This study aims to develop an automatic classifier for risk assessment in patients suffering from congestive heart failure (CHF). The proposed classifier separates lower risk patients from higher risk ones, using standard long-term heart rate variability (HRV) measures. Patients are labeled as lower or higher risk according to the New York Heart Association classification (NYHA). A retrospective analysis on two public Holter databases was performed, analyzing the data of 12 patients suffering from mild CHF (NYHA I and II), labeled as lower risk, and 32 suffering from severe CHF (NYHA III and IV), labeled as higher risk. Only patients with a fraction of total heartbeats intervals (RR) classified as normal-to-normal (NN) intervals (NN/RR) higher than 80% were selected as eligible in order to have a satisfactory signal quality. Classification and regression tree (CART) was employed to develop the classifiers. A total of 30 higher risk and 11 lower risk patients were included in the analysis. The proposed classification trees achieved a sensitivity and a specificity rate of 93.3% and 63.6%, respectively, in identifying higher risk patients. Finally, the rules obtained by CART are comprehensible and consistent with the consensus showed by previous studies that depressed HRV is a useful tool for risk assessment in patients suffering from CHF.
There is consensus that Heart Rate Variability is associated with the risk of vascular events. However, Heart Rate Variability predictive value for vascular events is not completely clear. The aim of this study is to develop novel predictive models based on data-mining algorithms to provide an automatic risk stratification tool for hypertensive patients. A database of 139 Holter recordings with clinical data of hypertensive patients followed up for at least 12 months were collected ad hoc. Subjects who experienced a vascular event (i.e., myocardial infarction, stroke, syncopal event) were considered as high-risk subjects. Several data-mining algorithms (such as support vector machine, tree-based classifier, artificial neural network) were used to develop automatic classifiers and their accuracy was tested by assessing the receiver-operator characteristics curve. Moreover, we tested the echographic parameters, which have been showed as powerful predictors of future vascular events. The best predictive model was based on random forest and enabled to identify high-risk hypertensive patients with sensitivity and specificity rates of 71.4% and 87.8%, respectively. The Heart Rate Variability based classifier showed higher predictive values than the conventional echographic parameters, which are considered as significant cardiovascular risk factors. Combination of Heart Rate Variability measures, analyzed with data-mining algorithm, could be a reliable tool for identifying hypertensive patients at high risk to develop future vascular events.
In hypertension, blockade of the renin-angiotensin system reduces left ventricular mass (LVM) independently of brachial systolic (S), diastolic (D), and mean (M) blood pressure (BP). From central to peripheral arteries, MBP and DBP are practically unchanged, whereas SBP and pulse pressure (PP) increase significantly. The objective was to determine whether changes in LVM under drug treatment was preferentially associated with changes in central or brachial SBP and PP. A substudy of 146 subjects was selected from 469 hypertensive patients submitted to a double-blind randomized trial comparing the combination of perindopril (2 mg; Per) and indapamide (0.625 mg; Ind) with atenolol (50 mg, one tablet per day). Before and after 1 year of treatment: LVM (echocardiography) in 146 subjects and, in 52 of them, central (carotid) BP and timing of wave reflections (tonometry). LVM changes were significantly associated with antihypertensive treatment, with lower LVM with Per/Ind than with atenolol. Changes in SBP and PP, but not in MBP and DBP, were more significantly associated with Per/Ind than with atenolol, with more pronounced effects using central than brachial measurements, and a longer delay in central return of wave reflections under Per/Ind. In the sampling of 52 patients with tonometry, the change in LVM between the two drug regimens was significantly linked to central, but not brachial, PP change. This observational study shows a lower LVM under Per/Ind than under atenolol. The greater change in LVM on Per/Ind was linked to central and not brachial blood pressure.
Background and Purpose —Endothelium-derived NO is formed from l -arginine by endothelial NO synthase (eNOS) encoded by the NOS 3 gene on chromosome 7. Because several studies have indicated that NO plays a key role in the development of the atherosclerotic process, we investigated whether common variants in the eNOS gene are associated with an increased risk of plaque on carotid arteries. Methods —We studied 375 subjects attending the hypertension center of our institution to be screened for arterial hypertension. The examined subjects were classified according to the presence of carotid plaques (intima-media thickness ≥1.5 mm), and 2 intronic (CA and 27-bp repeats) polymorphisms and 1 exonic (Glu298Asp) polymorphism of the eNOS gene were explored. Results —Only the Glu298Asp polymorphism of eNOS was associated with the presence of carotid plaques ( P <0.05). In particular, there was an excess of homozygotes for the Asp298 variant among subjects with carotid plaques, whereas the number of subjects who had the Glu298 allele in exon 7 of the eNOS gene was equally distributed in both study groups. Interestingly, the risk of having carotid plaques was increased ≈3 times in subjects who were homozygotic for the Asp298 variant compared with subjects who were homozygotic for the Glu298 variant and was independent of the other common risk factors (age, blood pressure, and smoking). Conclusions —Homozygosity for Asp298, a common variant of the eNOS gene, is an independent risk factor for carotid atherosclerosis in this study population.