A two-stage prediction filling method with support vector technologies optimized competitively in stages by grey wolf optimizer and particle swarm optimization for missing fasting blood glucose.

Missing values often affect the data utilization in epidemiological survey. In this study, according to the cut-off point value of the medical diagnostic standard of fasting blood glucose for diabetes, we divide fasting blood glucose test data from the China Health and Nutrition Survey (CHNS) of Shandong province in 2009 into two classes: the normal and the abnormal. Accordingly, for missing fasting blood glucose values, we propose a two-stage prediction filling method with optimized support vector technologies competitively by particle swarm optimization (PSO) or grey wolf optimizer (GWO), which is to first predict the class of the missing data with support vector machine (SVM) in the first stage and then predict the missing value with support vector regression (SVR) within the predicted class in the second stage. In addition, we use the LIBSVM as a gold standard to train both SVM and SVR in different stages. For two kinds of competitive optimizers in stages, in the first stage GWO has the highest classification accuracy (91.1%), and in the second stage PSO has the smallest in-class mean absolute error (0.48). So, GWO-SVM-PSO-SVR is determined as the optimal model and a predicted value with it serves as a fill value. The comparison results of the models in empirical analysis also show that it outdoes any of the other filling models in terms of mean absolute error and mean absolute percentage error. In addition, the sensitivity analysis shows that it presents high tolerance as the sample size changes and has a good stability.

U-shaped association of serum uric acid with all-cause mortality in patients with hyperlipidemia in the United States: a cohort study.

Background: Serum uric acid (SUA) interferes with lipid metabolism and is considered an independent risk factor for atherosclerosis, a major complication in patients with hyperlipidemia. However, the effects of uric acid levels on mortality in hyperlipidemic patients has yet to be sufficiently determined. In this study, we aimed to assess the association between all-cause mortality and SUA in a hyperlipidemic population. Methods: To determine mortality rates, we obtained data for 20,038 hyperlipidemia patients from the U.S. National Health and Nutrition Examination Surveys (NHANES) 2001-2018 and National Death Index. To examine the all-cause mortality effect of SUA, multivariable Cox regression models, restricted cubic spline models, and two pairwise Cox regression models were used. Results: Over a median follow-up of 9.4 years, a total of 2079 deaths occurred. Mortality was examined according to SUA level quintiles: <4.2, 4.3-4.9, 5.0-5.7, 5.8-6.5, and >6.6 mg/dl. In multivariable analysis using 5.8-6.5 mg/dl SUA as a reference, the hazard ratios (95% confidence interval) of all-cause mortality across the five groups were 1.24 (1.06-1.45), 1.19 (1.03-1.38), 1.07 (0.94-1.23), 1.00 (reference), and 1.29 (1.13-1.48), respectively. According to a restricted cubic spline, we noted a U-shaped relationship between SUA and all-cause mortality. The inflection point was approximately 6.30 mg/dl, with hazard ratios of 0.91 (0.85-0.97) and 1.22 (1.10-1.35) to the left and right of the inflection point, respectively. In both sexes, SUA was characterized by a U-shaped association, with inflection points at 6.5 and 6.0 mg/dl for males and females, respectively. Conclusion: Using nationally representative NHANES data, we identified a U-shaped association between SUA and all-cause mortality in participants with hyperlipidemia.