Rationale: Stent implantation into atherosclerotic plaques releases, apart from particulate debris, soluble substances that contribute to impaired microvascular perfusion.Objective: To quantify the release of vasoconstrictors and to determine the efficacy of coronary dilators to attenuate their action. Methods and Results:

MotivationBiomarker discovery methods are essential to identify a minimal subset of features (e.g., serum markers in predictive medicine) that are relevant to develop prediction models with high accuracy. By now, there exist diverse feature selection methods, which either are embedded, combined, or independent of predictive learning algorithms. Many preceding studies showed the defectiveness of single feature selection results, which cause difficulties for professionals in a variety of fields (e.g., medical practitioners) to analyze and interpret the obtained feature subsets. Whereas each of these methods is highly biased, an ensemble feature selection has the advantage to alleviate and compensate for such biases. Concerning the reliability, validity, and reproducibility of these methods, we examined eight different feature selection methods for binary classification datasets and developed an ensemble feature selection system.ResultsBy using an ensemble of feature selection methods, a quantification of the importance of the features could be obtained. The prediction models that have been trained on the selected features showed improved prediction performance.Electronic supplementary materialThe online version of this article (doi:10.1186/s13040-016-0114-4) contains supplementary material, which is available to authorized users.

Atherosclerotic coronary arteries are more calcified in patients with than without chronic kidney disease (CKD). We addressed the potential for coronary microvascular obstruction in patients with and without CKD during stenting for saphenous vein aorto-coronary graft (SVG) stenosis under protection with a distal occlusion/aspiration device. In patients with and without CKD (n = 20/20), SVG plaque composition was analyzed from virtual histology using intravascular ultrasound analysis before stent implantation. There was more dense calcium and more necrotic core in patients with than without CKD (14 ± 3 vs. 3 ± 1 % and 21 ± 3 vs. 12 ± 2 % of plaque volume, respectively). Coronary aspirate was retrieved during stent implantation and divided into particulate debris and plasma. Patients with CKD had more particulate debris and calcium release than patients without CKD. In contrast, the release of serotonin was less in patients with than without CKD (0.4 ± 0.1 vs. 1.2 ± 0.3 μmol/L), whereas that of catecholamines, endothelin, tissue factor, thromboxane, tumor necrosis factor α, and C reactive protein was not significantly different. Confirming the biochemical results, aspirate plasma from patients with CKD induced less vasoconstriction of rat mesenteric arteries than that from patients without CKD (with endothelium (+E), 26 ± 7 %; without endothelium (-E): 28 ± 7 % vs. +E, 68 ± 12 %; -E: 95 ± 16 % of maximum KCl-induced vasoconstriction). Graft atherosclerosis of patients with CKD is more degenerated and releases more particulate debris and calcium, but the aspirate has surprisingly less serotonin and vasoconstrictor potential.