The study investigates the latent pollution sources and most significant parameters that cause spatial variation and develops the best input for water quality modelling using principal component analysis (PCA) and artificial neural network (ANN). The dataset, 22 water quality parameters were obtained from Department of Environment Malaysia (DOE). The PCA generated six significant principal component scores (PCs) which explained 65.40 % of the total variance. Parameters for water quality variation are mainlyrelated to mineral components, anthropogenic activities, and natural processes. However, in ANN three input combination models (ANN A, B, and C) were developed to identify the best model that can predict water quality index (WQI) with very high precision. ANN A model appears to have the best prediction capacity with a coefficient of determination (R2) = 0.9999 and root mean square error (RMSE) = 0.0537. These results proved that the PCA and ANN methods can be applied as tools for decision-making and problem-solving for better managing of river quality.
BACKGROUND: The Asian population with atrial fibrillation (AF) have a higher risk of stroke than the caucasian population and a higher risk of intracranial bleeding when anticoagulated with warfarin. There are few real-world studies comparing the efficacy of non-vitamin K antagonist oral anticoagulants (NOACs) and warfarin among Asian patients to assess its outcomes of ischemic stroke and hemorrhagic stroke.
METHODS: A retrospective cohort study of 1000 patients on dabigatran and warfarin from 2009 to 2013.
RESULTS: Data were available for 500 patients on dabigatran and 500 patients on warfarin. The average follow-up duration was 315 ± 280 days in the dabigatran group and 355 ± 232 in the warfarin group. The time in therapeutic range (TTR) was 53.2% in the warfarin-treated group, with 32.8% of patients in the subtherapeutic international normalized ratio range of <2. None of the patients in the dabigatran group had ischemic cerebrovascular accident (CVA) compared to 4 (0.8%) patients in the warfarin group, hazard ratio (HR) 0.13, P = .3. There was 1 (0.2%) patient in both dabigatran and warfarin groups with hemorrhagic CVA (HR 1.16, P = .92). There were 3 (0.6%) patients with major bleeding in the dabigatran group compared to 2 (0.4%) patients in the warfarin group (HR 1.57, P = .59).
CONCLUSION: There were similar rates of efficacy for outcomes of ischemic CVA, hemorrhagic CVA, and bleeding when comparing dabigatran with warfarin. Our study shows that despite similar efficacy, suboptimal TTR rates and inconveniences with warfarin demonstrate that NOACs are preferred for stroke prevention in AF.
KEYWORDS: dabigatran; non-valvular atrial fibrillation; novel anticoagulant; stroke prevention; warfarin