Dengue in Myanmar: Spatiotemporal epidemiology, association with climate and short-term prediction

Forecasting dengue across Brazil with LSTM neural networks and SHAP-driven lagged climate and spatial effects

BACKGROUND

Dengue fever is a mosquito-borne viral disease that poses significant health risks and socioeconomic challenges in Brazil, necessitating accurate forecasting across its 27 federal states. With the country's diverse climate and geographical spread, effective dengue prediction requires models that can account for both climate variations and spatial dynamics. This study addresses these needs by using Long Short-Term Memory (LSTM) neural networks enhanced with SHapley Additive exPlanations (SHAP) integrating optimal lagged climate variables and spatial influence from neighboring states.

METHOD

An LSTM-based model was developed to forecast dengue cases across Brazil's 27 federal states, incorporating a comprehensive set of climate and spatial variables. SHAP was used to identify and select the most important lagged climate predictors. Additionally, lagged dengue cases from neighboring states were included to capture spatial dependencies. Model performance was evaluated using MAE, MAPE, and CRPS, with comparisons to baseline models.

RESULTS

The LSTM-Climate-Spatial model consistently demonstrated superior performance, effectively integrating temporal, climatic, and spatial information to capture the complex dynamics of dengue transmission. SHAP-enhanced variable selection improved accuracy by focusing on key drivers such as temperature, precipitation and humidity. The inclusion of spatial effects further strengthened forecasts in highly connected states showcasing the model's adaptability and robustness.

CONCLUSION

This study presents a scalable and robust framework for dengue forecasting across Brazil, effectively integrating temporal, climatic, and spatial information into an LSTM-based model. The model's successful application across Brazil's diverse regions demonstrates its generalizability to other dengue-endemic areas with varying climatic and epidemiological conditions. By integrating diverse data sources, the framework captures key transmission drivers, demonstrating the potential of LSTM neural networks for robust predictions. These findings provide valuable insights to enhance public health strategies and outbreak preparedness in Brazil.

Rapid human movement and dengue transmission in Bangladesh: a spatial and temporal analysis based on different policy measures of COVID-19 pandemic and Eid festival

BACKGROUND

Rapid human movement plays a crucial role in the spatial dissemination of the dengue virus. Nevertheless, robust quantification of this relationship using both spatial and temporal models remains necessary. This study aims to explore the spatial and temporal patterns of dengue transmission under various human movement contexts.

METHODS

We obtained district-wise aggregated dengue incidence data from the Management Information System, Directorate General of Health Services of Bangladesh. The stringency index (SI), along with eight individual policy measures (from the Oxford Coronavirus Government Response Tracker database) and six mobility indices (as measured by Google's Community Mobility Reports) were obtained as human movement indicators. A multi-step correlative modelling approach, including various spatial and temporal models, was utilized to explore the associations of dengue incidence with the SI, fourteen human movement indices and the Eid festival.

RESULTS

The global Moran's I indicated significant spatial autocorrelation in dengue incidence during the pre-pandemic (Moran's I: 0.14, P < 0.05) and post-pandemic periods (Moran's I: 0.42, P < 0.01), while the pandemic period (2020-2022) showed weaker, non-significant spatial clustering (Moran's I: 0.07, P > 0.05). Following the pandemic, we identified the emergence of new dengue hotspots. We found a strong negative relationship between monthly dengue incidence and the SI (rspearman: - 0.62, P < 0.01). Through the selection of an optimal Seasonal autoregressive integrated moving average model, we observed that the closure of public transport (β = - 1.66, P < 0.10) and restrictions on internal movement (β = - 2.13, P < 0.10) were associated with the reduction of dengue incidence. Additionally, observed cases were substantially lower than predicted cases during the period from 2020 to 2022. By utilising additional time-series models, we were able to identify in 2023 a rise in dengue incidence associated with the Eid festival intervention, even after adjusting for important climate variables.

CONCLUSIONS

Overall, rapid human movement was found to be associated with increased dengue transmission in Bangladesh. Consequently, the implemention of effective mosquito control interventions prior to large festival periods is necessary for preventing the spread of the disease nationwide. We emphasize the necessity for developing advanced surveillance and monitoring networks to track real-time human movement patterns and dengue incidence.

Performance of Fujifilm Dengue NS1 Antigen Rapid Diagnosis Kit Compared to Quantitative Real-Time Polymerase Chain Reaction

Dengue is a viral infection caused by the dengue virus (DENV), transmitted to humans through the bite of infected Aedes mosquitoes. About half of the world's population is now at risk of dengue, which represents a global public health concern, especially in tropical and subtropical countries. Early detection of the viral infection is crucial to manage the disease; hence, effective rapid diagnostic tests are essential. In this study, we evaluated the performance between the new Fujifilm Dengue non-structural antigen diagnosis kit (FF NS1 kit) and the SD Bioline NS1 antigen test kit (SD NS1 kit) against the quantitative real-time polymerase chain reaction (qRT-PCR) assays. The 140 acute serum samples collected from the Yangon General Hospital and Yangon Children's Hospital, Myanmar, from 2017 to 2019 were characterised by the three assays. With the qRT-PCR as the standard, the FF NS1 kit and the SD NS1 kit exhibited sensitivity of 94.3% and 88.6%, respectively, and specificity of 100% in both kits. Moreover, the positivity rates of the FF NS1 kit and the SD NS1 kit were 97.5% and 95% in primary infection and 90% and 80% in secondary infection, respectively. Our overall results suggest that the FF NS1 kit is reliable and accurate for detecting DENV infection.

Unraveling Dengue Virus Diversity in Asia: An Epidemiological Study through Genetic Sequences and Phylogenetic Analysis

Dengue virus (DENV) is the causative agent of dengue. Although most infected individuals are asymptomatic or present with only mild symptoms, severe manifestations could potentially devastate human populations in tropical and subtropical regions. In hyperendemic regions such as South Asia and Southeast Asia (SEA), all four DENV serotypes (DENV-1, DENV-2, DENV-3, and DENV-4) have been prevalent for several decades. Each DENV serotype is further divided into multiple genotypes, reflecting the extensive diversity of DENV. Historically, specific DENV genotypes were associated with particular geographical distributions within endemic regions. However, this epidemiological pattern has changed due to urbanization, globalization, and climate change. This review comprehensively traces the historical and recent genetic epidemiology of DENV in Asia from the first time DENV was identified in the 1950s to the present. We analyzed envelope sequences from a database covering 16 endemic countries across three distinct geographic regions in Asia. These countries included Bangladesh, Bhutan, India, Maldives, Nepal, Pakistan, and Sri Lanka from South Asia; Cambodia, Laos, Myanmar, Thailand, and Vietnam from Mainland SEA; and Indonesia, the Philippines, Malaysia, and Singapore from Maritime SEA. Additionally, we describe the phylogenetic relationships among DENV genotypes within each serotype, along with their geographic distribution, to enhance the understanding of DENV dynamics.

School and community driven dengue vector control and monitoring in Myanmar: Study protocol for a cluster randomized controlled trial

Background

Dengue is the most common and widespread mosquito-borne arboviral disease globally estimated to cause >390 million infections and >20,000 deaths annually. There are no effective preventive drugs and the newly introduced vaccines are not yet available. Control of dengue transmission still relies primarily on mosquito vector control. Although most vector control methods currently used by national dengue control programs may temporarily reduce mosquito populations, there is little evidence that they affect transmission. There is an urgent need for innovative, participatory, effective, and locally adapted approaches for sustainable vector control and monitoring in which students can be particularly relevant contributors and to demonstrate a clear link between vector reduction and dengue transmission reduction, using tools that are inexpensive and easy to use by local communities in a sustainable manner.

Methods

Here we describe a cluster randomized controlled trial to be conducted in 46 school catchment areas in two townships in Yangon, Myanmar. The outcome measures are dengue cases confirmed by rapid diagnostic test in the townships, dengue incidence in schools, entomological indices, knowledge, attitudes and practice, behavior, and engagement.

Conclusions

The trial involves middle school students that positions them to become actors in dengue knowledge transfer to their communities and take a leadership role in the delivery of vector control interventions and monitoring methods. Following this rationale, we believe that students can become change agents of decentralized vector surveillance and sustainable disease control in line with recent new paradigms in integrated and participatory vector surveillance and control. This provides an opportunity to operationalize transdisciplinary research towards sustainable health development. Due to the COVID-19 pandemic and political instability in Myanmar the project has been terminated by the donor, but the protocol will be helpful for potential future implementation of the project in Myanmar and/or elsewhere.Registration: This trial was registered in the ISRCTN Registry on 31 May 2022 ( https://doi.org/10.1186/ISRCTN78254298).