Effects of Heatwaves on Hospital Admissions for Cardiovascular and Respiratory Diseases, in Southern Vietnam, 2010-2018: Time Series Analysis.

This study investigated the associations between heatwaves and daily hospital admissions for cardiovascular and respiratory diseases in two provinces in Viet Nam known to be vulnerable to droughts during 2010-2018. This study applied a time series analysis with data extracted from the electronic database of provincial hospitals and meteorological stations from the corresponding province. To eliminate over-dispersion, this time series analysis used Quasi-Poisson regression. The models were controlled for the day of the week, holiday, time trend, and relative humidity. Heatwaves were defined as the maximum temperature exceeding P90th over the period from 2010 to 2018 during at least three consecutive days. Data from 31,191 hospital admissions for respiratory diseases and 29,056 hospitalizations for cardiovascular diseases were investigated in the two provinces. Associations between hospital admissions for respiratory diseases and heatwaves in Ninh Thuan were observed at lag 2, with excess risk (ER = 8.31%, 95% confidence interval: 0.64-16.55%). However, heatwaves were negatively associated with cardiovascular diseases in Ca Mau, which was determined amongst the elderly (age above 60), ER = -7.28%, 95%CI: -13.97--0.08%. Heatwaves can be a risk factor for hospital admission due to respiratory diseases in Vietnam. Further studies need to be conducted to assert the link between heat waves and cardiovascular diseases.

Deep learning models for forecasting dengue fever based on climate data in Vietnam.

BACKGROUND: Dengue fever (DF) represents a significant health burden in Vietnam, which is forecast to worsen under climate change. The development of an early-warning system for DF has been selected as a prioritised health adaptation measure to climate change in Vietnam. OBJECTIVE: This study aimed to develop an accurate DF prediction model in Vietnam using a wide range of meteorological factors as inputs to inform public health responses for outbreak prevention in the context of future climate change. METHODS: Convolutional neural network (CNN), Transformer, long short-term memory (LSTM), and attention-enhanced LSTM (LSTM-ATT) models were compared with traditional machine learning models on weather-based DF forecasting. Models were developed using lagged DF incidence and meteorological variables (measures of temperature, humidity, rainfall, evaporation, and sunshine hours) as inputs for 20 provinces throughout Vietnam. Data from 1997-2013 were used to train models, which were then evaluated using data from 2014-2016 by Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). RESULTS AND DISCUSSION: LSTM-ATT displayed the highest performance, scoring average places of 1.60 for RMSE-based ranking and 1.95 for MAE-based ranking. Notably, it was able to forecast DF incidence better than LSTM in 13 or 14 out of 20 provinces for MAE or RMSE, respectively. Moreover, LSTM-ATT was able to accurately predict DF incidence and outbreak months up to 3 months ahead, though performance dropped slightly compared to short-term forecasts. To the best of our knowledge, this is the first time deep learning methods have been employed for the prediction of both long- and short-term DF incidence and outbreaks in Vietnam using unique, rich meteorological features. CONCLUSION: This study demonstrates the usefulness of deep learning models for meteorological factor-based DF forecasting. LSTM-ATT should be further explored for mitigation strategies against DF and other climate-sensitive diseases in the coming years.

Vietnam Climate Change and Health Vulnerability and Adaptation Assessment, 2018.

BACKGROUND: The Global Climate Risk Index 2020 ranked Vietnam as the sixth country in the world most affected by climate variability and extreme weather events over the period 1999-2018. Sea level rise and extreme weather events are projected to be more severe in coming decades, which, without additional action, will increase the number of people at risk of climate-sensitive diseases, challenging the health system. This article summaries the results of a health vulnerability and adaptation (V&A) assessment conducted in Vietnam as evidences for development of the National Climate Change Health Adaptation Plan to 2030. METHODS: The assessment followed the first 4 steps outlined in the World Health Organization's Guidelines in conducting "Vulnerability and Adaptation Assessments." A framework and list of indicators were developed for semi-quantitative assessment for the period 2013 to 2017. Three sets of indicators were selected to assess the level of (1) exposure to climate change and extreme weather events, (2) health sensitivity, and (3) adaptation capacity. The indicators were rated and analyzed using a scoring system from 1 to 5. RESULTS: The results showed that climate-sensitive diseases were common, including dengue fever, diarrheal, influenza, etc, with large burdens of disease that are projected to increase. From 2013 to 2017, the level of "exposure" to climate change-related hazards of the health sector was "high" to "very high," with an average score from 3.5 to 4.4 (out of 5.0). For "health sensitivity," the scores decreased from 3.8 in 2013 to 3.5 in 2017, making the overall rating as "high." For "adaptive capacity," the scores were from 4.0 to 4.1, which meant adaptive capacity was "very low." The overall V&A rating in 2013 was "very high risk" (score 4.1) and "high risk" with scores of 3.8 in 2014 and 3.7 in 2015 to 2017. CONCLUSIONS: Adaptation actions of the health sector are urgently needed to reduce the vulnerability to climate change in coming decades. Eight adaptation solutions, among recommendations of V&A assessment, were adopted in the National Health Climate Change Adaptation Plan.

Spatiotemporal analysis of historical records (2001-2012) on dengue fever in Vietnam and development of a statistical model for forecasting risk.

BACKGROUND: Dengue fever is the most widespread infectious disease of humans transmitted by Aedes mosquitoes. It is the leading cause of hospitalization and death in children in the Southeast Asia and western Pacific regions. We analyzed surveillance records from health centers in Vietnam collected between 2001-2012 to determine seasonal trends, develop risk maps and an incidence forecasting model. METHODS: The data were analyzed using a hierarchical spatial Bayesian model that approximates its posterior parameter distributions using the integrated Laplace approximation algorithm (INLA). Meteorological, altitude and land cover (LC) data were used as predictors. The data were grouped by province (n = 63) and month (n = 144) and divided into training (2001-2009) and validation (2010-2012) sets. Thirteen meteorological variables, 7 land cover data and altitude were considered as predictors. Only significant predictors were kept in the final multivariable model. Eleven dummy variables representing month were also fitted to account for seasonal effects. Spatial and temporal effects were accounted for using Besag-York-Mollie (BYM) and autoregressive (1) models. Their levels of significance were analyzed using deviance information criterion (DIC). The model was validated based on the Theil's coefficient which compared predicted and observed incidence estimated using the validation data. Dengue incidence predictions for 2010-2012 were also used to generate risk maps. RESULTS: The mean monthly dengue incidence during the period was 6.94 cases (SD 14.49) per 100,000 people. Analyses on the temporal trends of the disease showed regular seasonal epidemics that were interrupted every 3 years (specifically in July 2004, July 2007 and September 2010) by major fluctuations in incidence. Monthly mean minimum temperature, rainfall, area under urban settlement/build-up areas and altitude were significant in the final model. Minimum temperature and rainfall had non-linear effects and lagging them by two months provided a better fitting model compared to using unlagged variables. Forecasts for the validation period closely mirrored the observed data and accurately captured the troughs and peaks of dengue incidence trajectories. A favorable Theil's coefficient of inequality of 0.22 was generated. CONCLUSIONS: The study identified temperature, rainfall, altitude and area under urban settlement as being significant predictors of dengue incidence. The statistical model fitted the data well based on Theil's coefficient of inequality, and risk maps generated from its predictions identified most of the high-risk provinces throughout the country.

Modeling ENSO impact on rice production in the Mekong River Delta.

The Mekong River Delta is the rice production hub in South-east Asia and has a key role in determining rice prices in the world market. The increasing variability in the local climate due to global climate changes and the increasing severity of the ENSO phenomenon threatens rice production in the region, which has consequences for local and global food security. Though existing mapping efforts delineate the consequences of saline water intrusion during El Niño and flooding events during La Niña in the basin, research to predict future impacts in rice production is rather limited. The current work uses ORYZA, an ecophysiological model, combined with historical climate data, climate change scenarios RCP4.5 and 8.5 and climate-related risk maps to project the aggregate productivity and rice production impacts by the year 2050. Results show that in years of average salinity intrusion and flooding, the winter-spring rice crop in the MRD would experience an average annual decrease of 720,450 tons for 2020-2050 under the RCP4.5 scenario compared to the baseline of 2005-2016 average and another 1.17 million tons under the RCP8.5 scenario. The autumn-winter crop would decrease by 331,480 tons under RCP4.5 and 462,720 tons under RCP8.5. In years of severe salinity intrusion and flooding, the winter-spring rice crop would decrease by 2.13 million tons (10.29% lower than the projection for an average year) under RCP4.5 and 2.5 million tons (13.62%) under RCP8.5. Under severe conditions, the autumn-winter crop would have an average decrease of 1.3 million tons (7.36%) under RCP4.5 and 1.4 million tons (10.88%) for the RCP8.5 scenario. Given that most of the rice produced in this area is exported, a decline in rice supply at this scale would likely have implications on the global market price of rice affecting global food security. Such decline will also have implications for the rural economy and food security of Vietnam. Suggestions for corrective measures to reduce the impacts are briefly discussed.