Developing a dengue prediction model based on climate in Tawau, Malaysia

A Coupled Statistical and Deterministic Model for Forecasting Climate-Driven Dengue Incidence in Selangor, Malaysia

The mosquito-borne dengue virus remains a major public health concern in Malaysia. Despite various control efforts and measures introduced by the Malaysian Government to combat dengue, the increasing trend of dengue cases persists and shows no sign of decreasing. Currently, early detection and vector control are the main methods employed to curb dengue outbreaks. In this study, a coupled model consisting of the statistical ARIMAX model and the deterministic SI-SIR model was developed and validated using the weekly reported dengue data from year 2014 to 2019 for Selangor, Malaysia. Previous studies have shown that climate variables, especially temperature, humidity, and precipitation, were able to influence dengue incidence and transmission dynamics through their effect on the vector. In this coupled model, climate is linked to dengue disease through mosquito biting rate, allowing real-time forecast of dengue cases using climate variables, namely temperature, rainfall and humidity. For the period chosen for model validation, the coupled model can forecast 1-2 weeks in advance with an average error of less than 6%, three weeks in advance with an average error of 7.06% and four weeks in advance with an average error of 8.01%. Further model simulation analysis suggests that the coupled model generally provides better forecast than the stand-alone ARIMAX model, especially at the onset of the outbreak. Moreover, the coupled model is more robust in the sense that it can be further adapted for investigating the effectiveness of various dengue mitigation measures subject to the changing climate.

Precision Prediction for Dengue Fever in Singapore: A Machine Learning Approach Incorporating Meteorological Data

OBJECTIVE

This study aimed to improve dengue fever predictions in Singapore using a machine learning model that incorporates meteorological data, addressing the current methodological limitations by examining the intricate relationships between weather changes and dengue transmission.

METHOD

Using weekly dengue case and meteorological data from 2012 to 2022, the data was preprocessed and analyzed using various machine learning algorithms, including General Linear Model (GLM), Support Vector Machine (SVM), Gradient Boosting Machine (GBM), Decision Tree (DT), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) algorithms. Performance metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R2) were employed.

RESULTS

From 2012 to 2022, there was a total of 164,333 cases of dengue fever. Singapore witnessed a fluctuating number of dengue cases, peaking notably in 2020 and revealing a strong seasonality between March and July. An analysis of meteorological data points highlighted connections between certain climate variables and dengue fever outbreaks. The correlation analyses suggested significant associations between dengue cases and specific weather factors such as solar radiation, solar energy, and UV index. For disease predictions, the XGBoost model showed the best performance with an MAE = 89.12, RMSE = 156.07, and R2 = 0.83, identifying time as the primary factor, while 19 key predictors showed non-linear associations with dengue transmission. This underscores the significant role of environmental conditions, including cloud cover and rainfall, in dengue propagation.

CONCLUSION

In the last decade, meteorological factors have significantly influenced dengue transmission in Singapore. This research, using the XGBoost model, highlights the key predictors like time and cloud cover in understanding dengue's complex dynamics. By employing advanced algorithms, our study offers insights into dengue predictive models and the importance of careful model selection. These results can inform public health strategies, aiming to improve dengue control in Singapore and comparable regions.

Prediction of dengue cases using the attention-based long short-term memory (LSTM) approach

This research proposes a 'temporal attention' addition for long-short term memory (LSTM) models for dengue prediction. The number of monthly dengue cases was collected for each of five Malaysian states i.e. Selangor, Kelantan, Johor, Pulau Pinang, and Melaka from 2011 to 2016. Climatic, demographic, geographic and temporal attributes were used as covariates. The proposed LSTM models with temporal attention was compared with several benchmark models including a linear support vector machine (LSVM), a radial basis function support vector machine (RBFSVM), a decision tree (DT), a shallow neural network (SANN) and a deep neural network (D-ANN). In addition, experiments were conducted to analyze the impact of look-back settings on each model performance. The results showed that the attention LSTM (A-LSTM) model performed best, with the stacked, attention LSTM (SA-LSTM) one in second place. The LSTM and stacked LSTM (S-LSTM) models performed almost identically but with the accuracy improved by the attention mechanism was added. Indeed, they were both found to be superior to the benchmark models mentioned above. The best results were obtained when all attributes were included in the model. The four models (LSTM, S-LSTM, A-LSTM and SA-LSTM) were able to accurately predict dengue presence 1-6 months ahead. Our findings provide a more accurate dengue prediction model than previously used, with the prospect of also applying this approach in other geographic areas.

Paradox between adequate sanitation and rainfall in dengue fever cases

BACKGROUND

Dengue fever is a tropical disease and a major public health concern, and almost half of the world's population lives in areas at risk of contracting this disease. Climate change is identified by WHO and other international health authorities as one of the primary factors that contribute to the rapid spread of dengue fever.

METHODS

We evaluated the effect of sanitation on the cross-correlation between rainfall and the first symptoms of dengue in the city of Mato Grosso do Sul, which is in a state in the Midwest region of Brazil, and employed the time-lagged detrended cross-correlation analysis (DCCAC) method.

RESULTS

Co-movements were obtained through the time-phased DCCAC to analyze the effects of climatic variables on arboviruses. The use of a time-lag analysis was more robust than DCCAC without lag to present the behavior of dengue cases in relation to accumulated precipitation. Our results show that the cross-correlation between rain and dengue increased as the city implemented actions to improve basic sanitation in the city.

CONCLUSION

With climate change and the increase in the global average temperature, mosquitoes are advancing beyond the tropics, and our results show that cities with improved sanitation have a high correlation between dengue and annual precipitation. Public prevention and control policies can be targeted according to the period of time and the degree of correlation calculated to structure vector control and prevention work in places where sanitation conditions are adequate.

A systematic review of dengue outbreak prediction models: Current scenario and future directions

Dengue is among the fastest-spreading vector-borne infectious disease, with outbreaks often overwhelm the health system and result in huge morbidity and mortality in its endemic populations in the absence of an efficient warning system. A large number of prediction models are currently in use globally. As such, this study aimed to systematically review the published literature that used quantitative models to predict dengue outbreaks and provide insights about the current practices. A systematic search was undertaken, using the Ovid MEDLINE, EMBASE, Scopus and Web of Science databases for published citations, without time or geographical restrictions. Study selection, data extraction and management process were devised in accordance with the 'Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies' ('CHARMS') framework. A total of 99 models were included in the review from 64 studies. Most models sourced climate (94.7%) and climate change (77.8%) data from agency reports and only 59.6% of the models adjusted for reporting time lag. All included models used climate predictors; 70.7% of them were built with only climate factors. Climate factors were used in combination with climate change factors (13.4%), both climate change and demographic factors (3.1%), vector factors (6.3%), and demographic factors (5.2%). Machine learning techniques were used for 39.4% of the models. Of these, random forest (15.4%), neural networks (23.1%) and ensemble models (10.3%) were notable. Among the statistical (60.6%) models, linear regression (18.3%), Poisson regression (18.3%), generalized additive models (16.7%) and time series/autoregressive models (26.7%) were notable. Around 20.2% of the models reported no validation at all and only 5.2% reported external validation. The reporting of methodology and model performance measures were inadequate in many of the existing prediction models. This review collates plausible predictors and methodological approaches, which will contribute to robust modelling in diverse settings and populations.

Development and user testing study of MozzHub: a bipartite network-based dengue hotspot detector

Traditionally, dengue is controlled by fogging, and the prime location for the control measure is at the patient's residence. However, when Malaysia was hit by the first wave of the Coronavirus disease (COVID-19), and the government-imposed movement control order, dengue cases have decreased by more than 30% from the previous year. This implies that residential areas may not be the prime locations for dengue-infected mosquitoes. The existing early warning system was focused on temporal prediction wherein the lack of consideration for spatial component at the microlevel and human mobility were not considered. Thus, we developed MozzHub, which is a web-based application system based on the bipartite network-based dengue model that is focused on identifying the source of dengue infection at a small spatial level (400 m) by integrating human mobility and environmental predictors. The model was earlier developed and validated; therefore, this study presents the design and implementation of the MozzHub system and the results of a preliminary pilot test and user acceptance of MozzHub in six district health offices in Malaysia. It was found that the MozzHub system is well received by the sample of end-users as it was demonstrated as a useful (77.4%), easy-to-operate system (80.6%), and has achieved adequate client satisfaction for its use (74.2%).

Concrete Performance Attenuation of Mix Nano-SiO2 and Nano-CaCO3 under High Temperature: A Comprehensive Review

Fire and extreme heat environmental changes can have an impact on concrete performance, and as climate change increases, new concrete structures are being developed. Nano-silica and nano-calcium carbonate have shown excellent performances in modifying concrete due to their large specific surface areas. This review describes the changes in concrete modified with nano-silica (NS) and nano-calcium carbonate (NC), which accelerate the hydration reaction with the cementitious materials to produce more C-S-H, resulting in a denser microstructure and improved mechanical properties and durability of the concrete. The mechanical property decay and visualization of deformation of mixed NS and NC concrete were tested by exposure to high temperatures to investigate the practical application of mixed composite nanomaterials (NC+NS) to concrete. The nano-modified concrete had better overall properties and was heated at 200 °C, 400 °C, 600 °C and 800 °C to relatively improve the mechanical properties of the nano concrete structures. The review concluded that high temperatures of 800 °C to 1000 °C severely damaged the structure of the concrete, reducing the mechanical properties by around 60%, and the dense nano concrete structures were more susceptible to cracking and damage. The high temperature resistance of NS and NC-modified nano concrete was relatively higher than that of normal concrete, with NC concrete being more resistant to damage at high temperatures than the NS samples.

Temporal and Spatiotemporal Arboviruses Forecasting by Machine Learning: A Systematic Review

Arboviruses are a group of diseases that are transmitted by an arthropod vector. Since they are part of the Neglected Tropical Diseases that pose several public health challenges for countries around the world. The arboviruses' dynamics are governed by a combination of climatic, environmental, and human mobility factors. Arboviruses prediction models can be a support tool for decision-making by public health agents. In this study, we propose a systematic literature review to identify arboviruses prediction models, as well as models for their transmitter vector dynamics. To carry out this review, we searched reputable scientific bases such as IEE Xplore, PubMed, Science Direct, Springer Link, and Scopus. We search for studies published between the years 2015 and 2020, using a search string. A total of 429 articles were returned, however, after filtering by exclusion and inclusion criteria, 139 were included. Through this systematic review, it was possible to identify the challenges present in the construction of arboviruses prediction models, as well as the existing gap in the construction of spatiotemporal models.

Prediction of Dengue Incidence in the Northeast Malaysia Based on Weather Data Using the Generalized Additive Model

Introduction

Dengue, a vector-borne viral illness, shows worldwide widening spatial distribution beyond its point of origination, namely, the tropical belt. The persistent hyperendemicity in Malaysia has resulted in the formation of the dengue early warning system. However, weather variables are yet to be fully utilized for prevention and control activities, particularly in east-coast peninsular Malaysia where limited studies have been conducted. We aim to provide a time-based estimate of possible dengue incidence increase following weather-related changes, thereby highlighting potential dengue outbreaks.

Method

All serologically confirmed dengue patients in Kelantan, a northeastern state in Malaysia, registered in the eDengue system with an onset of disease from January 2016 to December 2018, were included in the study with the exclusion of duplicate entry. Using a generalized additive model, climate data collected from the Kota Bharu weather station (latitude 6°10′N, longitude 102°18′E) was analysed with dengue data.

Result

A cyclical pattern of dengue cases was observed with annual peaks coinciding with the intermonsoon period. Our analysis reveals that maximum temperature, mean temperature, rainfall, and wind speed have a significant nonlinear effect on dengue cases in Kelantan. Our model can explain approximately 8.2% of dengue incidence variabilities.

Conclusion

Weather variables affect nearly 10% of the dengue incidences in Northeast Malaysia, thereby making it a relevant variable to be included in a dengue early warning system. Interventions such as vector control activities targeting the intermonsoon period are recommended.

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.

The roles of machine learning methods in limiting the spread of deadly diseases: A systematic review

Machine learning (ML) methods can be leveraged to prevent the spread of deadly infectious disease outbreak (e.g., COVID-19). This can be done by applying machine learning methods in predicting and detecting the deadly infectious disease. Most reviews did not discuss about the machine learning algorithms, datasets and performance measurements used for various applications in predicting and detecting the deadly infectious disease. In contrast, this paper outlines the literature review based on two major ways (e.g., prediction, detection) to limit the spread of deadly disease outbreaks. Hence, this study aims to investigate the state of the art, challenges and future works of leveraging ML methods to detect and predict deadly disease outbreaks according to two categories mentioned earlier. Specifically, this study provides a review on various approaches (e.g., individual and ensemble models), types of datasets, parameters or variables and performance measures used in the previous works. The literature review included all articles from journals and conference proceedings published from 2010 through 2020 in Scopus indexed databases using the search terms Predicting Disease Outbreaks and/or Detecting Disease using Machine Learning. The findings from this review focus on commonly used machine learning approaches, challenges and future works to limit the spread of deadly disease outbreaks through preventions and detections.

Dengue Transmission Mapping with Weather-Based Predictive Model in Three Southernmost Provinces of Thailand

This study aimed to show maps and analyses that display dengue cases and weather-related factors on dengue transmission in the three southernmost provinces of Thailand, namely Pattani, Yala, and Narathiwat provinces. Data on the number of dengue cases and weather variables including rainfall, rainy day, mean temperature, min temperature, max temperature, relative humidity, and air pressure for the period from January 2015 to December 2019 were obtained from the Bureau of Epidemiology, Ministry of Public Health and the Meteorological Department of Southern Thailand, respectively. Spearman rank correlation test was performed at lags from zero to two months and the predictive modeling used time series Poisson regression analysis. The distribution of dengue cases showed that in Pattani and Yala provinces the most dengue cases occurred in June. Narathiwat province had the most dengue cases occurring in August. The air pressure, relative humidity, rainfall, rainy day, and min temperature are the main predictors in Pattani province, while air pressure, rainy day, and max/mean temperature seem to play important roles in the number of dengue cases in Yala and Narathiwat provinces. The goodness-of-fit analyses reveal that the model fits the data reasonably well. The results provide scientific information for creating effective dengue control programs in the community, and the predictive model can support decision making in public health organizations and for management of the environmental risk area.

Predictive analysis of the number of human brucellosis cases in Xinjiang, China

Brucellosis is one of the major public health problems in China, and human brucellosis represents a serious public health concern in Xinjiang and requires a prediction analysis to help making early planning and putting forward science preventive and control countermeasures. According to the characteristics of the time series of monthly reported cases of human brucellosis in Xinjiang from January 2008 to June 2020, we used seasonal autoregressive integrated moving average (SARIMA) method and nonlinear autoregressive regression neural network (NARNN) method, which are widely prevalent and have high prediction accuracy, to construct prediction models and make prediction analysis. Finally, we established the SARIMA((1,4,5,7),0,0)(0,1,2)12 model and the NARNN model with a time lag of 5 and a hidden layer neuron of 10. Both models have high fitting performance. After comparing the accuracies of two established models, we found that the SARIMA((1,4,5,7),0,0)(0,1,2)12 model was better than the NARNN model. We used the SARIMA((1,4,5,7),0,0)(0,1,2)12 model to predict the number of monthly reported cases of human brucellosis in Xinjiang from July 2020 to December 2021, and the results showed that the fluctuation of the time series from July 2020 to December 2021 was similar to that of the last year and a half while maintaining the current prevention and control ability. The methodology applied here and its prediction values of this study could be useful to give a scientific reference for prevention and control human brucellosis.

Measuring the effectiveness of integrated vector management with targeted outdoor residual spraying and autodissemination devices on the incidence of dengue in urban Malaysia in the iDEM trial (intervention for Dengue Epidemiology in Malaysia): study protocol for a cluster randomized controlled trial

Background

In common with many South East Asian countries, Malaysia is endemic for dengue. Dengue control in Malaysia is currently based on reactive vector management within 24 h of a dengue case being reported. Preventive rather than reactive vector control approaches, with combined interventions, are expected to improve the cost-effectiveness of dengue control programs. The principal objective of this cluster randomized controlled trial is to quantify the effectiveness of a preventive integrated vector management (IVM) strategy on the incidence of dengue as compared to routine vector control efforts.

Methods

The trial is conducted in randomly allocated clusters of low- and medium-cost housing located in the Federal Territory of Kuala Lumpur and Putrajaya. The IVM approach combines: targeted outdoor residual spraying with K-Othrine Polyzone, deployment of mosquito traps as auto-dissemination devices, and community engagement activities. The trial includes 300 clusters randomly allocated in a 1:1 ratio. The clusters receive either the preventive IVM in addition to the routine vector control activities or the routine vector control activities only. Epidemiological data from monthly confirmed dengue cases during the study period will be obtained from the Vector Borne Disease Sector, Malaysian Ministry of Health e-Dengue surveillance system. Entomological surveillance data will be collected in 12 clusters randomly selected from each arm.

To measure the effectiveness of the IVM approach on dengue incidence, a negative binomial regression model will be used to compare the incidence between control and intervention clusters. To quantify the effect of the interventions on the main entomological outcome, ovitrap index, a modified ordinary least squares regression model using a robust standard error estimator will be used.

Discussion

Considering the ongoing expansion of dengue burden in Malaysia, setting up proactive control strategies is critical. Despite some limitations of the trial such as the use of passive surveillance to identify cases, the results will be informative for a better understanding of effectiveness of proactive IVM approach in the control of dengue. Evidence from this trial may help justify investment in preventive IVM approaches as preferred to reactive case management strategies.

Trial registration

ISRCTN ISRCTN81915073. Retrospectively registered on 17 April 2020.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13063-021-05298-2.

Climatic and socio-economic factors supporting the co-circulation of dengue, Zika and chikungunya in three different ecosystems in Colombia

Dengue, Zika and chikungunya are diseases of global health significance caused by arboviruses and transmitted by the mosquito Aedes aegypti, which is of worldwide circulation. The arrival of the Zika and chikungunya viruses to South America increased the complexity of transmission and morbidity caused by these viruses co-circulating in the same vector mosquito species. Here we present an integrated analysis of the reported arbovirus cases between 2007 and 2017 and local climate and socio-economic profiles of three distinct Colombian municipalities (Bello, Cúcuta and Moniquirá). These locations were confirmed as three different ecosystems given their contrasted geographic, climatic and socio-economic profiles. Correlational analyses were conducted with both generalised linear models and generalised additive models for the geographical data. Average temperature, minimum temperature and wind speed were strongly correlated with disease incidence. The transmission of Zika during the 2016 epidemic appeared to decrease circulation of dengue in Cúcuta, an area of sustained high incidence of dengue. Socio-economic factors such as barriers to health and childhood services, inadequate sanitation and poor water supply suggested an unfavourable impact on the transmission of dengue, Zika and chikungunya in all three ecosystems. Socio-demographic influencers were also discussed including the influx of people to Cúcuta, fleeing political and economic instability from neighbouring Venezuela. Aedes aegypti is expanding its range and increasing the global threat of these diseases. It is therefore vital that we learn from the epidemiology of these arboviruses and translate it into an actionable local knowledge base. This is even more acute given the recent historical high of dengue cases in the Americas in 2019, preceding the COVID-19 pandemic, which is itself hampering mosquito control efforts.

Dynamics of dengue outbreaks in gangetic West Bengal: A trend and time series analysis

Background and Aims:

Dengue is a vector-borne viral disease which is one of the major causes of public health problem in India, and its control is often the major challenges of municipal bodies in the country, especially in West Bengal. The previous outbreaks of the disease can be used to forecast the future occurrence and burden, so that authorities may optimize the available resources in order to contain and minimize the impact.

Materials and Methods:

Weekly disease outbreak data were extracted from Integrated Disease Surveillance Programme website and arranged as monthly data. Mann-Kendall test was used to determine the significance of the disease trends in various districts of Gangetic West Bengal. Time series analysis was done by using Seasonal ARIMA method to predict the number of Dengue outbreak cases for the year 2020.

Results:

Murshidabad was the only district of Gangetic West Bengal that had a significant upward Dengue cases outbreak trend. Nadia had a downward trend but it was not statistically significant. Model SARIMA (1,0,0) (1,0,0) ₁₂ was chosen to forecast the Dengue outbreak cases which showed that the cases might start from the month of June, peak in August and wane off in October 2020. However, this prediction was not significant.

Conclusion:

Gangetic West Bengal might experience similar dengue cases as the previous year, but their numbers would be low. Only the district of Murshidabad would have upward trend. Knowledge in advance about periods of disease occurrence may enable health authorities to initiate control measures during the start of the outbreak season.

The Impact of Dengue on Economic Growth: The Case of Southern Taiwan

Dengue has long been a public health problem in tropical and subtropical countries. In 2015, a dengue outbreak occurred in Taiwan, where 43,784 cases were reported. This study aims to assess the impact of dengue on Southern Taiwan’s economic growth according to the economic growth model-based regression approach recommended by the World Health Organization (WHO). Herein, annual data from Southern Taiwan on the number of dengue cases, income growth, and demographics from 2010–2015 were analyzed. The percentage of reduction of the average income per capita in 2015 due to the dengue outbreak was estimated. Dengue was determined to have a negative linear economic impact on Southern Taiwan’s economic growth. In particular, a reduction of 0.26% in the average income per capita was estimated in Southern Taiwan due to the 2015 outbreak. If the model is applied alongside other dengue outbreak forecast models, then the forecast for economic reduction due to a future dengue outbreak may also be estimated. Prevention and recovery policies may subsequently be decided upon based on not only the number of dengue cases but also the degree of economic burden resulting from an outbreak.