Background: Dengue Fever/Dengue Hemorrhagic Fever (DF/DHF) has emerged as one of the most important public health concerns in Viet Nam in recent years. Key breeding containers plays an important role in driving dengue vector control in the public. Objectives: The research was conducted to discover the dengue situation, its vectors and key containers to make relevant recommendations in reducing effectively the vector population. Subjects and methods: Two hundred households in two communes of Nam Dinh province (100 in each studied commune) were selected randomly. Vectors collected from the field were identified using mosquito key. The number of dengue larvae and mosquitoes were directly counted or adjustment methods were used to estimate the true number in each type of water storage facility. Results: In Minh Thuan commune, Ae. albopictus larvae were mainly concentrated in jars (49%) and discards (59%), most of Ae. aegypti was found in cement tanks with a volume more than 500L (72%). In Trung Dong commune, larvae of Ae. albopictus concentrated in jars (40%) and discards (25%) and aquariums (15%), while most of the Ae. aegypti larvae was discovered in cement tanks with volumes more than 500L (86%). Mosquito density index of Ae. albopictus in Trung Dong and Minh Thuan communes was 0.56 and 0.38, respectively. The Aedes larvae, houses for larvae and Breteau index were nearly at the threshold of dengue epidemic occurrence for Ae. aegypti and over a certain threshold for Ae. albopictus. Some recommendations were provided to help reduce the dengue vectors. Conclusion: Investigation of key mosquito larvae in water containers was useful in driving the effective dengue vector control. Further studies are required to evaluate the impact and methods to manage water containers in the local area.
Dengue fever ; mosquito ; vector control

Background: Cardiovascular diseases belong to the top three leading causes of mortality in the Philippines with 17.8 % of the total deaths. Lifestyle-related habits such as alcohol consumption, smoking, poor diet and nutrition, high sedentary behavior, overweight, and obesity have been increasingly implicated in the high rates of heart disease among Filipinos leading to a significant burden to the country's healthcare system. The objective of this study was to predict the presence of heart disease using various machine learning algorithms (support vector machine, naïve Bayes, random forest, logistic regression, decision tree, and adaptive boosting) evaluated on an anonymized publicly available cardiovascular disease dataset. Methodology: Various machine learning algorithms were applied on an anonymized publicly available cardiovascular dataset from a machine learning data repository (IEEE Dataport). A web-based application system named Heart Alert was developed based on the best machine learning model that would predict the risk of developing heart disease. An assessment of the effects of different optimization techniques as to the imputation methods (mean, median, mode, and multiple imputation by chained equations) and as to the feature selection method (recursive feature elimination) on the classification performance of the machine learning algorithms was made. All simulation experiments were implemented via Python 3.8 and its machine learning libraries (Scikit-learn, Keras, Tensorflow, Pandas, Matplotlib, Seaborn, NumPy). Results: The support vector machine without imputation and feature selection obtained the highest performance metrics (90.2% accuracy, 87.7% sensitivity, 93.6% specificity, 94.9% precision, 91.2% F1-score and an area under the receiver operating characteristic curve of 0.902 ) and was used to implement the heart disease prediction system (Heart Alert). Following very closely were random forest with mean or median imputation and logistic regression with mode imputation, all having no feature selection which also performed well. Conclusion The performance of the best four machine learning models suggests that for this dataset, imputation technique for missing values may or may not be done. Likewise, recursive feature elimination for feature selection may not apply as all variables seem to be important in heart disease prediction. An early accurate diagnosis leading to prompt intervention efforts is very crucial as it improves the patient's quality of life and diminishes the risk of developing cardiac events.
Machine Learning ; Support Vector Machine

Vector Borne Diseases ; Intersectoral Collaboration

OBJECTIVE: This study assessed the species composition of mosquitoes collected from ovitraps in selected public schools of Metro Manila, Philippines.

MATERIALS AND METHODS: Ovitraps were installed from November 2013 to February 2014, in purposively selected public elementary and high schools of Metro Manila. Ovitraps were installed inside classrooms and collected weekly and examined for mosquito eggs and larvae. Speciation was done once a month from November 2013 to February 2014. All positive paddles were immersed in water for larval emergence, reared to fourth instars and were identified using taxonomic keys.

RESULTS: A total of 1,482 ovitraps were installed in the selected public schools, and 18,325 larvae were collected from elementary schools, while 16,670 larvae were collected from high schools. The mean ovitrap index or infestation rate was 49.69% during the period of data collection. Mosquito larvae were identified as Aedes aegypti (88.94%) and Aedes albopictus (11.06%). Aedes aegypti and Aedes albopictus coexisted in some of the examined paddles. No significant differences were observed between the type of school and the presence of Aedes larvae. Significant differences were observed between total number of mosquito larvae and months of collection.

CONCLUSION: The presence of Aedes mosquitoes in schools evidently shows that continuous vector surveillance in schools is necessary as this information will help in the formulation of proactive vector control activities, thereby preventing the occurrence of mosquito-borne diseases.

Background: Japanese Encephalitis (JE) virus is a leading cause of encephalitis in children with high mortality and complication. JE is a dangerous infectious disease via Culex mosquitoes. Objective: To identify the density of some mosquitoes and vectors that transmit JE virus in Ha Nam province. Subject and Method:There were 30.333 mosquitoes including 05 genera and 15 species which were collected at night from April 2006 to March 2007 in the following communes: Tanson (midland area) Hungcong (plain area) and Liemchinh (suburban area). Results: A total of 06 Culex species, the highest rate is Culex tritaeniohychus (41.20%); Culex annulus (15.56%); other Culex species occupied around 0.15% -2.49%. In these communes, the density of Culex tritaeniohychus was higher than Culex annulus. They were found to be active all year round, but the highest density of Culex tritaeniohychus and Culex annulus is 5.86 and 2.15, respectively in April and fall to 4.35% and 1.71% in July. The collected mosquitoes during April, May, June and July includes 133 and 28 Culex tritaeniohychus and Culex annulus pools, respectively; all were to be processed for the isolation of Japanese Encephalitis (JE) virus. There were 12 Culex tritaeniohychus and 2 Culex annulus pools which were collected in Tanson commune yielding positive. Conclusion: The results were confirmed that Culex tritaenioohychus and Culex annulus are the major vectors that transmit JE virus in Ha Nam, 2006 - 2007. All 14 JE virus strains were isolated from collected mosquito pools during April, May and June; whereas JE virus strain was not yet isolated from collected mosquito pool in July. Thus, in order to control JE disease, it is necessary to control JE vectors in April, May and June.
Vector ; Culex tritaenioohychus ; Japanese encephalitis ; Ha Nam

Background: Using insecticides is considered as a temporary and rapid method for interrupting the disease transmission through disease vectors such as dengue. The insecticide Fendona, when absorbed into bed nets, is slowly released and rapidly knocks out, kills or repels mosquitoes as they come into contact with the bed net. Objectives: To evaluate the effectiveness of the Interceptor bed net (a unique textile-finishing product developed by BASF, Singapore PTE. LTD, that were coated with the Fendona insecticide) on controlling disease vector Aedes aegypti. Subjects and method: An experimental trial was carried out at the National Institute of Hygiene and Epidemiology and in the field of Hien Giang commune, Thuong Tin district, Ha Tay province. The changes of efficacy of Interceptor bed net were compared by not washing with washing at the different levels. Results: The unwashed bed nets can knock out and kill Aedes aegypti mosquitoes by 50% after 20 minutes of exposure on every trial. About 90-100% of total mosquitoes were killed after the first 30 minutes of exposure. Bed net\u2019s efficacy remains until 24 hours of the trial. The recovery rate of the mosquito is 0%. The same results were also observed after 90 days, 36 days and 18 days of bed nets being laundered. However, after 9 day of washing, the bed nets can only kill the mosquitoes up to about 90-95% of the total after the first 30 minutes of exposure. It also reached 100% of killing after 24 hours. However, its efficacy was conversely reduced with regard to the increase of laundry times. Conclusion: The density of adult mosquitoes and larvae for Aedes aegypti was significantly reduced in the intervention areas, even at zero level in comparison to the control sites. The insecticide had no side-effect or any stimulation to users, community, poultry, cattle and environment in the intervention sites.
Interceptor bednet ; disease vector ; Aedes aegypti

Considering the low accuracy of prediction in the positive samples and poor overall classification effects caused by unbalanced sample data of MicroRNA (miRNA) target, we proposes a support vector machine (SVM)-integration of under-sampling and weight (IUSM) algorithm in this paper, an under-sampling based on the ensemble learning algorithm. The algorithm adopts SVM as learning algorithm and AdaBoost as integration framework, and embeds clustering-based under-sampling into the iterative process, aiming at reducing the degree of unbalanced distribution of positive and negative samples. Meanwhile, in the process of adaptive weight adjustment of the samples, the SVM-IUSM algorithm eliminates the abnormal ones in negative samples with robust sample weights smoothing mechanism so as to avoid over-learning. Finally, the prediction of miRNA target integrated classifier is achieved with the combination of multiple weak classifiers through the voting mechanism. The experiment revealed that the SVM-IUSW, compared with other algorithms on unbalanced dataset collection, could not only improve the accuracy of positive targets and the overall effect of classification, but also enhance the generalization ability of miRNA target classifier.
Algorithms ; MicroRNAs ; chemistry ; Support Vector Machine

OBJECTIVES: The primary objective of this study is to compare model performance of machine learning methods with that of a previous study in which a nonlinear mixed effects model was created using NONMEM(R) for the pharmacokinetic and pharmacodynamic data for propofol. The secondary objective was to evaluate if a pharmacodynamic model describing the relationship between the dose of propofol and bispectral index (BIS) outperform that describing the relationship between a pharmacokinetic model derived-predicted concentrations of propofol and BIS. METHODS: Data were collected during a study involving the infusion of propofol into healthy volunteers. Pharmacokinetic and pharmacodynamic models were constructed using artificial neural networks (ANNs), support vector machines (SVMs), and multi-method ensembles and were compared with the nonlinear mixed effects method as implemented by NONMEM(R). Model performance was assessed by goodness-of-fit statistics, paired t-tests between predicted and observed values for each model and scatterplots. RESULTS: In pharmacokinetic analysis, ensemble I, the mean of ANN and NONMEM(R) predictions, achieved minimal error and the highest correlation coefficient. SVM produced the highest error and the lowest correlation coefficient. In pharmacodynamic analysis, ANN exhibited the best performance. An ANNModel describing the relationship between the dose of propofol and BIS was not inferior to an ANN model describing the relationship between predicted concentrations of propofol derived from an ANN pharmacokinetic model and BIS. CONCLUSIONS: In pharmacokinetic analysis, ensemble combined with ANN achieved slightly better performance than NONMEM(R). The relationship between the dose of propofol and BIS can be predicted without considering pharmacokinetics of propofol.
Machine Learning ; Propofol ; Support Vector Machine

MicroRNA (miRNA) is a family of endogenous single-stranded RNA about 22 nucleotides in length. Through targeting 3' UTR of message RNA (mRNA), they play important roles in post-transcriptional regulatory functions. For further research of miRNA function, the identification of more miRNA positive targets is needed urgently. Aiming at the high-dimensional small sample data sets in miRNA target prediction, an algorithm of eliminating redundant features is proposed based on v-SVM in this paper, and classification and features selection are also fused. The algorithm of eliminating redundant features optimizes the combination of features, and then constructs the best features combination which can represent miRNA and targets interaction model. The prior parameter v (0 < u < or = 1) controls the compression proportion of data set and selects more distinguishing support vectors. Finally, the classifier model of miRNA target prediction is built. The unbiased assessment of the classifier is achieved with a completely independent test dataset. Experiment results indicated that in both classification recognition and generalization performance of miRNA targets predicition, this model was superior to the present machine learning algorithms such as miTarget, NBmiRTar and TargetMiner, etc.
MicroRNAs ; Models, Theoretical ; Support Vector Machine

OBJECTIVE: According to the digital image features of corneal opacity, a multi classification model of support vector machine (SVM) was established to explore the objective quantification method of corneal opacity. METHODS: The cornea digital images of dead pigs were collected, part of the color features and texture features were extracted according to the previous experience, and the SVM multi classification model was established. The test results of the model were evaluated by precision, sensitivity and RESULTS: In the classification of corneal opacity, the highest CONCLUSIONS The SVM multi classification model can classify the degree of corneal opacity.
Animals ; Corneal Opacity ; Support Vector Machine ; Swine