Spatiotemporal and Socioeconomic Risk Factors for Dengue at the Province Level in Vietnam, 2013-2015: Clustering Analysis and Regression Model

Microclimate factors related to dengue virus burden clusters in two endemic towns of Mexico

In dengue-endemic areas, transmission control is limited by the difficulty of achieving sufficient coverage and sustainability of interventions. To maximize the effectiveness of interventions, areas with higher transmission could be identified and prioritized. The aim was to identify burden clusters of Dengue virus (DENV) infection and evaluate their association with microclimatic factors in two endemic towns from southern Mexico. Information from a prospective population cohort study (2·5 years of follow-up) was used, microclimatic variables were calculated from satellite information, and a cross-sectional design was conducted to evaluate the relationship between the outcome and microclimatic variables in the five surveys. Spatial clustering was observed in specific geographic areas at different periods. Both, land surface temperature (aPR 0·945; IC95% 0·895-0·996) and soil humidity (aPR 3·018; IC95% 1·013-8·994), were independently associated with DENV burden clusters. These findings can help health authorities design focused dengue surveillance and control activities in dengue endemic areas.

A Novel CNN-TLSTM Approach for Dengue Disease Identification and Prevention using IoT-Fog Cloud Architecture

One of the mosquito-borne pandemic viral infections is Dengue which is mostly transmitted to humans by the Aedes agypti or female Aedes albopictis mosquitoes. The dengue disease expansion is mainly due to the different factors such as climate change, socioeconomic factors, viral evolution, globalization, etc. The unavailability of certain antiviral therapy and specific vaccine increases the risk of the dengue disease spreading even further. This arises the need for a novel technique that overcomes the complexities associated with dengue disease prediction such as low reporting level, misclassification, and incompatible disease monitoring framework. This paper mainly overcomes the above-mentioned problems by integrating the Internet of Things (IoT), fog-cloud, and deep learning techniques for efficient dengue monitoring. A compatible disease monitoring framework is formed via the IoT devices and the reports are effectively created and transferred to the healthcare facilities via the fog-cloud model. The misdiagnosis error is overcome in this paper using the novel Hybrid Convolutional Neural Network (CNN) with Tanh Long and Short Term Memory (TLSTM) based Adaptive Teaching Learning Based Optimization (ATLBO) algorithm. The ATLBO optimized CNN-TLSTM architecture mainly analyzes the dengue-related parameters such as Soft Bleeding, Muscle Pain, Joint Pain, Skin rash, Fever, Water Site, Carbon Dioxide, Water Site Humidity, Water Site Temperature, etc. for an efficient clinical decision making and timely disease diagnosis. The experimental results are conducted using a real-time dataset and its performance is validated using various performance metrics. When compared in terms of different statistical parameters such as accuracy, f-measure, mean square error, and reliability, the proposed method offers superior results in the case of dengue disease detection than other existing methods. The ATLBO optimized hybrid CNN-TLSTM shows an accuracy of 96.9%, a precision of 95.7%, recall of 96.8%, and F-measure of 96.2% which is relatively high when compared to the existing techniques. The proposed model is capable of identifying the patients in a certain geographical region and preventing the disease emergency via immediate disease diagnosis and alerting the healthcare officials to offer the stipulated services.

Explaining Neighbourhood Variations in the Incidence of Dengue Fever in Jeddah City, Saudi Arabia

The rapid growth and development of cities is a contributing factor to the rise and persistence of dengue fever (DF) in many areas around the world. Many studies have examined how neighbourhood environmental conditions contribute to dengue fever and its spread, but have not paid enough attention to links between socio-economic conditions and other factors, including population composition, population density, the presence of migrant groups, and neighbourhood environmental conditions. This study examines DF and its distribution across 56 neighbourhoods of Jeddah City, Saudi Arabia, where the incidence of dengue remains high. Using stepwise multiple regression analysis it focuses on the key ecological correlates of DF from 2006-2009, the years of the initial outbreak. Neighbourhood variations in average case rates per 10,000 population (2006-2009) were largely predicted by the Saudi gender ratio and socio-economic status (SES), the respective beta coefficients being 0.56 and 0.32 (p < 0.001). Overall, 77.1% of cases occurred in the poorest neighbourhoods. SES effects, however, are complex and were partly mediated by neighbourhood population density and the presence of migrant groups. SES effects persisted after controls for both factors, suggesting the effect of other structural factors and reflecting a lack of DF awareness and the lack of vector control strategies in poorer neighbourhoods. Neighbourhood environmental conditions, as measured by the presence of surface water, were not significant. It is suggested that future research pay more attention to the different pathways that link neighbourhood social status to dengue and wider health outcomes.

Spatial connectivity in mosquito-borne disease models: a systematic review of methods and assumptions

Spatial connectivity plays an important role in mosquito-borne disease transmission. Connectivity can arise for many reasons, including shared environments, vector ecology and human movement. This systematic review synthesizes the spatial methods used to model mosquito-borne diseases, their spatial connectivity assumptions and the data used to inform spatial model components. We identified 248 papers eligible for inclusion. Most used statistical models (84.2%), although mechanistic are increasingly used. We identified 17 spatial models which used one of four methods (spatial covariates, local regression, random effects/fields and movement matrices). Over 80% of studies assumed that connectivity was distance-based despite this approach ignoring distant connections and potentially oversimplifying the process of transmission. Studies were more likely to assume connectivity was driven by human movement if the disease was transmitted by an Aedes mosquito. Connectivity arising from human movement was more commonly assumed in studies using a mechanistic model, likely influenced by a lack of statistical models able to account for these connections. Although models have been increasing in complexity, it is important to select the most appropriate, parsimonious model available based on the research question, disease transmission process, the spatial scale and availability of data, and the way spatial connectivity is assumed to occur.

Determine neighboring region spatial effect on dengue cases using ensemble ARIMA models

The state of Selangor, in Malaysia consist of urban and peri-urban centres with good transportation system, and suitable temperature levels with high precipitations and humidity which make the state ideal for high number of dengue cases, annually. This study investigates if districts within the Selangor state do influence each other in determining pattern of dengue cases. Study compares two different models; the Autoregressive Integrated Moving Average (ARIMA) and Ensemble ARIMA models, using the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) measurement to gauge their performance tools. ARIMA model is developed using the epidemiological data of dengue cases, whereas ensemble ARIMA incorporates the neighbouring regions' dengue models as the exogenous variable (X), into traditional ARIMA model. Ensemble ARIMA models have better model fit compared to the basic ARIMA models by incorporating neighbuoring effects of seven districts which made of state of Selangor. The AIC and BIC values of ensemble ARIMA models to be smaller compared to traditional ARIMA counterpart models. Thus, study concludes that pattern of dengue cases for a district is subject to spatial effects of its neighbouring districts and number of dengue cases in the surrounding areas.