The morbidity and mortality of cardiovascular diseases (CVDs) have been increasing year by year all over the world and expanding greatly to the younger population, which becomes the leading causes of death globally that threatens human life safety. Prediction of the occurrence of diseases by using risk related adverse events is crucial for screening and early detection of CVDs. Thus, the discovery of new biomarkers that related to risks of CVDs are of urgent in the field. Retinol-binding protein 4 (RBP4) is a 21-kDa adipokine, mainly secreted by adipocytes. Besides its well-established function in the induction of insulin resistance, it has also been found in recent years to be closely associated with CVDs and other risk factors, such as hypertension, coronary heart disease, heart failure, obesity, and hyperlipidemia. In this review, we mainly focus on the progress of research that establishes the correlation between RBP4 and CVDs and the corresponding major risk factors in recent years.
Background: Existing research has shown that retinol binding protein (RBP4) has an impairing effect on arterial elasticity and induces insulin resistance, but the clinical value of RBP4 in patients with coronary heart disease (CHD) combined with type 2 diabetes mellitus (T2DM) has not been investigated. This study sought to compare the complexity of coronary artery lesions and coronary artery elasticity between patients with CHD combined with T2DM and those with CHD without T2DM, analyze the risk factors affecting coronary artery elasticity, and investigate the value of RBP4 in assessing coronary artery elasticity in patients with CHD and T2DM. Methods: A total of 130 patients with confirmed CHD were consecutively enrolled, including 38 patients with CHD combined with T2DM and 92 patients with CHD without T2DM. Basic clinical data, laboratory findings, coronary angiography and intravascular ultrasound (IVUS) imaging data, and Gensini scores and coronary artery elasticity parameters were calculated in both groups. Elasticity parameters included: stiffness parameter (β), pressure-strain elastic modulus (Ep), distensibility coefficient (DC), and compliance coefficient (CC). Multiple linear regression equations were established with elasticity parameters as dependent variables to explore the factors influencing coronary artery elasticity parameters in patients within the two groups. Results: Compared with patients in the CHD without T2DM group, patients in the CHD combined with T2DM group had higher RBP4 levels, Gensini scores, β and Ep values, and lower DC and CC values. Linear regression analysis showed that Gensini score increased with higher β and Ep values and decreased with higher DC and CC values. In all patients in the CHD and CHD combined with T2DM groups, RBP4 was an independent risk factor for β values after correction for confounders by multiple linear regression analysis, whereas in patients in the CHD without T2DM group, the effect of RBP4 on β values was not statistically different. Conclusions: RBP4 was an independent risk factor of coronary artery elasticity in CHD patients with T2DM and in overall CHD patients, but it did not affect coronary artery elasticity in CHD patients without T2DM.
Feature selection is a fundamental pre‐processing step in machine learning that aims to reduce the dimensionality of a dataset by selecting the most effective features from the original features. This process is regarded as a combinatorial optimization problem, and the grey wolf optimizer (GWO), a novel meta‐heuristic algorithm, has gained popularity in feature selection due to its fast convergence speed and easy implementation. In this paper, an improved binary GWO algorithm incorporating a novel Population Adaptation strategy called PA‐BGWO is proposed. The PA‐BGWO takes into account the characteristics of the feature selection problem and designs three strategies. The proposed strategy includes an adaptive individual update procedure to enhance the exploitation ability and accelerate convergence speed, a head wolf fine‐tuned mechanism to exert the impact on each independent feature of the objective function, and a filter‐based method ReliefF for calculating feature weights with dynamically adjusted mutation probabilities based on the ranking features to effectively escape from local optima. Experimental comparisons with several state‐of‐the‐art feature selection methods on 15 classification problems demonstrate that the proposed approach can select a small feature subset with higher classification accuracy in most cases.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.