Konstantinos Vakalis

Automated Diagnosis of Coronary Artery Disease Based on Data Mining and Fuzzy Modeling

A fuzzy rule-based decision support system (DSS) is presented for the diagnosis of coronary artery disease (CAD). The system is automatically generated from an initial annotated dataset, using a four stage methodology: 1) induction of a decision tree from the data; 2) extraction of a set of rules from the decision tree, in disjunctive normal form and formulation of a crisp model; 3) transformation of the crisp set of rules into a fuzzy model; and 4) optimization of the parameters of the fuzzy model. The dataset used for the DSS generation and evaluation consists of 199 subjects, each one characterized by 19 features, including demographic and history data, as well as laboratory examinations. Tenfold cross validation is employed, and the average sensitivity and specificity obtained is 62% and 54%, respectively, using the set of rules extracted from the decision tree (first and second stages), while the average sensitivity and specificity increase to 80% and 65%, respectively, when the fuzzification and optimization stages are used. The system offers several advantages since it is automatically generated, it provides CAD diagnosis based on easily and noninvasively acquired features, and is able to provide interpretation for the decisions made.

Changes in vascular function and structure in juvenile idiopathic arthritis

Chronic inflammatory diseases in adults have been associated with increased cardiovascular risk and impaired vascular function. We aimed to assess the presence of early vascular dysfunction in patients with juvenile idiopathic arthritis (JIA) and investigate the role of inherent inflammatory process of JIA in vascular health.

Impact of renin-angiotensin-aldosterone system genes on the treatment response of patients with hypertension and metabolic syndrome

Objective. To evaluate the influence of clinical, biochemical and genetic markers on the response to antihypertensive treatment in patients with essential hypertension and the metabolic syndrome (MetS). Methods. Measurements of anthropometric indices, blood pressure (BP), and metabolic parameters were obtained from the medical records of 132 (77 women) newly diagnosed, untreated hypertensive patients. Renin-angiotensin-aldosterone system (RAAS) genes polymorphisms (including ACE I/D, angiotensinogen M235T, angiotensin II type 1 receptor [AT1-receptor] A1166C) were determined. Response to treatment was defined as BP less than 140/90 mmHg. Results. Patients with MetS (n=60) had higher systolic BP and pulse pressure and a more atherogenic lipid profile than patients without MetS.The frequencies of the ACE and the AT1-receptor gene polymorphisms were similar between patients with and without MetS. Response to treatment was positively associated with pulse pressure, and the presence of the C allele as well as the AC genotype of the AT1-receptor gene and inversely with age after adjustment for confounding factors. Conclusions. RAAS genes distribution does not differ between hypertensive patients with and without the MetS. Higher baseline pulse pressure levels, the presence of the C allele and/or the AC genotype may be in favour of a better response to structured antihypertensive treatment in patients with MetS. However, these findings need to be evaluated in future studies.

Paradoxical protective effect of central obesity in patients with suspected stable coronary artery disease

Increased body mass index (BMI) has been paradoxically inversely associated with the presence of angiographic coronary artery disease (CAD). Central obesity measures, considered to be more appropriate for assessing obesity‐related cardiovascular risk, have been little studied in relation to the presence of CAD. The aim was to investigate the association of central obesity with the presence of angiographic CAD as well as the prognostic significance of obesity measures in CAD prediction when added to other cardiovascular risk factors.

Increased Aortic Pulse Wave Velocity Is Associated With the Presence of Angiographic Coronary Artery Disease in Overweight and Obese Patients

BACKGROUND Increased arterial stiffness assessed by carotid-femoral pulse wave velocity (CFPWV) and central augmentation index (AIx), has been associated with a worse cardiovascular prognosis and increased prevalence of angiographic coronary artery disease (CAD). Obesity, a well-recognized cardiovascular risk factor, has been related to increased arterial stiffness, although not consistently. The aim of this work was to investigate the association of arterial stiffness indices with obesity measures in patients undergoing coronary angiography and to study any potential association of arterial stiffness with angiographic CAD in relation to obesity. METHODS Three hundred ninety-three patients with suspected stable CAD (aged 61±10 years; n = 303 men) referred for diagnostic coronary angiography were included. Body mass index (BMI), waist circumference (WC), and traditional cardiovascular risk factors were measured. Arterial stiffness was assessed by CFPWV and AIx using applanation tonometry in all patients. RESULTS CFPWV was not associated with obesity measures in multiple-adjusted logistic regression analysis (P > 0.05), whereas AIx was inversely associated with BMI and WC (P < 0.05 for both). Increased CFPWV was associated with CAD in overweight and obese patients (BMI ≥25kg/m(2); WC ≥94cm in men and ≥80cm in women; P < 0.05). No association of AIx with CAD was found (P > 0.05). CONCLUSIONS Arterial stiffness indices were not consistently associated with obesity, opposite to what might have been expected. The association of increased CFPWV with the presence of angiographic CAD in patients with increased BMI or WC values warrants further research.

Extent of coronary artery disease in patients undergoing angiography for stable or acute coronary syndromes.

BACKGROUND We aimed to investigate whether the angiographic extent of coronary artery disease (CAD) differs in patients undergoing coronary angiography for stable CAD or acute coronary syndrome (ACS) and identify predictors of CAD extent in these patients. METHODS We enrolled 584 consecutive patients (463 with stable CAD, 121 with ACS) with angiographically established CAD (≥1 stenosis >25%). The Gensini score was used to assess the extent of coronary atherosclerosis. RESULTS Stable CAD patients had greater Framingham risk score and greater prevalence of hypertension, hypercholesterolemia, and diabetes (p<0.05 for all). Fasting glucose and systolic and diastolic blood pressure were higher, while high-sensitivity C-reactive protein (hsCRP) levels were lower in patients with stable CAD than in those with ACS (p<0.05 for all). No difference in Gensini score was observed between the two groups (p=0.118), but patients with ACS were more likely to have at least one significant epicardial angiographic lesion (>50% stenosis) (OR 2.0, p=0.022). Higher Gensini score was independently associated with (i) higher hsCRP and glucose levels, hypercholesterolemia, and increased age in stable CAD patients (R2 0.15, p<0001) and (ii) increased age and higher glucose and hsCRP levels in patients with ACS (R2 0.17, p<0001). CONCLUSIONS Patients undergoing coronary angiography for ACS or stable CAD presented with a similar extent of angiographic CAD, although patients with ACS had a higher prevalence of significant lesions in the presence of a better cardiovascular risk profile and higher inflammation levels. The extent of angiographic CAD in both the groups shared common determinants such as hsCRP, age, and hyperglycemia, but these appeared to explain only a small part of the variation of coronary atherosclerosis.

Role of 9p21 and 2q36 variants and arterial stiffness in the prediction of coronary artery disease.

Genetic polymorphisms and arterial stiffness indices have been associated with cardiovascular prognosis and the presence and extent of angiographic coronary artery disease (CAD). We aimed to investigate whether arterial stiffness indices and 9p21 and 2q36 variants may improve prediction of CAD presence and extent when added to classical cardiovascular risk factors in patients at high risk for CAD.