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.

The first community outbreak of COVID-19 in Viet Nam: description and lessons learned.

OBJECTIVE: At the time of this study, the prevention of novel coronavirus disease 2019 (COVID-19) relied solely on nonpharmaceutical interventions. Implementation of these interventions is not always optimal and, consequently, several cases were imported into non-epidemic areas and led to large community outbreaks. This report describes the characteristics of the first community outbreak of COVID-19 in Viet Nam and the intensive preventive measures taken in response. METHODS: Cases were detected and tested for SARS-CoV-2 by real-time reverse transcriptase polymerase chain reaction. Contact tracing and active surveillance were conducted to identify suspected cases and individuals at risk. Clinical symptoms were recorded using a standardized questionnaire. RESULTS: In Vinh Phuc province from 20 January to 3 March 2020, there were 11 confirmed cases among 158 suspected cases and 663 contacts. Nine of the confirmed cases (81.8%) had mild symptoms at the time of detection and two (18.2%) were asymptomatic; none required admission to an intensive care unit. Five prevention and control measures were implemented, including quarantining a community of 10 645 individuals for 20 days. The outbreak was successfully contained as of 13 February 2020. DISCUSSION: In the absence of specific interventions, the intensive use of combined preventive measures can mitigate the spread of COVID-19. The lessons learned may be useful for other communities.

Burden of Influenza-Associated Respiratory Hospitalizations, Vietnam, 2014-2016.

Influenza burden estimates are essential to informing prevention and control policies. To complement recent influenza vaccine production capacity in Vietnam, we used acute respiratory infection (ARI) hospitalization data, severe acute respiratory infection (SARI) surveillance data, and provincial population data from 4 provinces representing Vietnam's major regions during 2014-2016 to calculate provincial and national influenza-associated ARI and SARI hospitalization rates. We determined the proportion of ARI admissions meeting the World Health Organization SARI case definition through medical record review. The mean influenza-associated hospitalization rates per 100,000 population were 218 (95% uncertainty interval [UI] 197-238) for ARI and 134 (95% UI 119-149) for SARI. Influenza-associated SARI hospitalization rates per 100,000 population were highest among children <5 years of age (1,123; 95% UI 946-1,301) and adults >65 years of age (207; 95% UI 186-227), underscoring the need for prevention and control measures, such as vaccination, in these at-risk populations.

Novel Mutation of SARS-CoV-2, Vietnam, July 2020.

A cluster of severe acute respiratory syndrome coronavirus 2 infections in Danang, Vietnam, began July 25, 2020, and resulted in 551 confirmed cases and 35 deaths as of February 2021. We analyzed 26 sequences from this cluster and identified a novel shared mutation in nonstructural protein 9, suggesting a single introduction into Vietnam.

The First 100 Days of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) Control in Vietnam.

BACKGROUND: One hundred days after severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) was first reported in Vietnam on 23 January, 270 cases were confirmed, with no deaths. We describe the control measures used by the government and their relationship with imported and domestically acquired case numbers, with the aim of identifying the measures associated with successful SARS-CoV-2 control. METHODS: Clinical and demographic data on the first 270 SARS-CoV-2 infected cases and the timing and nature of government control measures, including numbers of tests and quarantined individuals, were analyzed. Apple and Google mobility data provided proxies for population movement. Serial intervals were calculated from 33 infector-infectee pairs and used to estimate the proportion of presymptomatic transmission events and time-varying reproduction numbers. RESULTS: A national lockdown was implemented between 1 and 22 April. Around 200 000 people were quarantined and 266 122 reverse transcription polymerase chain reaction (RT-PCR) tests conducted. Population mobility decreased progressively before lockdown. In total, 60% (163/270) of cases were imported; 43% (89/208) of resolved infections remained asymptomatic for the duration of infection. The serial interval was 3.24 days, and 27.5% (95% confidence interval [CI], 15.7%-40.0%) of transmissions occurred presymptomatically. Limited transmission amounted to a maximum reproduction number of 1.15 (95% CI, .·37-2.·36). No community transmission has been detected since 15 April. CONCLUSIONS: Vietnam has controlled SARS-CoV-2 spread through the early introduction of mass communication, meticulous contact tracing with strict quarantine, and international travel restrictions. The value of these interventions is supported by the high proportion of asymptomatic and imported cases, and evidence for substantial presymptomatic transmission.

Transmission of SARS-CoV 2 During Long-Haul Flight.

To assess the role of in-flight transmission of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), we investigated a cluster of cases among passengers on a 10-hour commercial flight. Affected persons were passengers, crew, and their close contacts. We traced 217 passengers and crew to their final destinations and interviewed, tested, and quarantined them. Among the 16 persons in whom SARS-CoV-2 infection was detected, 12 (75%) were passengers seated in business class along with the only symptomatic person (attack rate 62%). Seating proximity was strongly associated with increased infection risk (risk ratio 7.3, 95% CI 1.2-46.2). We found no strong evidence supporting alternative transmission scenarios. In-flight transmission that probably originated from 1 symptomatic passenger caused a large cluster of cases during a long flight. Guidelines for preventing SARS-CoV-2 infection among air passengers should consider individual passengers' risk for infection, the number of passengers traveling, and flight duration.

Plans for Nationwide Serosurveillance Network in Vietnam.

In recent years, serosurveillance has gained momentum as a way of determining disease transmission and immunity in populations, particularly with respect to vaccine-preventable diseases. At the end of 2017, the Oxford University Clinical Research Unit and the National Institute of Hygiene and Epidemiology held a meeting in Vietnam with national policy makers, researchers, and international experts to discuss current seroepidemiologic projects in Vietnam and future needs and plans for nationwide serosurveillance. This report summarizes the meeting and the plans that were discussed to set up nationwide serosurveillance in Vietnam.

Litchi-associated acute encephalitis in children, Northern Vietnam, 2004-2009.

Since the end of the 1990s, unexplained outbreaks of acute encephalitis in children coinciding with litchi harvesting (May-July) have been documented in the Bac Giang Province in northern Vietnam. A retrospective ecologic analysis of data for 2004-2009 involving environmental, agronomic, and climatic factors was conducted to investigate the suspected association between the outbreaks and litchi harvesting. The clinical, biological, and immunologic characteristics of the patients suggested a viral etiology. The ecologic study revealed an independent association between litchi plantation surface proportion and acute encephalitis incidence: Incidence rate ratios were 1.52 (95% CI 0.90-2.57), 2.94 (95% CI 1.88-4.60), and 2.76 (95% CI 1.76-4.32) for second, third, and fourth quartiles, respectively, compared with the lowest quartile. This ecologic study confirmed the suspected association between incidence of acute encephalitis and litchi plantations and should be followed by other studies to identify the causative agent for this syndrome.