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.
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.
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).
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.
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.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Earthworms are a resilient group of species thriving in varied habitats through feeding on decaying organic matter, and are therefore predicted to survive an abrupt sunlight reduction scenario, e.g., ...a nuclear winter. In this study, the feasibility and cost-effectiveness of foraging earthworms to reduce global famine in such a scenario with or without global catastrophic infrastructure loss was considered. Previously reported earthworm extraction methods (digging and sorting, vermifuge application, worm grunting, and electroshocking) were analysed, along with scalability, climate-related barriers to foraging, and pre-consumption processing requirements. Estimations of the global wild earthworm resource suggest it could provide three years of the protein needs of the current world human population, at a median cost of USD 353·kg−1 dry carbohydrate equivalent or a mean cost of USD 1200 (90% confidence interval: 32–8500)·kg−1 dry carbohydrate equivalent. At this price, foraging would cost a median of USD 185 to meet one person’s daily caloric requirement, or USD 32 if targeted to high-earthworm-biomass and low-labour-cost regions; both are more expensive than most existing resilient food solutions. While short-term targeted foraging could still be beneficial in select areas given its quick ramp-up, earthworms may bioaccumulate heavy metals, radioactive material, and other contaminants, presenting a significant health risk. Overall, earthworm foraging cannot be recommended as a scalable resilient food solution unless further research addresses uncertainties regarding cost-effectiveness and food safety.
No other significant internal derangement of the knee was noted on arthroscopy before revision reconstruction of the ACL using ipsilateral hamstring tendon grafts was undertaken.
The authors present a case of bilateral total hip replacements (THRs) in a 56-year-old patient with arthrogryposis multiplex congenita (AMC). The considerations for the perioperative period and the ...outcome are discussed. Preoperative planning included an anaesthetic review and availability of fiberoptic intubation due to poor mouth opening. Perioperatively, contractures can make positioning and exposure difficult but in this case a standard posterior approach was taken. Particular attention was given to soft tissue balancing given the theoretical risk of dislocation. There were no perioperative complications. Postoperatively there has been improvement in pain and hip scores but the patient has failed to return to work. Objective improvements in range of motion (ROM) have not been made. This experience suggests THR is a safe and effective treatment for osteoarthritic hip pain in patients with AMC but patients should be informed that ROM is unlikely to improve.
Diarrhoea disease pose significant threats to national morbidity and mortality in Vietnam, especially on children below 5 years old. Being a climate sensitive disease, it has strong links to various ...meteorological factors like rainfall. Together with global climate changes, these meteorological factors have contributed the increasing of Diarrhoea incidence in Vietnam. Thus, having an effective early warning system is becoming an urgent need. However, it has not been paid enough attention with very few research works, mainly focusing on quantilizing the relationships among climate and diarrhoea incidence using linear regressions. Exploring more sophisticated machine learning techniques is therefore an interesting work towards more efficient and effective warning systems. In this paper, different types of prediction models from traditional to deep learning methods are studied for predicting Diarrhoea rate in six provinces in Vietnam in both long- and short-terms. Experiments show that LSTM-ATT acquires better performance compared to all other approaches like SARIMA, CNN, LSTM, Transformer, and Prophet.
We compared the use of patient-controlled analgesia (PCA) morphine and p.r.n. intravenous morphine in an intensive care unit setting. Thirty-eight patients scheduled for admission to the Surgical ...Intensive Care Unit (SICU) were prospectively randomized to either a PCA group or a p.r.n. intravenous morphine group. Assessments included pain and sedation scores, respiratory rates, pulse oximetry, and morphine utilization. PCA was found to be comparable in safety and efficacy to nurse-administered morphine in the intensive care environment. An unexpected finding was the higher initial morphine utilization seen in the patients utilizing PCA.
PDF
