

How habitat factors affect an Aedes mosquitoes driven outbreak at temperate latitudes: The case of the Chikungunya virus in Italy

BACKGROUND

Outbreaks of Aedes-borne diseases in temperate areas are not frequent, and limited in number of cases. We investigate the associations between habitat factors and temperature on individuals' risk of chikungunya (CHIKV) in a non-endemic area by spatially analyzing the data from the 2017 Italian outbreak.

METHODOLOGY/PRINCIPAL FINDINGS

We adopted a case-control study design to analyze the association between land-cover variables, temperature, and human population density with CHIKV cases. The observational unit was the area, at different scales, surrounding the residence of each CHIKV notified case. The statistical analysis was conducted considering the whole dataset and separately for the resort town of Anzio and the metropolitan city of Rome, which were the two main foci of the outbreak. In Rome, a higher probability for the occurrence of CHIKV cases is associated with lower temperature (OR = 0.72; 95% CI: 0.61-0.85) and with cells with higher vegetation coverage and human population density (OR = 1.03; 95% CI: 1.00-1.05). In Anzio, CHIKV case occurrence was positively associated with human population density (OR = 1.03; 95% CI: 1.00-1.06) but not with habitat factors or temperature.

CONCLUSION/SIGNIFICANCE

Using temperature, human population density and vegetation coverage data as drives for CHIKV transmission, our estimates could be instrumental in assessing spatial heterogeneity in the risk of experiencing arboviral diseases in non-endemic temperate areas.

The association between dengue case and climate: A systematic review and meta-analysis

Although previous research frequently indicates that climate factors impact dengue transmission, the results are inconsistent. Therefore, this systematic review and meta-analysis highlights and address the complex global health problems towards the human-environment interface and the inter-relationship between these variables. For this purpose, four online electronic databases were searched to conduct a systematic assessment of published studies reporting the association between dengue cases and climate between 2010 and 2022. The meta-analysis was conducted using random effects to assess correlation, publication bias and heterogeneity. The final assessment included eight studies for both systematic review and meta-analysis. A total of four meta-analyses were conducted to evaluate the correlation of dengue cases with climate variables, namely precipitation, temperature, minimum temperature and relative humidity. The highest correlation is observed for precipitation between 83 mm and 15 mm (r = 0.38, 95% CI = 0.31, 0.45), relative humidity between 60.5% and 88.7% (r = 0.30, 95% CI = 0.23, 0.37), minimum temperature between 6.5 °C and 21.4 °C (r = 0.28, 95% CI = 0.05, 0.48) and mean temperature between 21.0 °C and 29.8 °C (r = 0.07, 95% CI = -0.1, 0.24). Thus, the influence of climate variables on the magnitude of dengue cases in terms of their distribution, frequency, and prevailing variables was established and conceptualised. The results of this meta-analysis enable multidisciplinary collaboration to improve dengue surveillance, epidemiology, and prevention programmes.

An assessment of remotely sensed environmental variables on Dengue epidemiology in Central India

In recent decades, dengue has been expanding rapidly in the tropical cities. Even though environmental factors and landscape features profoundly impact dengue vector abundance and disease epidemiology, significant gaps exist in understanding the role of local environmental heterogeneity on dengue epidemiology in India. In this study, we assessed the role of remotely sensed climatic factors (rainfall, temperature and humidity) and landscape variables (land use pattern, vegetation and built up density) on dengue incidence (2012–2019) in Bhopal city, Central India. Dengue hotspots in the city were assessed through geographical information system based spatial statistics. Dengue incidence increased from 0.59 cases in 2012 to 9.11 cases in 2019 per 10,000 inhabitants, and wards located in Southern Bhopal were found to be dengue hotspots. Distributed lag non-linear model combined with quasi Poisson regression was used to assess the exposure-response association, relative risk (RR), and delayed effects of environmental factors on dengue incidence. The analysis revealed a non-linear relationship between meteorological variables and dengue cases. The model shows that the risk of dengue cases increases with increasing mean temperature, rainfall and absolute humidity. The highest RR of dengue cases (~2.0) was observed for absolute humidity ≥60 g/m³ with a 5–15 week lag. Rapid urbanization assessed by an increase in the built-up area (a 9.1% increase in 2020 compared to 2014) could also be a key factor driving dengue incidence in Bhopal city. The study sheds important insight into the synergistic effects of both the landscape and climatic factors on the transmission dynamics of dengue. Furthermore, the study provides key baseline information on the climatic variables that can be used in the micro-level dengue prediction models in Bhopal and other cities with similar climatic conditions.

Dengue, a viral disease transmitted by infected Aedes mosquitoes, is a major public health concern globally. In addition to its increased incidence in recent years, dengue is also spreading to new geographical regions. Local environmental factors are known to modify the mosquito vector density that directly impacts dengue virus transmission. Understanding the influence of environmental factors (meteorological conditions and landscape features) on dengue epidemiology in local settings is important for focused dengue intervention. Here, by utilizing dengue incidence and remotely sensed environmental data from 2012–2019, we have assessed the role of environmental factors in driving dengue virus transmission in the city of Bhopal in Central India. During the study period, a 14.5 fold increase in dengue incidence was observed in Bhopal city, which is way higher than the 2.3 fold increase reported at the national level. The risk of dengue virus transmission was higher with higher temperature and absolute humidity. An increase in built-up area, a proxy for urbanization, was found to be another predictor of increased dengue incidence in Bhopal. These findings can provide a stepping-stone for the development of dengue prediction models and the identification of dengue hotspots in order to improve vector control of this disease in cities with similar environmental conditions.

A Retrospective Study of Climate Change Affecting Dengue: Evidences, Challenges and Future Directions

Climate change is unexpected weather patterns that can create an alarming situation. Due to climate change, various sectors are affected, and one of the sectors is healthcare. As a result of climate change, the geographic range of several vector-borne human infectious diseases will expand. Currently, dengue is taking its toll, and climate change is one of the key reasons contributing to the intensification of dengue disease transmission. The most important climatic factors linked to dengue transmission are temperature, rainfall, and relative humidity. The present study carries out a systematic literature review on the surveillance system to predict dengue outbreaks based on Machine Learning modeling techniques. The systematic literature review discusses the methodology and objectives, the number of studies carried out in different regions and periods, the association between climatic factors and the increase in positive dengue cases. This study also includes a detailed investigation of meteorological data, the dengue positive patient data, and the pre-processing techniques used for data cleaning. Furthermore, correlation techniques in several studies to determine the relationship between dengue incidence and meteorological parameters and machine learning models for predictive analysis are discussed. In the future direction for creating a dengue surveillance system, several research challenges and limitations of current work are discussed.

Improving Dengue Forecasts by Using Geospatial Big Data Analysis in Google Earth Engine and the Historical Dengue Information-Aided Long Short Term Memory Modeling

Simple Summary

Forecasting dengue cases often face challenges from (1) time-effectiveness due to time-consuming satellite data downloading and processing, (2) weak spatial representation due to data dependence on administrative unit-based statistics or weather station-based observations, and (3) stagnant accuracy without historical dengue cases. With the advance of the geospatial big data cloud computing in Google Earth Engine and deep learning, this study proposed an efficient framework of dengue prediction at an epidemiological week basis using geospatial big data analysis in Google Earth Engine and Long Short Term Memory modeling. We focused on the dengue epidemics in the Federal District of Brazil during 2007–2019. Based on Google Earth Engine and epidemiological calendar, we computed the weekly composite for each dengue driving factor, and spatially aggregated the pixel values into dengue transmission areas to generate the time series of driving factors. A multi-step-ahead Long Short Term Memory modeling was used, and the time-differenced natural log-transformed dengue cases and the time series of driving factors were considered as outcomes and explantary factors, respectively, with two modeling scenarios (with and without historical cases). The performance is better when historical cases were used, and the 5-weeks-ahead forecast has the best performance.

Abstract

Timely and accurate forecasts of dengue cases are of great importance for guiding disease prevention strategies, but still face challenges from (1) time-effectiveness due to time-consuming satellite data downloading and processing, (2) weak spatial representation capability due to data dependence on administrative unit-based statistics or weather station-based observations, and (3) stagnant accuracy without the application of historical case information. Geospatial big data, cloud computing platforms (e.g., Google Earth Engine, GEE), and emerging deep learning algorithms (e.g., long short term memory, LSTM) provide new opportunities for advancing these efforts. Here, we focused on the dengue epidemics in the urban agglomeration of the Federal District of Brazil (FDB) during 2007–2019. A new framework was proposed using geospatial big data analysis in the Google Earth Engine (GEE) platform and long short term memory (LSTM) modeling for dengue case forecasts over an epidemiological week basis. We first defined a buffer zone around an impervious area as the main area of dengue transmission by considering the impervious area as a human-dominated area and used the maximum distance of the flight range of Aedes aegypti and Aedes albopictus as a buffer distance. Those zones were used as units for further attribution analyses of dengue epidemics by aggregating the pixel values into the zones. The near weekly composite of potential driving factors was generated in GEE using the epidemiological weeks during 2007–2019, from the relevant geospatial data with daily or sub-daily temporal resolution. A multi-step-ahead LSTM model was used, and the time-differenced natural log-transformed dengue cases were used as outcomes. Two modeling scenarios (with and without historical dengue cases) were set to examine the potential of historical information on dengue forecasts. The results indicate that the performance was better when historical dengue cases were used and the 5-weeks-ahead forecast had the best performance, and the peak of a large outbreak in 2019 was accurately forecasted. The proposed framework in this study suggests the potential of the GEE platform, the LSTM algorithm, as well as historical information for dengue risk forecasting, which can easily be extensively applied to other regions or globally for timely and practical dengue forecasts.