Mapping dengue risk in Singapore using Random Forest

Spatial model of Dengue Hemorrhagic Fever (DHF) risk: scoping review

BACKGROUND

Creating a spatial model of dengue fever risk is challenging duet to many interrelated factors that could affect dengue. Therefore, it is crucial to understand how these critical factors interact and to create reliable predictive models that can be used to mitigate and control the spread of dengue.

METHODS

This scoping review aims to provide a comprehensive overview of the important predictors, and spatial modelling tools capable of producing Dengue Haemorrhagic Fever (DHF) risk maps. We conducted a methodical exploration utilizing diverse sources, i.e., PubMed, Scopus, Science Direct, and Google Scholar. The following data were extracted from articles published between January 2011 to August 2022: country, region, administrative level, type of scale, spatial model, dengue data use, and categories of predictors. Applying the eligibility criteria, 45 out of 1,349 articles were selected.

RESULTS

A variety of models and techniques were used to identify DHF risk areas with an arrangement of various multiple-criteria decision-making, statistical, and machine learning technique. We found that there was no pattern of predictor use associated with particular approaches. Instead, a wide range of predictors was used to create the DHF risk maps. These predictors may include climatology factors (e.g., temperature, rainfall, humidity), epidemiological factors (population, demographics, socio-economic, previous DHF cases), environmental factors (land-use, elevation), and relevant factors.

CONCLUSIONS

DHF risk spatial models are useful tools for detecting high-risk locations and driving proactive public health initiatives. Relying on geographical and environmental elements, these models ignored the impact of human behaviour and social dynamics. To improve the prediction accuracy, there is a need for a more comprehensive approach to understand DHF transmission dynamics.

A systematic review of the data, methods and environmental covariates used to map Aedes-borne arbovirus transmission risk

BACKGROUND

Aedes (Stegomyia)-borne diseases are an expanding global threat, but gaps in surveillance make comprehensive and comparable risk assessments challenging. Geostatistical models combine data from multiple locations and use links with environmental and socioeconomic factors to make predictive risk maps. Here we systematically review past approaches to map risk for different Aedes-borne arboviruses from local to global scales, identifying differences and similarities in the data types, covariates, and modelling approaches used.

METHODS

We searched on-line databases for predictive risk mapping studies for dengue, Zika, chikungunya, and yellow fever with no geographical or date restrictions. We included studies that needed to parameterise or fit their model to real-world epidemiological data and make predictions to new spatial locations of some measure of population-level risk of viral transmission (e.g. incidence, occurrence, suitability, etc.).

RESULTS

We found a growing number of arbovirus risk mapping studies across all endemic regions and arboviral diseases, with a total of 176 papers published 2002-2022 with the largest increases shortly following major epidemics. Three dominant use cases emerged: (i) global maps to identify limits of transmission, estimate burden and assess impacts of future global change, (ii) regional models used to predict the spread of major epidemics between countries and (iii) national and sub-national models that use local datasets to better understand transmission dynamics to improve outbreak detection and response. Temperature and rainfall were the most popular choice of covariates (included in 50% and 40% of studies respectively) but variables such as human mobility are increasingly being included. Surprisingly, few studies (22%, 31/144) robustly tested combinations of covariates from different domains (e.g. climatic, sociodemographic, ecological, etc.) and only 49% of studies assessed predictive performance via out-of-sample validation procedures.

CONCLUSIONS

Here we show that approaches to map risk for different arboviruses have diversified in response to changing use cases, epidemiology and data availability. We identify key differences in mapping approaches between different arboviral diseases, discuss future research needs and outline specific recommendations for future arbovirus mapping.

Singapore's 5 decades of dengue prevention and control-Implications for global dengue control

This paper summarises the lessons learnt in dengue epidemiology, risk factors, and prevention in Singapore over the last half a century, during which Singapore evolved from a city of 1.9 million people to a highly urban globalised city-state with a population of 5.6 million. Set in a tropical climate, urbanisation among green foliage has created ideal conditions for the proliferation of Aedes aegypti and Aedes albopictus, the mosquito vectors that transmit dengue. A vector control programme, largely for malaria, was initiated as early as 1921, but it was only in 1966 that the Vector Control Unit (VCU) was established to additionally tackle dengue haemorrhagic fever (DHF) that was first documented in the 1960s. Centred on source reduction and public education, and based on research into the bionomics and ecology of the vectors, the programme successfully reduced the Aedes House Index (HI) from 48% in 1966 to <5% in the 1970s. Further enhancement of the programme, including through legislation, suppressed the Aedes HI to around 1% from the 1990s. The current programme is characterised by 4 key features: (i) proactive inter-epidemic surveillance and control that is stepped up during outbreaks; (ii) risk-based prevention and intervention strategies based on advanced data analytics; (iii) coordinated inter-sectoral cooperation between the public, private, and people sectors; and (iv) evidence-based adoption of new tools and strategies. Dengue seroprevalence and force of infection (FOI) among residents have substantially and continuously declined over the 5 decades. This is consistent with the observation that dengue incidence has been delayed to adulthood, with severity highest among the elderly. Paradoxically, the number of reported dengue cases and outbreaks has increased since the 1990s with record-breaking epidemics. We propose that Singapore's increased vulnerability to outbreaks is due to low levels of immunity in the population, constant introduction of new viral variants, expanding urban centres, and increasing human density. The growing magnitude of reported outbreaks could also be attributed to improved diagnostics and surveillance, which at least partially explains the discord between rising trend in cases and the continuous reduction in dengue seroprevalence. Changing global and local landscapes, including climate change, increasing urbanisation and global physical connectivity are expected to make dengue control even more challenging. The adoption of new vector surveillance and control tools, such as the Gravitrap and Wolbachia technology, is important to impede the growing threat of dengue and other Aedes-borne diseases.

Prediction of risk factors for scrub typhus from 2006 to 2019 based on random forest model in Guangzhou, China

OBJECTIVES

Scrub typhus is an increasingly serious public health problem, which is becoming the most common vector-borne disease in Guangzhou. This study aimed to analyse the correlation between scrub typhus incidence and potential factors and rank the importance of influential factors.

METHODS

We collected monthly scrub typhus cases, meteorological variables, rodent density (RD), Normalised Difference Vegetation Index (NDVI), and land use type in Guangzhou from 2006 to 2019. Correlation analysis and a random forest model were used to identify the risk factors for scrub typhus and predict the importance rank of influencing factors related to scrub typhus incidence.

RESULTS

The epidemiological results of the scrub typhus cases in Guangzhou between 2006 and 2019 showed that the incidence rate was on the rise. The results of correlation analysis revealed that a positive relationship between scrub typhus incidence and meteorological factors of mean temperature (T_mean ), accumulative rainfall (RF), relative humidity (RH), sunshine hours (SH), and NDVI, RD, population density, and green land coverage area (all p < 0.001). Additionally, we tested the relationship between the incidence of scrub typhus and the lagging meteorological factors through cross-correlation function, and found that incidence was positively correlated with 1-month lag T_mean , 2-month lag RF, 2-month lag RH, and 6-month lag SH (all p < 0.001). Based on the random forest model, we found that the T_mean was the most important predictor among the influential factors, followed by NDVI.

CONCLUSIONS

Meteorological factors, NDVI, RD, and land use type jointly affect the incidence of scrub typhus in Guangzhou. Our results provide a better understanding of the influential factors correlated with scrub typus, which can improve our capacity for biological monitoring and help public health authorities to formulate disease control strategies.

The Potential of Surveillance Data for Dengue Risk Mapping: An Evaluation of Different Approaches in Cuba

To better guide dengue prevention and control efforts, the use of routinely collected data to develop risk maps is proposed. For this purpose, dengue experts identified indicators representative of entomological, epidemiological and demographic risks, hereafter called components, by using surveillance data aggregated at the level of Consejos Populares (CPs) in two municipalities of Cuba (Santiago de Cuba and Cienfuegos) in the period of 2010-2015. Two vulnerability models (one with equally weighted components and one with data-derived weights using Principal Component Analysis), and three incidence-based risk models were built to construct risk maps. The correlation between the two vulnerability models was high (tau > 0.89). The single-component and multicomponent incidence-based models were also highly correlated (tau ≥ 0.9). However, the agreement between the vulnerability- and the incidence-based risk maps was below 0.6 in the setting with a prolonged history of dengue transmission. This may suggest that an incidence-based approach does not fully reflect the complexity of vulnerability for future transmission. The small difference between single- and multicomponent incidence maps indicates that in a setting with a narrow availability of data, simpler models can be used. Nevertheless, the generalized linear mixed multicomponent model provides information of covariate-adjusted and spatially smoothed relative risks of disease transmission, which can be important for the prospective evaluation of an intervention strategy. In conclusion, caution is needed when interpreting risk maps, as the results vary depending on the importance given to the components involved in disease transmission. The multicomponent vulnerability mapping needs to be prospectively validated based on an intervention trial targeting high-risk areas.

Artificial intelligence in public health: the potential of epidemic early warning systems

The use of artificial intelligence (AI) to generate automated early warnings in epidemic surveillance by harnessing vast open-source data with minimal human intervention has the potential to be both revolutionary and highly sustainable. AI can overcome the challenges faced by weak health systems by detecting epidemic signals much earlier than traditional surveillance. AI-based digital surveillance is an adjunct to-not a replacement of-traditional surveillance and can trigger early investigation, diagnostics and responses at the regional level. This narrative review focuses on the role of AI in epidemic surveillance and summarises several current epidemic intelligence systems including ProMED-mail, HealthMap, Epidemic Intelligence from Open Sources, BlueDot, Metabiota, the Global Biosurveillance Portal, Epitweetr and EPIWATCH. Not all of these systems are AI-based, and some are only accessible to paid users. Most systems have large volumes of unfiltered data; only a few can sort and filter data to provide users with curated intelligence. However, uptake of these systems by public health authorities, who have been slower to embrace AI than their clinical counterparts, is low. The widespread adoption of digital open-source surveillance and AI technology is needed for the prevention of serious epidemics.

A systematic review of published literature on mosquito control action thresholds across the world

BACKGROUND

Despite the use of numerous methods of control measures, mosquito populations and mosquito-borne diseases are still increasing globally. Evidence-based action thresholds to initiate or intensify control activities have been identified as essential in reducing mosquito populations to required levels at the correct/optimal time. This systematic review was conducted to identify different mosquito control action thresholds existing across the world and associated surveillance and implementation characteristics.

METHODOLOGY/PRINCIPAL FINDINGS

Searches for literature published from 2010 up to 2021 were performed using two search engines, Google Scholar and PubMed Central, according to PRISMA guidelines. A set of inclusion/exclusion criteria were identified and of the 1,485 initial selections, only 87 were included in the final review. Thirty inclusions reported originally generated thresholds. Thirteen inclusions were with statistical models that seemed intended to be continuously utilized to test the exceedance of thresholds in a specific region. There was another set of 44 inclusions that solely mentioned previously generated thresholds. The inclusions with "epidemiological thresholds" outnumbered those with "entomological thresholds". Most of the inclusions came from Asia and those thresholds were targeted toward Aedes and dengue control. Overall, mosquito counts (adult and larval) and climatic variables (temperature and rainfall) were the most used parameters in thresholds. The associated surveillance and implementation characteristics of the identified thresholds are discussed here.

CONCLUSIONS/SIGNIFICANCE

The review identified 87 publications with different mosquito control thresholds developed across the world and published during the last decade. Associated surveillance and implementation characteristics will help organize surveillance systems targeting the development and implementation of action thresholds, as well as direct awareness towards already existing thresholds for those with programs lacking available resources for comprehensive surveillance systems. The findings of the review highlight data gaps and areas of focus to fill in the action threshold compartment of the IVM toolbox.

Telehealth utilization in U.S. medicare beneficiaries aged 65 years and older during the COVID-19 pandemic

BACKGROUND

The COVID-19 pandemic has become a serious public health concern for older adults and amplified the value of deploying telehealth solutions. The purpose of this study was to investigate telehealth offered by providers among U.S. Medicare beneficiaries aged 65 years and older during the COVID-19 pandemic.

METHODS

This cross-sectional study analyzed Medicare beneficiaries aged 65 years and older using data from the Medicare Current Beneficiary Survey, Winter 2021 COVID-19 Supplement ([Formula: see text]). We identified variables that were associated with telehealth offered by primary care physicians and beneficiaries' access to the Internet through a multivariate classification analysis utilizing Random Forest machine learning techniques.

FINDINGS

For study participants interviewed by telephone, 81.06% of primary care providers provided telehealth services, and 84.62% of the Medicare beneficiaries had access to the Internet. The survey response rates for each outcome were 74.86% and 99.55% respectively. The two outcomes were positively correlated ([Formula: see text]). The Our machine learning model predicted the outcomes accurately utilizing 44 variables. Residing area and race/ethnicity were most informative for predicting telehealth coverage, and Medicare-Medicaid dual eligibility and income were most informative for predicting Internet access. Other strong correlates included age, ability to access basic needs and certain mental and physical health conditions. Interactions were found among statuses of residing area, age, Medicare Advantage and heart conditions that intensified the disparity of outcomes.

CONCLUSIONS

We found that telehealth offered by providers likely increased during the COVID-19 pandemic for older beneficiaries, providing important access to care for certain subgroups. Policymakers must continue to identify effective means of delivering telehealth services, modernize the framework of regulatory, accreditation and reimbursement, and address disparities in access to telehealth with a particular focus on underserved communities.

Weather integrated multiple machine learning models for prediction of dengue prevalence in India

Dengue is a rapidly spreading viral disease transmitted to humans by Aedes mosquitoes. Due to global urbanization and climate change, the number of dengue cases are gradually increasing in recent decades. Hence, an early prediction of dengue continues to be a major concern for public health in countries with high prevalence of dengue. Creating a robust forecast model for the accurate prediction of dengue is a complex task and can be done through various data modelling approaches. In the present study, we have applied vector auto regression, generalized boosted models, support vector regression, and long short-term memory (LSTM) to predict the dengue prevalence in Kerala state of the Indian subcontinent. We consider the number of dengue cases as the target variable and weather variables viz., relative humidity, soil moisture, mean temperature, precipitation, and NINO3.4 as independent variables. Various analytical models have been applied on both datasets and predicted the dengue cases. Among all the models, the LSTM model was outperformed with superior prediction capability (RMSE: 0.345 and R²:0.86) than the other models. However, other models are able to capture the trend of dengue cases but failed in predicting the outbreak periods when compared to LSTM. The findings of this study will be helpful for public health agencies and policymakers to draw appropriate control measures before the onset of dengue. The proposed LSTM model for dengue prediction can be followed by other states of India as well.

Application of big data and artificial intelligence in epidemic surveillance and containment

Faced with the current time-sensitive COVID-19 pandemic, the overburdened healthcare systems have resulted in a strong demand to develop newer methods to control the spread of the pandemic. Big data and artificial intelligence (AI) have been leveraged amid the COVID-19 pandemic; however, little is known about their use for supporting public health efforts. In epidemic surveillance and containment, efforts are needed to treat critical patients, track and manage the health status of residents, isolate suspected cases, and develop vaccines and antiviral drugs. The applications of emerging practices of artificial intelligence and big data have become powerful "weapons" to fight against the pandemic and provide strong support in pandemic prevention and control, such as early warning, analysis and judgment, interruption and intervention of epidemic, to achieve goals of early detection, early report, early diagnosis, early isolation and early treatment. These are the decisive factors to control the spread of the epidemic and reduce the mortality. This paper systematically summarized the application of big data and AI in epidemic, and describes practical cases and challenges with emphasis on epidemic prevention and control. The included studies showed that big data and AI have the potential strength to fight against COVID-19. However, many of the proposed methods are not yet widely accepted. Thus, the most rewarding research would be on methods that promise value beyond COVID-19. More efforts are needed for developing standardized reporting protocols or guidelines for practice.

Predicting the distribution of COVID-19 through CGAN-Taking Macau as an example

Machine learning (ML) is an innovative method that is widely used in data prediction. Predicting the COVID-19 distribution using ML is essential for urban security risk assessment and governance. This study uses conditional generative adversarial network (CGAN) to construct a method to predict the COVID-19 hotspot distribution through urban texture and business formats and establishes a relationship between urban elements and COVID-19 so that machines can automatically predict the epidemic hotspots in cities. Taking Macau as an example, this method is used to determine the correlation between the urban texture and business hotspots of Macau and the new epidemic hotspot clusters. Different types of samples afforded different epidemic prediction accuracies. The results show the following: (1) CGAN can accurately predict the distribution area of COVID-19, and the accuracy can exceed 70%. (2) The results of predicting the COVID-19 distribution through urban texture and POI data of hospitals and stations are the best, with an accuracy of more than 60% in experiments in different regions of Macau. (3) The proposed method can also predict other areas in the city that may be at risk of COVID-19 and help urban epidemic prevention and control.

Using machine learning to understand microgeographic determinants of the Zika vector, Aedes aegypti

There are limited data on why the 2016 Zika outbreak in Miami-Dade County, Florida was confined to certain neighborhoods. In this research, Aedes aegypti, the primary vector of Zika virus, are studied to examine neighborhood-level differences in their population dynamics and underlying processes. Weekly mosquito data were acquired from the Miami-Dade County Mosquito Control Division from 2016 to 2020 from 172 traps deployed around Miami-Dade County. Using random forest, a machine learning method, predictive models of spatiotemporal dynamics of Ae. aegypti in response to meteorological conditions and neighborhood-specific socio-demographic and physical characteristics, such as land-use and land-cover type and income level, were created. The study area was divided into two groups: areas affected by local transmission of Zika during the 2016 outbreak and unaffected areas. Ae. aegypti populations in areas affected by Zika were more strongly influenced by 14- and 21-day lagged weather conditions. In the unaffected areas, mosquito populations were more strongly influenced by land-use and day-of-collection weather conditions. There are neighborhood-scale differences in Ae. aegypti population dynamics. These differences in turn influence vector-borne disease diffusion in a region. These results have implications for vector control experts to lead neighborhood-specific vector control strategies and for epidemiologists to guide vector-borne disease risk preparations, especially for containing the spread of vector-borne disease in response to ongoing climate change.

Assessing the efficacy of male Wolbachia-infected mosquito deployments to reduce dengue incidence in Singapore: study protocol for a cluster-randomized controlled trial

BACKGROUND

Dengue is a severe environmental public health challenge in tropical and subtropical regions. In Singapore, decreasing seroprevalence and herd immunity due to successful vector control has paradoxically led to increased transmission potential of the dengue virus. We have previously demonstrated that incompatible insect technique coupled with sterile insect technique (IIT-SIT), which involves the release of X-ray-irradiated male Wolbachia-infected mosquitoes, reduced the Aedes aegypti population by 98% and dengue incidence by 88%. This novel vector control tool is expected to be able to complement current vector control to mitigate the increasing threat of dengue on a larger scale. We propose a multi-site protocol to study the efficacy of IIT-SIT at reducing dengue incidence.

METHODS/DESIGN

The study is designed as a parallel, two-arm, non-blinded cluster-randomized (CR) controlled trial to be conducted in high-rise public housing estates in Singapore, an equatorial city-state. The aim is to determine whether large-scale deployment of male Wolbachia-infected Ae. aegypti mosquitoes can significantly reduce dengue incidence in intervention clusters. We will use the CR design, with the study area comprising 15 clusters with a total area of 10.9 km², covering approximately 722,204 residents in 1713 apartment blocks. Eight clusters will be randomly selected to receive the intervention, while the other seven will serve as non-intervention clusters. Intervention efficacy will be estimated through two primary endpoints: (1) odds ratio of Wolbachia exposure distribution (i.e., probability of living in an intervention cluster) among laboratory-confirmed reported dengue cases compared to test-negative controls and (2) laboratory-confirmed reported dengue counts normalized by population size in intervention versus non-intervention clusters.

DISCUSSION

This study will provide evidence from a multi-site, randomized controlled trial for the efficacy of IIT-SIT in reducing dengue incidence. The trial will provide valuable information to estimate intervention efficacy for this novel vector control approach and guide plans for integration into national vector control programs in dengue-endemic settings.

TRIAL REGISTRATION

ClinicalTrials.gov, identifier: NCT05505682 . Registered on 16 August 2022. Retrospectively registered.

A Systematic Review on Modeling Methods and Influential Factors for Mapping Dengue-Related Risk in Urban Settings

Dengue fever is an acute mosquito-borne disease that mostly spreads within urban or semi-urban areas in warm climate zones. The dengue-related risk map is one of the most practical tools for executing effective control policies, breaking the transmission chain, and preventing disease outbreaks. Mapping risk at a small scale, such as at an urban level, can demonstrate the spatial heterogeneities in complicated built environments. This review aims to summarize state-of-the-art modeling methods and influential factors in mapping dengue fever risk in urban settings. Data were manually extracted from five major academic search databases following a set of querying and selection criteria, and a total of 28 studies were analyzed. Twenty of the selected papers investigated the spatial pattern of dengue risk by epidemic data, whereas the remaining eight papers developed an entomological risk map as a proxy for potential dengue burden in cities or agglomerated urban regions. The key findings included: (1) Big data sources and emerging data-mining techniques are innovatively employed for detecting hot spots of dengue-related burden in the urban context; (2) Bayesian approaches and machine learning algorithms have become more popular as spatial modeling tools for predicting the distribution of dengue incidence and mosquito presence; (3) Climatic and built environmental variables are the most common factors in making predictions, though the effects of these factors vary with the mosquito species; (4) Socio-economic data may be a better representation of the huge heterogeneity of risk or vulnerability spatial distribution on an urban scale. In conclusion, for spatially assessing dengue-related risk in an urban context, data availability and the purpose for mapping determine the analytical approaches and modeling methods used. To enhance the reliabilities of predictive models, sufficient data about dengue serotyping, socio-economic status, and spatial connectivity may be more important for mapping dengue-related risk in urban settings for future studies.

Access to care through telehealth among U.S. Medicare beneficiaries in the wake of the COVID-19 pandemic

Background

The coronavirus disease 2019 (COVID-19) public health emergency has amplified the potential value of deploying telehealth solutions. Less is known about how trends in access to care through telehealth changed over time.

Objectives

To investigate trends in forgone care and telehealth coverage among Medicare beneficiaries during the COVID-19 pandemic.

Methods

A cross-sectional study design was used to analyze the outcomes of 31,907 Medicare beneficiaries using data from three waves of survey data from the Medicare Current Beneficiary Survey COVID-19 Supplement (Summer 2020, Fall 2020, and Winter 2021). We identified informative variables through a multivariate classification analysis utilizing Random Forest machine learning techniques.

Findings

The rate of reported forgone medical care because of COVID-19 decreased largely (22.89-3.31%) with a small increase in telehealth coverage (56.24-61.84%) from the week of June 7, 2020, to the week of April 4 to 25, 2021. Overall, there were 21.97% of respondents did not know whether their primary care providers offered telehealth services; the rates of forgone care and telehealth coverage were 11.68 and 59.52% (11.73 and 81.18% from yes and no responses). Our machine learning model predicted the outcomes accurately utilizing 43 variables. Informative factors included Medicare beneficiaries' age, Medicare-Medicaid dual eligibility, ability to access basic needs, certain mental and physical health conditions, and interview date.

Conclusions

This cross-sectional survey study found proliferation and utilization of telehealth services in certain subgroups during the COVID-19 pandemic, providing important access to care. There is a need to confront traditional barriers to the proliferation of telehealth. Policymakers must continue to identify effective means of maintaining continuity of care and growth of telehealth services.

The practicality of Malaysia dengue outbreak forecasting model as an early warning system

Dengue is a harmful tropical disease that causes death to many people. Currently, the dengue vaccine development is still at an early stage, and only intervention methods exist after dengue cases increase. Thus, previously, two scientific experimental field studies were conducted in producing a dengue outbreak forecasting model as an early warning system. Successfully, an Autoregressive Distributed Lag (ADL) Model was developed using three factors: the epidemiological, entomological, and environmental with an accuracy of 85%; but a higher percentage is required in minimizing the error for the model to be useful. Hence, this study aimed to develop a practical and cost-effective dengue outbreak forecasting model with at least 90% accuracy to be embedded in an early warning computer system using the Internet of Things (IoT) approach. Eighty-one weeks of time series data of the three factors were used in six forecasting models, which were Autoregressive Distributed Lag (ADL), Hierarchical Forecasting (Bottom-up and Optimal combination) and three Machine Learning methods: (Artificial Neural Network (ANN), Support Vector Machine (SVM) and Random Forest). Five error measures were used to evaluate the consistency performance of the models in order to ensure model performance. The findings indicated Random Forest outperformed the other models with an accuracy of 95% when including all three factors. But practically, collecting mosquito related data (the entomological factor) was very costly and time consuming. Thus, it was removed from the model, and the accuracy dropped to 92% but still high enough to be of practical use, i.e., beyond 90%. However, the practical ground operationalization of the early warning system also requires several rain gauges to be located at the dengue hot spots due to localized rainfall. Hence, further analysis was conducted in determining the location of the rain gauges. This has led to the recommendation that the rain gauges should be located about 3–4 km apart at the dengue hot spots to ensure the accuracy of the rainfall data to be included in the dengue outbreak forecasting model so that it can be embedded in the early warning system. Therefore, this early warning system can save lives, and prevention is better than cure.

Recurrent Neural Networks for Feature Extraction from Dengue Fever

Dengue fever modelling in endemic locations is critical to reducing outbreaks and improving vector-borne illness control. Early projections of dengue are a crucial tool for disease control because of the unavailability of treatments and universal vaccination. Neural networks have made significant contributions to public health in a variety of ways. In this paper, we develop a deep learning modelling using random forest (RF) that helps extract the features of the dengue fever from the text datasets. The proposed modelling involves the data collection, preprocessing of the input texts, and feature extraction. The extracted features are studied to test how well the feature extraction using RF is effective on dengue datasets. The simulation result shows that the proposed method achieves higher degree of accuracy that offers an improvement of more than 12% than the existing methods in extracting the features from the input datasets than the other feature extraction methods. Further, the study reduces the errors associated with feature extraction that is 10% lesser than the other existing methods, and this shows the efficacy of the model.

Temporal Correlation Between Urban Microclimate, Vector Mosquito Abundance, and Dengue Cases

Dengue Hemorrhagic Fever (DHF) is a major mosquito-borne viral disease. Studies have reported a strong correlation between weather, the abundance of Aedes aegypti, the vector of DHF virus, and dengue incidence. However, this conclusion has been based on the general climate pattern of wide regions. In general, however, the human population, level of infrastructure, and land-use change in rural and urban areas often produce localized climate patterns that may influence the interaction between climate, vector abundance, and dengue incidence. Thoroughly understanding this correlation will allow the development of a customized and precise local early warning system. To achieve this purpose, we conducted a cohort study, during January-December 2017, in 16 districts in Bandung, West Java, Indonesia. In the selected areas, local weather stations and modified light mosquito traps were set up to obtain data regarding daily weather and the abundance of adult female Ae. aegypti. A generalized linear model was applied to analyze the effect of local weather and female adult Ae. aegypti on the number of dengue cases. The result showed a significant non-linear correlation among mosquito abundance, maximum temperature, and dengue cases. Using our model, the data showed that the addition of a single adult Ae. aegypti mosquito increased the risk of dengue infection by 1.8%, while increasing the maximum temperature by one degree decreased the risk by 17%. This finding suggests specific actionable insights needed to supplement existing mosquito eradication programs.

Data-driven computational intelligence applied to dengue outbreak forecasting: a case study at the scale of the city of Natal, RN-Brazil

Dengue is recognized as a health problem that causes significant socioeconomic impacts throughout the world, affecting millions of people each year. A commonly used method for monitoring the dengue vector is to count the eggs that Aedes aegypti mosquitoes have laid in spatially distributed ovitraps. Given this approach, the present study uses a database collected from 397 ovitraps allocated across the city of Natal, RN—Brazil. The Egg Density Index for each neighborhood was computed weekly, over four complete years (from 2016 to 2019), and simultaneously analyzed with the dengue case incidence. Our results illustrate that the incidence of dengue is related to the socioeconomic level of the neighborhoods in the city of Natal. A deep learning algorithm was used to predict future dengue case incidence, either based on the previous weeks of dengue incidence or the number of eggs present in the ovitraps. The analysis reveals that ovitrap data allows earlier prediction (four to six weeks) compared to dengue incidence itself (one week). Therefore, the results validate that the quantification of Aedes aegypti eggs can be valuable for the early planning of public health interventions.

A Comparison of Infectious Disease Forecasting Methods across Locations, Diseases, and Time

Accurate infectious disease forecasting can inform efforts to prevent outbreaks and mitigate adverse impacts. This study compares the performance of statistical, machine learning (ML), and deep learning (DL) approaches in forecasting infectious disease incidences across different countries and time intervals. We forecasted three diverse diseases: campylobacteriosis, typhoid, and Q-fever, using a wide variety of features (n = 46) from public datasets, e.g., landscape, climate, and socioeconomic factors. We compared autoregressive statistical models to two tree-based ML models (extreme gradient boosted trees [XGB] and random forest [RF]) and two DL models (multi-layer perceptron and encoder–decoder model). The disease models were trained on data from seven different countries at the region-level between 2009–2017. Forecasting performance of all models was assessed using mean absolute error, root mean square error, and Poisson deviance across Australia, Israel, and the United States for the months of January through August of 2018. The overall model results were compared across diseases as well as various data splits, including country, regions with highest and lowest cases, and the forecasted months out (i.e., nowcasting, short-term, and long-term forecasting). Overall, the XGB models performed the best for all diseases and, in general, tree-based ML models performed the best when looking at data splits. There were a few instances where the statistical or DL models had minutely smaller error metrics for specific subsets of typhoid, which is a disease with very low case counts. Feature importance per disease was measured by using four tree-based ML models (i.e., XGB and RF with and without region name as a feature). The most important feature groups included previous case counts, region name, population counts and density, mortality causes of neonatal to under 5 years of age, sanitation factors, and elevation. This study demonstrates the power of ML approaches to incorporate a wide range of factors to forecast various diseases, regardless of location, more accurately than traditional statistical approaches.

Analysis and prediction of hand, foot and mouth disease incidence in China using Random Forest and XGBoost

Hand, foot and mouth disease (HFMD) is an increasingly serious public health problem, and it has caused an outbreak in China every year since 2008. Predicting the incidence of HFMD and analyzing its influential factors are of great significance to its prevention. Now, machine learning has shown advantages in infectious disease models, but there are few studies on HFMD incidence based on machine learning that cover all the provinces in mainland China. In this study, we proposed two different machine learning algorithms, Random Forest and eXtreme Gradient Boosting (XGBoost), to perform our analysis and prediction. We first used Random Forest to examine the association between HFMD incidence and potential influential factors for 31 provinces in mainland China. Next, we established Random Forest and XGBoost prediction models using meteorological and social factors as the predictors. Finally, we applied our prediction models in four different regions of mainland China and evaluated the performance of them. Our results show that: 1) Meteorological factors and social factors jointly affect the incidence of HFMD in mainland China. Average temperature and population density are the two most significant influential factors; 2) Population flux has different delayed effect in affecting HFMD incidence in different regions. From a national perspective, the model using population flux data delayed for one month has better prediction performance; 3) The prediction capability of XGBoost model was better than that of Random Forest model from the overall perspective. XGBoost model is more suitable for predicting the incidence of HFMD in mainland China.

Spatiotemporal epidemiology and forecasting of dengue in the state of Punjab, India: Study protocol

Dengue burden in India is a major public health problem. The present study has been designed to understand mechanisms by which routine data generate evidence. Secondary data analysis of routine datasets to understand spatiotemporal epidemiology and forecast dengue will be conducted. Data science approach will be adopted to generate a reproducible framework in the R environment. The lab-confirmed dengue reported by the state health authorities from 01 January 2015 to 31 December 2019 will be included. Multiple climatic variables from satellite imagery, climatic models, vegetation and built-up indices, and sociodemographic variables will be explored as risk factors. Exploratory data analysis followed by statistical analysis and machine learning will be performed. Data analysis will include geospatial information analysis, time series analysis, and spatiotemporal analysis. The study will provide value addition to the existing disease surveillance mechanisms by developing a framework for incorporating multiple routine data sources available in the country.

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

BACKGROUND

Dengue is an endemic vector-borne disease influenced by environmental factors such as landscape and climate. Previous studies separately assessed the effects of landscape and climate factors on mosquito occurrence and dengue incidence. However, both factors concurrently coexist in time and space and can interact, affecting mosquito development and dengue disease transmission. For example, eggs laid in a suitable environment can hatch after being submerged in rain water. It has been difficult for conventional statistical modeling approaches to demonstrate these combined influences due to mathematical constraints.

OBJECTIVES

To investigate the combined influences of landscape and climate factors on mosquito occurrence and dengue incidence.

METHODS

Entomological, epidemiological, and landscape data from the rainy season (July-December) were obtained from respective government agencies in Metropolitan Manila, Philippines, from 2012 to 2014. Temperature, precipitation and vegetation data were obtained through remote sensing. A random forest algorithm was used to select the landscape and climate variables. Afterward, using the identified key variables, a model-based (MOB) recursive partitioning was implemented to test the combined influences of landscape and climate factors on ovitrap index (vector mosquito occurrence) and dengue incidence.

RESULTS

The MOB recursive partitioning for ovitrap index indicated a high sensitivity of vector mosquito occurrence on environmental conditions generated by a combination of high residential density areas with low precipitation. Moreover, the MOB recursive partitioning indicated high sensitivity of dengue incidence to the effects of precipitation in areas with high proportions of residential density and commercial areas.

CONCLUSIONS

Dengue dynamics are not solely influenced by individual effects of either climate or landscape, but rather by their synergistic or combined effects. The presented findings have the potential to target vector surveillance in areas identified as suitable for mosquito occurrence under specific climatic conditions and may be relevant as part of urban planning strategies to control dengue.

The role of urbanisation in the spread of Aedes mosquitoes and the diseases they transmit-A systematic review

Background

This systematic review aims to assess how different urbanisation patterns related to rapid urban growth, unplanned expansion, and human population density affect the establishment and distribution of Aedes aegypti and Aedes albopictus and create favourable conditions for the spread of dengue, chikungunya, and Zika viruses.

Methods and findings

Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a systematic review was conducted using the PubMed, Virtual Health Library, Cochrane, WHO Library Database (WHOLIS), Google Scholar, and and the Institutional Repository for Information Sharing (IRIS) databases. From a total of 523 identified studies, 86 were selected for further analysis, and 29 were finally analysed after applying all inclusion and exclusion criteria. The main explanatory variables used to associate urbanisation with epidemiological/entomological outcomes were the following: human population density, urban growth, artificial geographical space, urban construction, and urban density. Associated with the lack of a global definition of urbanisation, several studies provided their own definitions, which represents one of the study’s limitations. Results were based on 8 ecological studies/models, 8 entomological surveillance studies, 7 epidemiological surveillance studies, and 6 studies consisting of spatial and predictive models. According to their focus, studies were categorised into 2 main subgroups, namely “Aedes ecology” and “transmission dynamics.” There was a consistent association between urbanisation and the distribution and density of Aedes mosquitoes in 14 of the studies and a strong relationship between vector abundance and disease transmission in 18 studies. Human population density of more than 1,000 inhabitants per square kilometer was associated with increased levels of arboviral diseases in 15 of the studies.

Conclusions

The use of different methods in the included studies highlights the interplay of multiple factors linking urbanisation with ecological, entomological, and epidemiological parameters and the need to consider a variety of these factors for designing effective public health approaches.

The expansion of urbanisation is often associated with the emergence and spread of vector-borne diseases by creating favourable conditions for the survival of Aedes species and the spread of dengue, chikungunya, and Zika viruses. This systematic review examined the relationship of urbanisation to the emergence and spread of Aedes mosquito–borne diseases and epidemics. From a total of 523 identified studies, 29 were included in the analysis. Studies were categorised into 2 main subgroups, namely “Aedes ecology” and “transmission dynamics” according to the main influence factors posed by urbanisation. Selected articles showed a clear relationship of urbanisation with distribution and density of Aedes mosquitoes and a robust association between vector production, human population density, and disease transmission. Differing definitions of ’urbanisation’ and the interplay of numerous factors linking urbanisation with ecological, entomological, and epidemiological parameters highlight the need for a multidimensional perspective when assessing the impacts of rapid and unplanned urban expansion and when designing effective control programmes.

A novel approach to modeling epidemic vulnerability, applied to Aedes aegypti-vectored diseases in Perú

Background

A proactive approach to preventing and responding to emerging infectious diseases is critical to global health security. We present a three-stage approach to modeling the spatial distribution of outbreak vulnerability to Aedes aegypti-vectored diseases in Perú.

Methods

Extending a framework developed for modeling hemorrhagic fever vulnerability in Africa, we modeled outbreak vulnerability in three stages: index case potential (stage 1), outbreak receptivity (stage 2), and epidemic potential (stage 3), stratifying scores on season and El Niño events. Subsequently, we evaluated the validity of these scores using dengue surveillance data and spatial models.

Results

We found high validity for stage 1 and 2 scores, but not stage 3 scores. Vulnerability was highest in Selva Baja and Costa, and in summer and during El Niño events, with index case potential (stage 1) being high in both regions but outbreak receptivity (stage 2) being generally high in Selva Baja only.

Conclusions

Stage 1 and 2 scores are well-suited to predicting outbreaks of Ae. aegypti-vectored diseases in this setting, however stage 3 scores appear better suited to diseases with direct human-to-human transmission. To prevent outbreaks, measures to detect index cases should be targeted to both Selva Baja and Costa, while Selva Baja should be prioritized for healthcare system strengthening. Successful extension of this framework from hemorrhagic fevers in Africa to an arbovirus in Latin America indicates its broad utility for outbreak and pandemic preparedness and response activities.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12879-021-06530-9.

Case-area targeted interventions (CATI) for reactive dengue control: Modelling effectiveness of vector control and prophylactic drugs in Singapore

BACKGROUND

Targeting interventions to areas that have recently experienced cases of disease is one strategy to contain outbreaks of infectious disease. Such case-area targeted interventions (CATI) have become an increasingly popular approach for dengue control but there is little evidence to suggest how precisely targeted or how recent cases need to be, to mount an effective response. The growing interest in the development of prophylactic and therapeutic drugs for dengue has also given new relevance for CATI strategies to interrupt transmission or deliver early treatment.

METHODS/PRINCIPAL FINDINGS

Here we develop a patch-based mathematical model of spatial dengue spread and fit it to spatiotemporal datasets from Singapore. Simulations from this model suggest CATI strategies could be effective, particularly if used in lower density areas. To maximise effectiveness, increasing the size of the radius around an index case should be prioritised even if it results in delays in the intervention being applied. This is partially because large intervention radii ensure individuals receive multiple and regular rounds of drug dosing or vector control, and thus boost overall coverage. Given equivalent efficacy, CATIs using prophylactic drugs are predicted to be more effective than adult mosquito-killing vector control methods and may even offer the possibility of interrupting individual chains of transmission if rapidly deployed. CATI strategies quickly lose their effectiveness if baseline transmission increases or case detection rates fall.

CONCLUSIONS/SIGNIFICANCE

These results suggest CATI strategies can play an important role in dengue control but are likely to be most relevant for low transmission areas where high coverage of other non-reactive interventions already exists. Controlled field trials are needed to assess the field efficacy and practical constraints of large operational CATI strategies.

Interactions between staphylococcal enterotoxins A and D and superantigen-like proteins 1 and 5 for predicting methicillin and multidrug resistance profiles among Staphylococcus aureus ocular isolates

BACKGROUND

Methicillin-resistant Staphylococcus aureus (MRSA) and multidrug-resistant (MDR) S. aureus strains are well recognized as posing substantial problems in treating ocular infections. S. aureus has a vast array of virulence factors, including superantigens and enterotoxins. Their interactions and ability to signal antibiotics resistance have not been explored.

OBJECTIVES

To predict the relationship between superantigens and methicillin and multidrug resistance among S. aureus ocular isolates.

METHODS

We used a DNA microarray to characterize the enterotoxin and superantigen gene profiles of 98 S. aureus isolates collected from common ocular sources. The outcomes contained phenotypic and genotypic expressions of MRSA. We also included the MDR status as an outcome, categorized as resistance to three or more drugs, including oxacillin, penicillin, erythromycin, clindamycin, moxifloxacin, tetracycline, trimethoprim-sulfamethoxazole and gentamicin. We identified gene profiles that predicted each outcome through a classification analysis utilizing Random Forest machine learning techniques.

FINDINGS

Our machine learning models predicted the outcomes accurately utilizing 67 enterotoxin and superantigen genes. Strong correlates predicting the genotypic expression of MRSA were enterotoxins A, D, J and R and superantigen-like proteins 1, 3, 7 and 10. Among these virulence factors, enterotoxin D and superantigen-like proteins 1, 5 and 10 were also significantly informative for predicting both MDR and MRSA in terms of phenotypic expression. Strong interactions were identified including enterotoxins A (entA) interacting with superantigen-like protein 1 (set6-var1_11), and enterotoxin D (entD) interacting with superantigen-like protein 5 (ssl05/set3_probe 1): MRSA and MDR S. aureus are associated with the presence of both entA and set6-var1_11, or both entD and ssl05/set3_probe 1, while the absence of these genes in pairs indicates non-multidrug-resistant and methicillin-susceptible S. aureus.

CONCLUSIONS

MRSA and MDR S. aureus show a different spectrum of ocular pathology than their non-resistant counterparts. When assessing the role of enterotoxins in predicting antibiotics resistance, it is critical to consider both main effects and interactions.

Novel statistical approaches to identify risk factors for soil-transmitted helminth infection in Timor-Leste

•

We compared logistic regression, recursive partitioning and Bayesian networks to identify risk factors for STH infection.

•

Logistic regression identified fewest variables associated with STH infections compared with the two alternative methods.

•

Recursive partitioning identified more demographic and WASH variables, and Bayesian networks more environmental variables.

•

Model performance was similar across all three statistical techniques.

•

Recursive partitioning can identify at-risk population subgroups, while Bayesian networks can run real-time scenarios.

Soil-transmitted helminths (STHs) are parasitic intestinal worms that infect almost a fifth of the global population. Sustainable control of STHs requires understanding the complex interaction of factors contributing to transmission. Identifying risk factors has mainly relied on logistic regression models where the underlying assumption of independence between variables is not always satisfied. Previously demonstrated risk factors including water, sanitation and hygiene (WASH) access and behaviours, and socioeconomic status are intrinsically linked. Similarly, environmental factors including climate, soil and land attributes are often strongly correlated. Alternative methods such as recursive partitioning and Bayesian networks can handle correlated variables, but there are no published studies comparing these methods with logistic regression in the context of STH risk factor analysis. Baseline cross-sectional data from school-aged children in the (S)WASH-D for Worms study were used to compare risk factors identified from modelling the same data using three different statistical techniques. Outcomes of interest were infection with Ascaris spp. and any hookworm species (Necator americanus, Ancylostoma duodenale, and Ancylostoma ceylanicum). Mixed-effects logistic regression identified the fewest risk factors. Recursive partitioning identified the most WASH and demographic risk factors, while Bayesian networks identified the most environmental risk factors. Recursive partitioning produced classification trees that visualised potentially at-risk population sub-groups. Bayesian networks helped visualise relationships between variables and enabled interactive modelling of outcomes based on different scenarios for the predictor variables of interest. Model performance was similar across all techniques. Risk factors identified across all techniques were vegetation for Ascaris spp., and cleaning oneself with water after defecating for hookworm. This study adds to the limited body of evidence exploring alternative data modelling approaches in identifying risk factors for STH infections. Our findings suggest these approaches can provide novel insights for more robust interpretation.

Added-value of mosquito vector breeding sites from street view images in the risk mapping of dengue incidence in Thailand

Dengue is an emerging vector-borne viral disease across the world. The primary dengue mosquito vectors breed in containers with sufficient water and nutrition. Outdoor containers can be detected from geotagged images using state-of-the-art deep learning methods. In this study, we utilize such container information from street view images in developing a risk mapping model and determine the added value of including container information in predicting dengue risk. We developed seasonal-spatial models in which the target variable dengue incidence was explained using weather and container variable predictors. Linear mixed models with fixed and random effects are employed in our models to account for different characteristics of containers and weather variables. Using data from three provinces of Thailand between 2015 and 2018, the models are developed at the sub-district level resolution to facilitate the development of effective targeted intervention strategies. The performance of the models is evaluated with two baseline models: a classic linear model and a linear mixed model without container information. The performance evaluated with the correlation coefficients, R-squared, and AIC shows the proposed model with the container information outperforms both baseline models in all three provinces. Through sensitivity analysis, we investigate the containers that have a high impact on dengue risk. Our findings indicate that outdoor containers identified from street view images can be a useful data source in building effective dengue risk models and that the resulting models have potential in helping to target container elimination interventions.

Cholera Risk: A Machine Learning Approach Applied to Essential Climate Variables

Oceanic and coastal ecosystems have undergone complex environmental changes in recent years, amid a context of climate change. These changes are also reflected in the dynamics of water-borne diseases as some of the causative agents of these illnesses are ubiquitous in the aquatic environment and their survival rates are impacted by changes in climatic conditions. Previous studies have established strong relationships between essential climate variables and the coastal distribution and seasonal dynamics of the bacteria Vibrio cholerae, pathogenic types of which are responsible for human cholera disease. In this study we provide a novel exploration of the potential of a machine learning approach to forecast environmental cholera risk in coastal India, home to more than 200 million inhabitants, utilising atmospheric, terrestrial and oceanic satellite-derived essential climate variables. A Random Forest classifier model is developed, trained and tested on a cholera outbreak dataset over the period 2010–2018 for districts along coastal India. The random forest classifier model has an Accuracy of 0.99, an F1 Score of 0.942 and a Sensitivity score of 0.895, meaning that 89.5% of outbreaks are correctly identified. Spatio-temporal patterns emerged in terms of the model’s performance based on seasons and coastal locations. Further analysis of the specific contribution of each Essential Climate Variable to the model outputs shows that chlorophyll-a concentration, sea surface salinity and land surface temperature are the strongest predictors of the cholera outbreaks in the dataset used. The study reveals promising potential of the use of random forest classifiers and remotely-sensed essential climate variables for the development of environmental cholera-risk applications. Further exploration of the present random forest model and associated essential climate variables is encouraged on cholera surveillance datasets in other coastal areas affected by the disease to determine the model’s transferability potential and applicative value for cholera forecasting systems.

Impact of sars-cov-2 interventions on dengue transmission

An estimated 105 million dengue infections occur per year across 120 countries, where traditional vector control is the primary control strategy to reduce contact between mosquito vectors and people. The ongoing sars-cov-2 pandemic has resulted in dramatic reductions in human mobility due to social distancing measures; the effects on vector-borne illnesses are not known. Here we examine the pre and post differences of dengue case counts in Malaysia, Singapore and Thailand, and estimate the effects of social distancing as a treatment effect whilst adjusting for temporal confounders. We found that social distancing is expected to lead to 4.32 additional cases per 100,000 individuals in Thailand per month, which equates to 170 more cases per month in the Bangkok province (95% CI: 100-242) and 2008 cases in the country as a whole (95% CI: 1170-2846). Social distancing policy estimates for Thailand were also found to be robust to model misspecification, and variable addition and omission. Conversely, no significant impact on dengue transmission was found in Singapore or Malaysia. Across country disparities in social distancing policy effects on reported dengue cases are reasoned to be driven by differences in workplace-residence structure, with an increase in transmission risk of arboviruses from social distancing primarily through heightened exposure to vectors in elevated time spent at residences, demonstrating the need to understand the effects of location on dengue transmission risk under novel population mixing conditions such as those under social distancing policies.

Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia

The robust estimate and forecast capability of random forests (RF) has been widely recognized, however this ensemble machine learning method has not been widely used in mosquito-borne disease forecasting. In this study, two sets of RF models were developed at the national (pooled department-level data) and department level in Colombia to predict weekly dengue cases for 12-weeks ahead. A pooled national model based on artificial neural networks (ANN) was also developed and used as a comparator to the RF models. The various predictors included historic dengue cases, satellite-derived estimates for vegetation, precipitation, and air temperature, as well as population counts, income inequality, and education. Our RF model trained on the pooled national data was more accurate for department-specific weekly dengue cases estimation compared to a local model trained only on the department's data. Additionally, the forecast errors of the national RF model were smaller to those of the national pooled ANN model and were increased with the forecast horizon increasing from one-week-ahead (mean absolute error, MAE: 9.32) to 12-weeks ahead (MAE: 24.56). There was considerable variation in the relative importance of predictors dependent on forecast horizon. The environmental and meteorological predictors were relatively important for short-term dengue forecast horizons while socio-demographic predictors were relevant for longer-term forecast horizons. This study demonstrates the potential of RF in dengue forecasting with a feasible approach of using a national pooled model to forecast at finer spatial scales. Furthermore, including sociodemographic predictors is likely to be helpful in capturing longer-term dengue trends.

A greener vision for vector control: The example of the Singapore dengue control programme

Vector-borne diseases are a major cause of morbidity and mortality worldwide. Aedes-borne diseases, in particular, including dengue, chikungunya, yellow fever, and Zika, are increasing at an alarming rate due to urbanisation, population movement, weak vector control programmes, and climate change. The World Health Organization calls for strengthening of vector control programmes in line with the Global Vector Control Response (GVCR) strategy, and many vector control programmes are transitioning to this new approach. The Singapore dengue control programme, situated within the country’s larger vision of a clean, green, and sustainable environment for the health and well-being of its citizens, provides an excellent example of the GVCR approach in action. Since establishing vector control operations in the 1960s, the Singapore dengue control programme succeeded in reducing the dengue force of infection 10-fold by the 1990s and has maintained it at low levels ever since. Key to this success is consideration of dengue as an environmental disease, with a strong focus on source reduction and other environmental management methods as the dominant vector control strategy. The programme collaborates closely with other government ministries, as well as town councils, communities, the private sector, and academic and research institutions. Community engagement programmes encourage source reduction, and house-to-house inspections accompanied by a strong legislative framework with monetary penalties help to support compliance. Strong vector and epidemiological surveillance means that routine control activities can be heightened to specifically target dengue clusters. Despite its success, the programme continues to innovate to tackle challenges such as climate change, low herd immunity, and manpower constraints. Initiatives include development of novel vector controls such as Wolbachia-infected males and spatiotemporal models for dengue risk assessment. Lessons learnt from the Singapore programme can be applied to other settings, even those less well-resourced than Singapore, for more effective vector control.

Infections due to dengue and other viruses transmitted by Aedes mosquitoes are on the rise worldwide as a result of urbanisation, trade, population movement, and climate change. Contemporary vector control programmes have struggled to control Aedes-borne diseases, but the Singapore dengue control programme provides a success story. Key to the success is consideration of dengue as an environmental disease, with a corresponding focus on removal of water containers from in and around homes, solid waste management, and limited use of insecticides. The programme relies on close collaboration with other government and nongovernment actors including communities. Community engagement campaigns to ensure high awareness are supported by house-to-house inspections for mosquito habitats and a legislative framework including penalties for noncompliance. The Singapore dengue control programme provides important lessons that can be applied to other Aedes control programmes and vector control programmes more widely.

Gravitrap deployment for adult Aedes aegypti surveillance and its impact on dengue cases

House Index, Container Index, and Breteau Index are the most commonly used indices for dengue vector surveillance. However, these larval indices are a poor proxy for measuring the adult population—which is responsible for disease transmission. Information on the adult distribution and density are important for assessing transmission risk as well as for developing effective control strategies. This study introduces a new entomological index, Gravitrap aegypti index (GAI), which estimates the adult female Aedes aegypti population in the community and presents its association with dengue cases. Gravitraps were deployed across 34 treatment sites in Singapore from September 2013 to September 2016. The GAI, derived from the Gravitrap surveillance data, was analysed to investigate the spatio-temporal patterns of the Ae. aegypti population in Singapore. The index was further categorised into low, moderate, and high-risk groups and its association with dengue cases were examined. A Before-After Control Impact analysis was performed to evaluate the epidemiology impact of Gravitrap system on dengue transmission. The Ae. aegypti population exhibits a seasonal pattern, and spatial heterogeneity in Ae. aegypti abundance was observed among treatment sites. The Ae. aegypti population was also found to be unevenly distributed among floors of an apartment block, with low floors (floors 1–4) having a higher abundance of mosquitoes trapped than mid (floors 5–8) and high (floors ≥9) floors. Areas with high GAI were shown to have higher dengue case count. Gravitrap has also demonstrated to be a good dengue control tool. The contribution of cases by treatment sites to the national numbers was lower after Gravitraps deployment. The GAI, which is of better relevance to dengue transmission risk, could be recommended as an indicator for decision making in vector control efforts, and to monitor the spatio-temporal variability of the adult Aedes population in the country. In addition, findings from this study indicate that Gravitraps can be used as a dengue control tool to reduce dengue transmission.

In the absence of an effective vaccine: vector surveillance and control remain the key strategy for dengue prevention and control. The collection of the adult female Aedes mosquito is thus important to understand disease transmission dynamics. Information on its distribution and density are also essential for assessing transmission risk as well as for devising an effective control strategy. Here, we described a new approach to dengue vector surveillance based on adult female Aedes trapping using Gravitraps. Using the Gravitrap surveillance data, we derived a new entomological index, Gravitrap aegypti index (GAI), which estimates the adult female Ae. aegypti population in the community and presents its association with dengue cases. When analysed, the index can provide useful information on the spatio-temporal distribution of the Ae. aegypti population in the country and hence, assist planning of vector control. The GAI, which is of better relevance to dengue transmission risk, could be used as an indicator for decision making in vector control efforts, and to monitor the spatio-temporal variability of the adult Aedes population. In addition, findings from this study indicate that Gravitraps can be used as a dengue control tool to reduce dengue transmission.

Implementation of geographical information systems for the study of diseases caused by vector-borne arboviruses in Southeast Asia: A review based on the publication record

The spread of mosquito-borne diseases in Southeast Asia has dramatically increased in the latest decades. These infections include dengue, chikungunya and Japanese Encephalitis (JE), high-burden viruses sharing overlapping disease manifestation and vector distribution. The use of Geographical Information Systems (GIS) to monitor the dynamics of disease and vector distribution can assist in disease epidemic prediction and public health interventions, particularly in Southeast Asia where sustained high temperatures drive the epidemic spread of these mosquito-borne viruses. Due to lack of accurate data, the spatial and temporal dynamics of these mosquito-borne viral disease transmission countries are poorly understood, which has limited disease control effort. By following studies carried out on these three viruses across the region in a specific time period revealing general patterns of research activities and characteristics, this review finds the need to improve decision-support by disease mapping and management. The results presented, based on a publication search with respect to diseases due to arboviruses, specifically dengue, chikungunya and Japanese encephalitis, should improve opportunities for future studies on the implementation of GIS in the control of mosquito-borne viral diseases in Southeast Asia.

[Infectious and parasitic diseases in Brazil, 2010 to 2017: considerations for surveillanceEnfermedades infecciosas y parasitarias en Brasil de 2010 a 2017: aspectos para la vigilancia sanitaria]

Objetivo.

Apresentar um método para identificar áreas críticas relativas a doenças infecciosas e parasitárias selecionadas para fins de vigilância em saúde, analisando a sua associação a indicadores de pobreza no Brasil.

Métodos.

Foram mapeadas as taxas de incidência de dengue, doença de Chagas aguda, esquistossomose, hanseníase, hepatite A, leishmaniose tegumentar, leishmaniose visceral, leptospirose, malária e tuberculose. Foram realizadas análises para os anos de 2010 a 2017 a partir de um indicador síntese, calculado como a média dos coeficientes médios de incidência para cada agravo normalizada pela média e desvio padrão durante o período analisado. A estimativa da base populacional foi de 2014. Os coeficientes calculados foram estratificados para classificação dos municípios em criticidade muito alta, alta, média, baixa ou muito baixa conforme cada doença. Também foram selecionados indicadores de diferentes dimensões que expressassem desigualdades socioeconômicas e segregação espacial nos municípios brasileiros, sendo testada a sua associação às doenças em estudo.

Resultados.

O indicador mostrou que 40,5% dos municípios brasileiros apresentam alta criticidade, sobretudo nas regiões Norte, parte do Nordeste e Centro-Oeste. Os indicadores “proporção de pobreza”, “lixo no entorno”, “esgoto no entorno” e “famílias chefiadas por mulheres” podem aumentar a chance de a localidade apresentar maior criticidade para as doenças. O indicador “esgoto adequado” pode ser considerado potencial fator de proteção.

Conclusões.

A técnica utilizada foi adequada para orientar ações de vigilância no país e permite a articulação entre vigilâncias locais e demais setores para contornar os problemas de saúde causados por doenças infecciosas e parasitárias e fatores relacionados.

Influenza activity prediction using meteorological factors in a warm temperate to subtropical transitional zone, Eastern China

Influenza activity is subject to environmental factors. Accurate forecasting of influenza epidemics would permit timely and effective implementation of public health interventions, but it remains challenging. In this study, we aimed to develop random forest (RF) regression models including meterological factors to predict seasonal influenza activity in Jiangsu provine, China. Coefficient of determination (R2) and mean absolute percentage error (MAPE) were employed to evaluate the models' performance. Three RF models with optimum parameters were constructed to predict influenza like illness (ILI) activity, influenza A and B (Flu-A and Flu-B) positive rates in Jiangsu. The models for Flu-B and ILI presented excellent performance with MAPEs <10%. The predicted values of the Flu-A model also matched the real trend very well, although its MAPE reached to 19.49% in the test set. The lagged dependent variables were vital predictors in each model. Seasonality was more pronounced in the models for ILI and Flu-A. The modification effects of the meteorological factors and their lagged terms on the prediction accuracy differed across the three models, while temperature always played an important role. Notably, atmospheric pressure made a major contribution to ILI and Flu-B forecasting. In brief, RF models performed well in influenza activity prediction. Impacts of meteorological factors on the predictive models for influenza activity are type-specific.

Estimating the burden of dengue and the impact of release of wMel Wolbachia-infected mosquitoes in Indonesia: a modelling study

BACKGROUND

Wolbachia-infected mosquitoes reduce dengue virus transmission, and city-wide releases in Yogyakarta city, Indonesia, are showing promising entomological results. Accurate estimates of the burden of dengue, its spatial distribution and the potential impact of Wolbachia are critical in guiding funder and government decisions on its future wider use.

METHODS

Here, we combine multiple modelling methods for burden estimation to predict national case burden disaggregated by severity and map the distribution of burden across the country using three separate data sources. An ensemble of transmission models then predicts the estimated reduction in dengue transmission following a nationwide roll-out of wMel Wolbachia.

RESULTS

We estimate that 7.8 million (95% uncertainty interval [UI] 1.8-17.7 million) symptomatic dengue cases occurred in Indonesia in 2015 and were associated with 332,865 (UI 94,175-754,203) lost disability-adjusted life years (DALYs). The majority of dengue's burden was due to non-severe cases that did not seek treatment or were challenging to diagnose in outpatient settings leading to substantial underreporting. Estimated burden was highly concentrated in a small number of large cities with 90% of dengue cases occurring in 15.3% of land area. Implementing a nationwide Wolbachia population replacement programme was estimated to avert 86.2% (UI 36.2-99.9%) of cases over a long-term average.

CONCLUSIONS

These results suggest interventions targeted to the highest burden cities can have a disproportionate impact on dengue burden. Area-wide interventions, such as Wolbachia, that are deployed based on the area covered could protect people more efficiently than individual-based interventions, such as vaccines, in such dense environments.

Forecasting dengue fever in Brazil: An assessment of climate conditions

Local climate conditions play a major role in the biology of the Aedes aegypti mosquito, the main vector responsible for transmitting dengue, zika, chikungunya and yellow fever in urban centers. For this reason, a detailed assessment of periods in which changes in climate conditions affect the number of human cases may improve the timing of vector-control efforts. In this work, we develop new machine-learning algorithms to analyze climate time series and their connection to the occurrence of dengue epidemic years for seven Brazilian state capitals. Our method explores the impact of two key variables-frequency of precipitation and average temperature-during a wide range of time windows in the annual cycle. Our results indicate that each Brazilian state capital considered has its own climate signatures that correlate with the overall number of human dengue-cases. However, for most of the studied cities, the winter preceding an epidemic year shows a strong predictive power. Understanding such climate contributions to the vector's biology could lead to more accurate prediction models and early warning systems.

Using Human Movement Data to Identify Potential Areas of Zika Transmission: Case Study of the Largest Zika Cluster in Singapore

Singapore experienced its first Zika virus (ZIKV) cluster in August 2016. To understand the implication of human movement on disease spread, a retrospective study was conducted using aggregated and anonymized mobile phone data to examine movement from the cluster to identify areas of possible transmission. An origin–destination model was developed based on the movement of three groups of individuals: (i) construction workers, (ii) residents and (iii) visitors out of the cluster locality to other parts of the island. The odds ratio of ZIKV cases in a hexagon visited by an individual from the cluster, independent of the group of individuals, is 3.20 (95% CI: 2.65–3.87, p-value < 0.05), reflecting a higher count of ZIKV cases when there is a movement into a hexagon from the cluster locality. A comparison of independent ROC curves tested the statistical significance of the difference between the areas under the curves of the three groups of individuals. Visitors (difference in AUC = 0.119) and residents (difference in AUC = 0.124) have a significantly larger difference in area under the curve compared to the construction workers (p-value < 0.05). This study supports the proof of concept of using mobile phone data to approximate population movement, thus identifying areas at risk of disease transmission.

A novel entomological index, Aedes aegypti Breeding Percentage, reveals the geographical spread of the dengue vector in Singapore and serves as a spatial risk indicator for dengue

Background

Aedes aegypti is an efficient primary vector of dengue, and has a heterogeneous distribution in Singapore. Aedes albopictus, a poor vector of dengue, is native and ubiquitous on the island. Though dengue risk follows the dispersal of Ae. aegypti, the spatial distribution of the vector is often poorly characterized. Here, based on the ubiquitous presence of Ae. albopictus, we developed a novel entomological index, Ae. aegypti Breeding Percentage (BP), to demonstrate the expansion of Ae. aegypti into new territories that redefined the dengue burden map in Singapore. We also determined the thresholds of BP that render the specific area higher risk of dengue transmission.

Methods

We performed analysis of dengue fever incidence and Aedes mosquito breeding in Singapore by utilizing island-wide dengue cases and vector surveillance data from 2003 to 2013. The percentage of Ae. aegypti breeding among the total Aedes breeding habitats (BP), and the reported number of dengue fever cases in each year were calculated for each residential grid.

Results

The BP of grids, for every year over the 11-year study period, had a consistent positive correlation with the annual case counts. Our findings suggest that the geographical expansion of Ae. aegypti to previously “non-dengue” areas have contributed substantially to the recent dengue fever incidence in Singapore. Our analysis further indicated that non-endemic areas in Singapore are likely to be at risk of dengue fever outbreaks beyond an Ae. aegypti BP of 20%.

Conclusions

Our analyses indicate areas with increasing Ae. aegypti BP are likely to become more vulnerable to dengue outbreaks. We propose the usage of Ae. aegypti BP as a factor for spatial risk stratification of dengue fever in endemic countries. The Ae. aegypti BP could be recommended as an indicator for decision making in vector control efforts, and also be used to monitor the geographical expansion of Ae. aegypti.

Electronic supplementary material

The online version of this article (10.1186/s13071-018-3281-y) contains supplementary material, which is available to authorized users.