Long-term predictors of dengue outbreaks in Bangladesh: A data mining approach

Analysis of effects of meteorological variables on dengue incidence in Bangladesh using VAR and Granger causality approach

Background

Dengue fever is a serious public health issue in Bangladesh, where its incidence rises with the monsoon. Meteorological variables are believed to be responsible factors among others. Therefore, this study examines the effects of meteorological variables (temperature, rainfall, and humidity) on dengue incidence in Bangladesh. While previous studies have examined the relationship between dengue and meteorological variables using single model approaches, this study employs advanced econometric techniques to capture dynamic interactions. Furthermore, in the case of Bangladesh, this type of analysis is necessary due to the fact that dengue outbreak become one of the major issues. However, the analysis related to this issue is not available.

Methods

For estimation purposes, the Augmented Dickey-Fuller (ADF) test, Vector Autoregressive (VAR) model, Granger causality tests, Impulse Response Function (IRF), Variance Decomposition (VDC), and Vector Error Correction Model (VECM) are employed.

Results

Rainfall has a significant impact on dengue incidence compared to temperature and humidity. The Granger causality test demonstrates that rainfall and dengue incidence are causally related unidirectionally. Rainfall can potentially have a short-term and long-term effect on the incidence of dengue, as per the estimates of the VECM model.

Conclusions

These findings will assist policymakers in Bangladesh in developing a dengue fever early warning system depending on climate change. In order to efficiently avoid the spread of dengue in Bangladesh's dengue-endemic urban areas, this study suggests societal monitoring.

Mathematical analysis and prediction of future outbreak of dengue on time-varying contact rate using machine learning approach

This article introduces a novel mathematical model analyzing the dynamics of Dengue in the recent past, specifically focusing on the 2023 outbreak of this disease. The model explores the patterns and behaviors of dengue fever in Bangladesh. Incorporating a sinusoidal function reveals significant mid-May to Late October outbreak predictions, aligning with the government's exposed data in our simulation. For different amplitudes (A) within a sequence of values (A = 0.1 to 0.5), the highest number of infected mosquitoes occurs in July. However, simulations project that when βM = 0.5 and A = 0.1, the peak of human infections occurs in late September. Not only the next-generation matrix approach along with the stability of disease-free and endemic equilibrium points are observed, but also a cutting-edge Machine learning (ML) approach such as the Prophet model is explored for forecasting future Dengue outbreaks in Bangladesh. Remarkably, we have fitted our solution curve of infection with the reported data by the government of Bangladesh. We can predict the outcome of 2024 based on the ML Prophet model situation of Dengue will be detrimental and proliferate 25 % compared to 2023. Finally, the study marks a significant milestone in understanding and managing Dengue outbreaks in Bangladesh.

Climate change, thermal anomalies, and the recent progression of dengue in Brazil

Dengue is rapidly expanding its transmission area across Brazil and much of South America. In this study, data-mining techniques were used to identify climatic and demographic indicators that could explain the recent (2014-2020) and simultaneous trends of expansion and exacerbation of the incidence in some regions of Brazil. The previous circulation of the virus (dengue incidence rates between 2007 and 2013), urbanization, and the occurrence of temperature anomalies for a prolonged period were the main factors that led to increased incidence of dengue in the central region of Brazil. Regions with high altitudes, which previously acted as a barrier for dengue transmission, became areas of high incidence rates. The algorithm that was developed during this study can be utilized to assess future climate scenarios and plan preventive actions.

A Bayesian machine learning approach for spatio-temporal prediction of COVID-19 cases

Modeling the spread of infectious diseases in space and time needs to take care of complex dependencies and uncertainties. Machine learning methods, and neural networks, in particular, are useful in modeling this sort of complex problems, although they generally lack of probabilistic interpretations. We propose a neural network method embedded in a Bayesian framework for modeling and predicting the number of cases of infectious diseases in areal units. A key feature is that our combined model considers the impact of human movement on the spread of the infectious disease, as an additional random factor to the also considered spatial neighborhood and temporal correlation components. Our model is evaluated over a COVID-19 dataset for 245 health zones of Castilla-Leon (Spain). The results show that a Bayesian model informed by a neural network method is generally able to predict the number of cases of COVID-19 in both space and time, with the human mobility factor having a strong influence on the model, together with the number of infections and deaths in nearby areas.

Empirical Study on Classifiers for Earlier Prediction of COVID-19 Infection Cure and Death Rate in the Indian States

Machine Learning methods can play a key role in predicting the spread of respiratory infection with the help of predictive analytics. Machine Learning techniques help mine data to better estimate and predict the COVID-19 infection status. A Fine-tuned Ensemble Classification approach for predicting the death and cure rates of patients from infection using Machine Learning techniques has been proposed for different states of India. The proposed classification model is applied to the recent COVID-19 dataset for India, and a performance evaluation of various state-of-the-art classifiers to the proposed model is performed. The classifiers forecasted the patients’ infection status in different regions to better plan resources and response care systems. The appropriate classification of the output class based on the extracted input features is essential to achieve accurate results of classifiers. The experimental outcome exhibits that the proposed Hybrid Model reached a maximum F1-score of 94% compared to Ensembles and other classifiers like Support Vector Machine, Decision Trees, and Gaussian Naïve Bayes on a dataset of 5004 instances through 10-fold cross-validation for predicting the right class. The feasibility of automated prediction for COVID-19 infection cure and death rates in the Indian states was demonstrated.

Data-driven methods for dengue prediction and surveillance using real-world and Big Data: A systematic review

Background

Traditionally, dengue surveillance is based on case reporting to a central health agency. However, the delay between a case and its notification can limit the system responsiveness. Machine learning methods have been developed to reduce the reporting delays and to predict outbreaks, based on non-traditional and non-clinical data sources. The aim of this systematic review was to identify studies that used real-world data, Big Data and/or machine learning methods to monitor and predict dengue-related outcomes.

Methodology/Principal findings

We performed a search in PubMed, Scopus, Web of Science and grey literature between January 1, 2000 and August 31, 2020. The review (ID: CRD42020172472) focused on data-driven studies. Reviews, randomized control trials and descriptive studies were not included. Among the 119 studies included, 67% were published between 2016 and 2020, and 39% used at least one novel data stream. The aim of the included studies was to predict a dengue-related outcome (55%), assess the validity of data sources for dengue surveillance (23%), or both (22%). Most studies (60%) used a machine learning approach. Studies on dengue prediction compared different prediction models, or identified significant predictors among several covariates in a model. The most significant predictors were rainfall (43%), temperature (41%), and humidity (25%). The two models with the highest performances were Neural Networks and Decision Trees (52%), followed by Support Vector Machine (17%). We cannot rule out a selection bias in our study because of our two main limitations: we did not include preprints and could not obtain the opinion of other international experts.

Conclusions/Significance

Combining real-world data and Big Data with machine learning methods is a promising approach to improve dengue prediction and monitoring. Future studies should focus on how to better integrate all available data sources and methods to improve the response and dengue management by stakeholders.

Dengue is one of the most important arbovirus infections in the world and its public health, societal and economic burden is increasing. Although the majority of dengue cases are asymptomatic or mild, severe disease forms can lead to death. For this reason, early diagnosis and monitoring of dengue are crucial to decrease mortality. However, most endemic regions still rely on traditional monitoring methods, despite the growing availability of novel data sources and data-driven methods based on real-world data, Big Data, and machine learning algorithms. In this systematic review, we identified and analyzed studies that used these novel approaches for dengue monitoring and/or prediction. We found that novel data streams, such as Internet search engines and social media platforms, and machine learning methods can be successfully used to improve dengue management, but are still vastly ignored in real life. These approaches should be combined with traditional methods to help stakeholders better prepare for each outbreak and improve early responsiveness.

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.

Impact of Climate Variability and Incidence on Dengue Hemorrhagic Fever in Palembang City, South Sumatra, Indonesia

Dengue hemorrhagic fever (DHF) is a dengue virus infection transmitted by Aedes spp. Climate has a profound influence on mosquito breeding. Palembang has the highest rate of DHF in South Sumatra. This study aimed to investigate the relationship between the components of climate factors and the incidence of DHF in Palembang. This study was cross-sectional, with an observational analytic approach. The Palembang City Health Office compiled data on DHF incidence rates from 2016 to 2020. Climatic factor data (rainfall, number of rainy days, temperature, humidity, wind speed, sun irradiance) were collected from the Climatology Station Class I Palembang - BMKG Station and Task Force that same year. The Spearman test was used to conduct the correlation test. Between 2016 and 2020, there were 3,398 DHF patients. From January to May, DHF increased. There was a significant correlation between rainfall (r = 0.320; p = 0.005), number of rainy days (r = 0.295; p = 0.020), temperature (r = 0.371; p = 0.040), and humidity (r = 0.221; p = 0.024), wind speed (r= 0.76; p = 0.492), and sunlight (r = 0.008; p = 0.865). Rainfall, the number of rainy days, and temperature were three climatic factors determining the increase in dengue incidence in Palembang.

Climate Variability, Dengue Vector Abundance and Dengue Fever Cases in Dhaka, Bangladesh: A Time-Series Study

Numerous studies on climate change and variability have revealed that these phenomena have noticeable influence on the epidemiology of dengue fever, and such relationships are complex due to the role of the vector—the Aedes mosquitoes. By undertaking a step-by-step approach, the present study examined the effects of climatic factors on vector abundance and subsequent effects on dengue cases of Dhaka city, Bangladesh. Here, we first analyzed the time-series of Stegomyia indices for Aedes mosquitoes in relation to temperature, rainfall and relative humidity for 2002–2013, and then in relation to reported dengue cases in Dhaka. These data were analyzed at three sequential stages using the generalized linear model (GLM) and generalized additive model (GAM). Results revealed strong evidence that an increase in Aedes abundance is associated with the rise in temperature, relative humidity, and rainfall during the monsoon months, that turns into subsequent increases in dengue incidence. Further we found that (i) the mean rainfall and the lag mean rainfall were significantly related to Container Index, and (ii) the Breteau Index was significantly related to the mean relative humidity and mean rainfall. The relationships of dengue cases with Stegomyia indices and with the mean relative humidity, and the lag mean rainfall were highly significant. In examining longitudinal (2001–2013) data, we found significant evidence of time lag between mean rainfall and dengue cases.

A systematic review on AI/ML approaches against COVID-19 outbreak

A pandemic disease, COVID-19, has caused trouble worldwide by infecting millions of people. The studies that apply artificial intelligence (AI) and machine learning (ML) methods for various purposes against the COVID-19 outbreak have increased because of their significant advantages. Although AI/ML applications provide satisfactory solutions to COVID-19 disease, these solutions can have a wide diversity. This increase in the number of AI/ML studies and diversity in solutions can confuse deciding which AI/ML technique is suitable for which COVID-19 purposes. Because there is no comprehensive review study, this study systematically analyzes and summarizes related studies. A research methodology has been proposed to conduct the systematic literature review for framing the research questions, searching criteria and relevant data extraction. Finally, 264 studies were taken into account after following inclusion and exclusion criteria. This research can be regarded as a key element for epidemic and transmission prediction, diagnosis and detection, and drug/vaccine development. Six research questions are explored with 50 AI/ML approaches in COVID-19, 8 AI/ML methods for patient outcome prediction, 14 AI/ML techniques in disease predictions, along with five AI/ML methods for risk assessment of COVID-19. It also covers AI/ML method in drug development, vaccines for COVID-19, models in COVID-19, datasets and their usage and dataset applications with AI/ML.

COVID-19 Outbreak Prediction with Machine Learning

Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and these models are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models need to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak as an alternative to susceptible–infected–recovered (SIR) and susceptible-exposed-infectious-removed (SEIR) models. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP; and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior across nations, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research. This paper further suggests that a genuine novelty in outbreak prediction can be realized by integrating machine learning and SEIR models.

Enhanced Gaussian process regression-based forecasting model for COVID-19 outbreak and significance of IoT for its detection

Virus based epidemic is one of the speedy and widely spread infectious disease which can affect the economy of the country as well as it is life-threatening too. So, there is a need to forecast the epidemic lifespan, which can help us in taking preventive measures and remedial action on time. These preventive measures and corrective action may consist of closing schools, closing malls, closing theaters, sealing of borders, suspension of public services, and suspension of traveling. Resuming such restrictions is depends upon the outbreak momentum and its decay rate. The accurate forecasting of the epidemic lifespan is one of the enormously essential and challenging tasks. It is a challenging task because the lack of knowledge about the novel virus-based diseases and its consequences with complicated societal-governmental factors can influence the widespread of this newly born disease. At this stage, any forecasting can play a vital role, and it will be reliable too. As we know, the novel virus-based diseases are in a growing phase, and we also do not have real-time data samples. Thus, the biggest challenge is to find out the machine learning-based best forecasting model, which could offer better forecasting with the limited training samples. In this paper, the Multi-Task Gaussian Process (MTGP) regression model with enhanced predictions of novel coronavirus (COVID-19) outbreak is proposed. The purpose of the proposed MTGP regression model is to predict the COVID-19 outbreak worldwide. It will help the countries in planning their preventive measures to reduce the overall impact of the speedy and widely spread infectious disease. The result of the proposed model has been compared with the other prediction model to find out its suitability and correctness. In subsequent analysis, the significance of IoT based devices in COVID-19 detection and prevention has been discussed.

COVID-19 Pandemic Prediction for Hungary; A Hybrid Machine Learning Approach

Several epidemiological models are being used around the world to project the number of infected individuals and the mortality rates of the COVID-19 outbreak. Advancing accurate prediction models is of utmost importance to take proper actions. Due to the lack of essential data and uncertainty, the epidemiological models have been challenged regarding the delivery of higher accuracy for long-term prediction. As an alternative to the susceptible-infected-resistant (SIR)-based models, this study proposes a hybrid machine learning approach to predict the COVID-19, and we exemplify its potential using data from Hungary. The hybrid machine learning methods of adaptive network-based fuzzy inference system (ANFIS) and multi-layered perceptron-imperialist competitive algorithm (MLP-ICA) are proposed to predict time series of infected individuals and mortality rate. The models predict that by late May, the outbreak and the total morality will drop substantially. The validation is performed for 9 days with promising results, which confirms the model accuracy. It is expected that the model maintains its accuracy as long as no significant interruption occurs. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research.

The 'lifecycle' of human beings: a call to explore vector-borne diseases from an ecosystem perspective

Background

Dengue virus, an Aedes mosquito-borne flavivirus, is associated with close to 400 million reported infections per annum worldwide. Reduction of dengue virus transmission depends entirely on limiting Aedes breeding or preventing adult female contact with humans. Currently, the World Health Organization promotes the strategic approach of integrated vector management in order to optimise resources for mosquito control.

Main text

Neglected tropical disease researchers focus on geographical zones where the incidence of clinical cases, and prevalence of vectors, are high. In combatting those infectious diseases such as dengue that affect mainly low-income populations in developing regions, a mosquito-centric approach is frequently adopted. This prioritises environmental factors that facilitate or impede the lifecycle progression of the vector. Climatic variables (such as rainfall and wind speed) that impact the vector’s lifecycle either causally or by happenstance also affect the human host’s ‘lifecycle’, but in very different ways. The socioeconomic impacts of the same variables that influence vector control impact host vulnerability but at different points in the human lifecycle to those of the vector. Here, we argue that the vulnerability of the vector and that of the host interact in complex and unpredictable ways that are characteristic of (complex and intransigent) ‘wicked problems’. Moreover, they are treated by public health programs in ways that may ignore this complexity. This opinion draws on recent evidence showing that the best climate predictors of the scale of dengue outbreaks in Bangladesh cannot be explained through a simple vector-to-host causal model.

Conclusions

In mapping causal pathways for vector-borne diseases this article makes a case to elevate the lifecycle of the human host to a level closer in equivalence to that of the vector. Here, we suggest value may be gained from transferring Rittel and Webber’s concept of a wicked (social) problem to dengue, malaria and other mosquito-transmitted public health concerns. This would take a ‘problem definition’ rather than a ‘solution-finding’ approach, particularly when considering problems in which climate impacts simultaneously on human and vector vulnerability.