Dengue Prediction in Latin America Using Machine Learning and the One Health Perspective: A Literature Review

Delineating dengue risk zones in Jaipur: An interdisciplinary approach to inform public health strategies

Dengue fever (DF) is a pervasive public health concern in tropical climates, with densely populated regions, such as India, disproportionately affected. Addressing this issue requires a multifaceted understanding of the environmental and sociocultural factors that contribute to the risk of dengue infection. This study aimed to identify high-risk zones for DF in Jaipur, Rajasthan, India, by integrating physical, demographic, and epidemiological data in a comprehensive risk analysis framework. We investigated environmental variables, such as soil type and plant cover, to characterize the potential habitats of Aedes aegypti, the primary dengue vector. Concurrently, demographic metrics were evaluated to assess the population's susceptibility to dengue outbreaks. High-risk areas were systematically identified through a comparative analysis that integrated population density and incidence rates per ward. The results revealed a significant correlation between high population density and an increased risk of dengue, predominantly facilitated by vertical transmission. Spatially, these high-risk zones are concentrated in the northern and southern sectors of Jaipur, with the northern and southwestern wards exhibiting the most acute risk profiles. This study underscores the importance of targeted public health interventions and vaccination campaigns in vulnerable areas. It further lays the groundwork for future research to evaluate the effectiveness of such interventions, thereby contributing to the development of robust evidence-based strategies for dengue risk mitigation.

Spatiotemporal models of dengue epidemiology in the Philippines: Integrating remote sensing and interpretable machine learning

Previous dengue epidemiological analyses have been limited in spatiotemporal extent or covariate dimensions, the latter neglecting the multifactorial nature of dengue. These constraints, caused by rigid and traditional statistical tools which collapse amidst 'Big Data', prompt interpretable machine-learning (iML) approaches. Predicting dengue incidence and mortality in the Philippines, a data-limited yet high-burden country, the mlr3 universe of R packages was used to build and optimize ML models based on remotely sensed provincial and dekadal 3 NDVI and 9 rainfall features from 2016 to 2020. Between two tasks, models differ across four random forest-based learners and two clustering strategies. Among 16 candidates, rfsrc-year-case and ranger-year-death significantly perform best for predicting dengue incidence and mortality, respectively. Therefore, temporal clustering yields the best models, reflective of dengue seasonality. The two best models were subjected to tripartite global exploratory model analyses, which encompass model-agnostic post-hoc methods such as Permutation Feature Importance (PFI) and Accumulated Local Effects (ALE). PFI reveals that the models differ in their important explanatory aspect, rainfall for rfsrc-year-case and NDVI for ranger-year-death, among which long-term average (lta) features are most relevant. Trend-wise, ALE reveals that average incidence predictions are positively associated with 'Rain.lta', reflective of dengue cases peaking during the wet season. In contrast, those for mortality are negatively associated with 'NDVI.lta', reflective of urban spaces driving dengue-related deaths. By technologically addressing the challenges of the human-animal-ecosystem interface, this study adheres to the One Digital Health paradigm operationalized under Sustainable Development Goals (SDGs). Leveraging data digitization and predictive modeling for epidemiological research paves SDG 3, which prioritizes holistic health and well-being.

Compulsory Vaccination Coverage in 12 Sub-Saharan African Countries Two Years Following the COVID-19 Pandemic

The coronavirus disease 2019 (COVID-19) pandemic is a global threat, challenging health services' provision and utilization. This study aimed to assess compulsory vaccination coverage in 12 Sub-Saharan African countries two years following the COVID-19 pandemic using the Health Belief Model. A cross-sectional survey was conducted from November 1 to December 15, 2022. Multivariate logistic regression was conducted to identify the determinants of vaccination coverage. Among the 5032 respondents, 73.1% reported that their children received compulsory vaccination. The lowest coverage was observed in Ghana (36.5%), while the highest was in Burkina Faso and Congo (92.0%). Factors associated with non-vaccination included older mothers (adjusted odds ratio (AOR) = 1.04, 95%CI: 1.03-1.05), lower mothers' education, older children (AOR = 0.76, 95%CI: 0.60-0.96), children with chronic illnesses (AOR = 0.55, 95%CI: 0.45-0.66), and difficult accessibility to healthcare facilities (AOR = 11.27, 95%CI: 9.48-13.44). Low perceived risk, in which non-vaccinated children were believed to be at no higher risk for infectious diseases and the disease severity would not worsen among non-vaccinated children, increased the likelihood of non-vaccination (AOR = 2.29, 95%CI: 1.75-2.99 and AOR = 2.12, 95%CI: 1.64-2.73, respectively). Perceiving vaccines as unnecessary, and needless for breastfed babies increased the probability of non-vaccination (AOR = 1.38, 95%CI: 1.10-1.73 and AOR = 1.69, 95%CI: 1.31-2.19, respectively). Higher odds of non-vaccination were found when the provision of vaccine information did not motivate parents to vaccinate their children (AOR = 4.29, 95%CI: 3.15-5.85). Conversely, believing that vaccines were safe for children decreased the odds of non-vaccination (AOR = 0.72, 95%CI: 0.58-0.88). Parental perceptions and concerns should be considered in interventions aiming to increase compulsory vaccine acceptance and coverage.

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.

The One Health Concept

The concept of One Health has been developed as the appreciation that human health is intricately connected to those of other animals and the environment that they inhabit. In recent years, the COVID-19 pandemic and noticeable effects of climate change have encouraged national and international cooperation to apply One Health strategies to address key issues of health and welfare. The United Nations (UN) Sustainable Development Goals have established targets for health and wellbeing, clean water and sanitation, climate action, as well as sustainability in marine and terrestrial ecosystems. The One Health Quadripartite comprises the World Health Organization (WHO), the World Organization for Animal Health (WOAH-formerly OIE), the United Nations Food and Agriculture Organization (FAO) and the United Nations Environment Programme (UNEP). There are six areas of focus which are Laboratory services, Control of zoonotic diseases, Neglected tropical diseases, Antimicrobial resistance, Food safety and Environmental health. This article discusses the concept of One Health by considering examples of infectious diseases and environmental issues under each of those six headings. Biomedical Scientists, Clinical Scientists and their colleagues working in diagnostic and research laboratories have a key role to play in applying the One Health approach to key areas of healthcare in the 21st Century.

Immune system gene polymorphisms associated with severe dengue in Latin America: a systematic review

One of the main challenges in the clinical management of dengue is the early identification of cases that could progress to severe forms of the disease. A biomarker that may enable this identification is the presence of genetic polymorphisms in genes associated with immune responses. The objective of this study was to perform a systematic review of the Latin American literature on these genes. An electronic literature search was carried out in PubMed, Scopus, Lilacs, and the Virtual Health Library, and reference lists of systematic reviews in the area. Case-control studies conducted in Latin American countries examining at least one form of genetic polymorphism related to immune responses against severe dengue were included. In total, 424 articles were identified and 26 were included in this systematic review. Of the 26 selected articles, 16 reported polymorphisms associated with the risk of developing severe dengue (Risk); Similarly, 16 articles reported polymorphisms associated with a decreased risk of severe dengue (Protective). The final analysis revealed that multiple polymorphisms in immune system genes were early markers of the progression of dengue in Latin Americans and found that polymorphisms of the TNF-alpha gene may have a critical role in dengue pathogenesis.

A machine learning model to assess potential misdiagnosed dengue hospitalization

Dengue, like other arboviruses with broad clinical spectra, can easily be misdiagnosed as other infectious diseases due to the overlap of signs and symptoms. During large outbreaks, severe dengue cases have the potential to overwhelm the health care system and understanding the burden of dengue hospitalizations is therefore important to better allocate medical care and public health resources. A machine learning model that used data from the Brazilian public healthcare system database and the National Institute of Meteorology (INMET) was developed to estimate potential misdiagnosed dengue hospitalizations in Brazil. The data was modeled into a hospitalization level linked dataset. Then, Random Forest, Logistic Regression and Support Vector Machine algorithms were assessed. The algorithms were trained by dividing the dataset in training/test set and performing a cross validation to select the best hyperparameters in each algorithm tested. The evaluation was done based on accuracy, precision, recall, F1 score, sensitivity, and specificity. The best model developed was Random Forest with an accuracy of 85% on the final reviewed test. This model shows that 3.4% (13,608) of all hospitalizations in the public healthcare system from 2014 to 2020 could have been dengue misdiagnosed as other diseases. The model was helpful in finding potentially misdiagnosed dengue and might be a useful tool to help public health decision makers in planning resource allocation.

Dengue as a Disease Threatening Global Health: A Narrative Review Focusing on Latin America and Brazil

Arboviruses constitute the largest known group of viruses. These viruses are the etiological agents of pathologies known as arboviruses, with dengue being one of the most prevalent. Dengue has resulted in important socioeconomic burdens placed on different countries around the world, including those in Latin America, especially Brazil. Thus, this work intends to carry out a narrative-based review of the literature, conducted using a study of the secondary data developed through a survey of scientific literature databases, and to present the situation of dengue, particularly its distribution in these localities. Our findings from the literature demonstrate the difficulties that managers face in controlling the spread of and planning a response against dengue, pointing to the high cost of the disease for public coffers, rendering the resources that are already limited even scarcer. This can be associated with the different factors that affect the spread of the disease, including ecological, environmental, and social factors. Thus, in order to combat the disease, it is expected that targeted and properly coordinated public policies need to be adopted not only in specific localities, but also globally.

Mapping the Spatiotemporal Distribution of Bovine Rabies in Colombia, 2005-2019

Introduction: Rabies is caused by a virus belonging to the genus Lyssavirus and family Rhabdoviridae, which can infect any mammal including humans. Hematophagous, fructivorous, and insectivorous bats have become the main reservoir of sylvatic rabies in Latin America. In the sylvatic cycle, hematophagous bats are usually the main reservoir. In contrast, dogs and cats fulfil this critical role in the urban cycle. However, in rural areas, the most affected animals are bovines. They show clinical signs such as behavioural changes, hypersalivation, muscle tremors, spasms caused by extensive damage to the central nervous system, and death from respiratory paralysis. Objective: To describe the spatiotemporal distribution of bovine rabies in Colombia from 2005 to 2019. Methods: Retrospective cross-sectional descriptive observational study, based on the monthly reports of the Colombian Agricultural Institute (ICA) on the surveillance of bovine rabies in Colombia from 2005 to 2019, retrieved from its official website. The data were converted to databases in Microsoft Access 365®. Multiple epidemiological maps were developed with the GIS software Kosmo RC1® 3.0 coupled to the shape files (.shp) of all the country’s municipalities. Results: During the study period, 4888 cases of rabies were confirmed in cattle, ranging from a peak of 542 cases (11.1%) in 2014 to 43 in 2019 (0.88%). From 2014 to 2019, there has been a significant reduction in the annual national number of cases (r2 = 0.9509, p < 0.05). In 2019, 32.6% of the cases occurred in January, and 48.8% occurred in the department of Sucre. In 2009, the maximum number of spatial clusters (13) occurred in the Orinoquia region, where other clusters were also identified in 2005, 2006 and 2008. In 2018, 98 outbreaks were identified that led to the death of cattle and other animals, 28.6% of them in the department of Sucre. In the first half of 2019, of 38 outbreaks, 55.2% were identified in Sucre. Conclusions: It is necessary to review the current national program for the prevention and control of rabies in cattle, incorporating concepts from the ecology of bats, as well as the prediction of contagion waves of geographical and temporal spread in the context of the OneHealth Approach. Sylvatic rabies remains a threat in Colombia that requires further study.