Background-Differences in vascular reactivity to phenylephrine (PE) responsiveness have been largely evidenced in patients undergoing cardiac surgery with cardiopulmonary bypass (CPB). Because nitric oxide (NO) strongly affects modulation of the vascular tone in response to vasopressor agents, we hypothesized that the G894T polymorphism of the endothelial NO synthase gene (eNOS) could be related to changes in the pressor response to PE. Methods and Results-The protocol was performed in 68 patients undergoing coronary artery bypass grafting (nϭ33) or valve surgery (nϭ35) in whom mean arterial pressure decreased below 65 mm Hg during normothermic CPB. Under constant and nonpulsatile pump flow conditions (2 to 2.4 L ⅐ min Ϫ1 ⅐ m Ϫ2 ), a PE dose-response curve was generated by the cumulative injection of individual doses of PE (25 to 500 g). The G894T polymorphism of the eNOS gene was determined, and 3 groups were defined according to genotype (TT, GT, and GG). Groups were similar with regard to perioperative characteristics. The PE dose-dependent response was significantly higher in the allele 894T carriers (TT and GT) than in the homozygote GG group (Pϭ0.02), independently of possible confounding variables. Conclusions-These results evidenced an enhanced responsiveness to ␣-adrenergic stimulation in patients with the 894T allele in the eNOS gene. (Circulation. 1999;99:3096-3098.)

Pericardial levels of 8-iso-PGF2alpha increase with the functional severity of heart failure and are associated with ventricular dilatation. These data suggest an important role for in vivo oxidant stress on ventricular remodeling and the progression to heart failure.

BackgroundThe benefits of cardiac surgery are sometimes difficult to predict and the decision to operate on a given individual is complex. Machine Learning and Decision Curve Analysis (DCA) are recent methods developed to create and evaluate prediction models.Methods and findingWe conducted a retrospective cohort study using a prospective collected database from December 2005 to December 2012, from a cardiac surgical center at University Hospital. The different models of prediction of mortality in-hospital after elective cardiac surgery, including EuroSCORE II, a logistic regression model and a machine learning model, were compared by ROC and DCA. Of the 6,520 patients having elective cardiac surgery with cardiopulmonary bypass, 6.3% died. Mean age was 63.4 years old (standard deviation 14.4), and mean EuroSCORE II was 3.7 (4.8) %. The area under ROC curve (IC95%) for the machine learning model (0.795 (0.755–0.834)) was significantly higher than EuroSCORE II or the logistic regression model (respectively, 0.737 (0.691–0.783) and 0.742 (0.698–0.785), p < 0.0001). Decision Curve Analysis showed that the machine learning model, in this monocentric study, has a greater benefit whatever the probability threshold.ConclusionsAccording to ROC and DCA, machine learning model is more accurate in predicting mortality after elective cardiac surgery than EuroSCORE II. These results confirm the use of machine learning methods in the field of medical prediction.