Diagnosis of Acute Coronary Syndrome with a Support Vector Machine.

Acute coronary syndrome (ACS) is a serious condition arising from an imbalance of supply and demand to meet myocardium's metabolic needs. Patients typically present with retrosternal chest pain radiating to neck and left arm. Electrocardiography (ECG) and laboratory tests are used indiagnosis. However in emergency departments, there are some difficulties for physicians to decide whether hospitalizing, following up or discharging the patient. The aim of the study is to diagnose ACS and helping the physician with his decisionto discharge or to hospitalizevia machine learning techniques such as support vector machine (SVM) by using patient data including age, sex, risk factors, and cardiac enzymes (CK-MB, Troponin I) of patients presenting to emergency department with chest pain. Clinical, laboratory, and imaging data of 228 patients presenting to emergency department with chest pain were reviewedand the performance of support vector machine. Four different methods (Support vector machine (SVM), Artificial neural network (ANN), Naïve Bayes and Logistic Regression) were tested and the results of SVM which has the highest accuracy is reported. Among 228 patients aged 19 to 91 years who were included in the study, 99 (43.4 %) were qualified as ACS, while 129 (56.5 %) had no ACS. The classification model using SVM attained a 99.13 % classification success. The present study showed a 99.13 % classification success for ACS diagnosis attained by Support Vector Machine. This study showed that machine learning techniques may help emergency department staff make decisions by rapidly producing relevant data.

Is there any relation between coronary atherosclerosis and tympanosclerosis?

OBJECTIVE: Atherosclerosis is a chronic inflammatory disease of medium and large-sized arteries. Tympanosclerosis is the hyalinization and calcification of the connective tissue in the middle ear, including the tympanic membrane. The etiology and pathogenesis of tympanosclerosis are still controversial. There are some reports about the possible relationship between development of tympanosclerosis and atherosclerosis. Therefore, we aimed a cross-sectional study to investigate relationship between tympanosclerosis and atherosclerosis in patients referred for coronary angiography. METHODS: The study population consisted of 203 consecutive patients (145 men, mean age 59+/-11 years) who underwent coronary angiography. Otoscopic examination was performed in all patients. All angiographies were examined to calculate coronary artery vessel stenosis and extent scores. Mann-Whitney U test was used to compare the angiographic scores with existence of tympanosclerosis. RESULTS: Among the 203 patients, 35 (17%) patients had angiographically normal coronary arteries without any atheroma plaque and 168 (83%) had coronary atherosclerosis. In the otoscopic examination, tympanosclerosis was found in 14 patients (6.9%). No significant differences in distribution of clinical atherosclerotic risk factors (age, gender, body mass index, hypertension, diabetes mellitus, cigarette smoking and cholesterol levels) were found between groups with and without tympanosclerosis. Tympanosclerosis was found in 4 patients with normal coronary arteries (11.4%). In the group of coronary atherosclerosis, 10 patients have tympanosclerosis (5.9%). In addition, there was no statistically significant association of coronary artery vessel, stenosis or extent scores of atherosclerosis with tympanosclerosis (p>0.05). CONCLUSIONS: We could not find any association between tympanosclerosis and angiographic extent and severity of atherosclerosis, contrary to other studies. More studies are needed to understand etiological mechanisms and association between them.

[Femoral vascular complications after percutaneous coronary interventions]. / Perkütan koroner girisimler sonrasi femoral vasküler komplikasyonlar.

OBJECTIVE: We aimed to investigate peripheral vascular complications and their relation with treatment and clinical parameters in percutaneous transluminal coronary angioplasty (PTCA) patients. METHODS: We included into the study 321 patients (aged 57+/-11 years) underwent PTCA between November 2001-August 2002. The age, gender, glycoprotein 2b/3a use, thrombolytic use, intraaortic balloon treatment, transient pacemaker treatment, reintervention history, hypertension, diabetes mellitus, smoking status, family history and the correlations of these parameters with local vascular complications were assessed in all patients. RESULTS: Pseudoaneurysm incidence was significantly correlated with; age [(n=13, 68.0%) p=0.0001, OR 8.38], female gender [(n=12, 63.1%) p<0.015, OR 0.32], reintervention [(n=10, 52.1%) p<0.004, OR 3.6], venous sheath usage [(n=12, 63%) p<0.0001, OR 9.07], thrombolytic treatment [(n=5, 26.3%) p<0.0001, OR 7.9], and intraaortic balloon adjustment [(n=6, 31.5%) p<0.0001, OR 7.2]. No correlation was found between pseudoaneurysm incidence and glycoprotein 2b/3a treatment, smoking, diabetes mellitus, hypertension and family history. CONCLUSION: The present study showed that patients of female gender, with reintervention, thrombolytic treatment, venous sheath use and intraaortic balloon adjustment are at high risk for serious femoral vascular complications, especially when they are aged. Additionally, glycoprotein 2b/3a agents can be used without increased risk of peripheral vascular complications.

The relationship between plasma endothelin-1, nitric oxide levels, and heart rate variability in patients with coronary slow flow.

BACKGROUND: Coronary slow flow (CSF) is characterized by delayed opacification of coronary arteries in the absence of epicardial occlusive disease. In this study, we aimed to determine endothelin-1 (ET-1), nitric oxide (NOx) levels and time domain heart rate variability (HRV) parameters in patients with CSF and relationship among these parameters. METHODS: Thirty-three patients with CSF detected in the coronary angiography (17 females; mean age 55 +/- 7) and 19 patients with normal coronary flow (10 females; mean age 54 +/- 11) as a control group were enrolled in the study. Patients were divided into two groups according to exercise testing as if positive (group A, n = 8) or negative (group B, n = 25). RESULTS: Plasma ET-1 levels were higher in the group A patients (28.7 +/- 17.4 pg/ml) than that of group B (15.9 +/- 10.6 pg/ml) and control group (6.0 +/- 5.7 pg/ml); and higher in group B patients than that of control group (P < 0.05). Although groups A and B did not differ according to plasma NOx levels (23.4 +/- 13.5 micromol/L vs. 32.8 +/- 22.7 micromol/L, P > 0.05), NOx levels in group A were lower than the control group (23.4 +/- 13.5 micromol/L versus 42.5 +/- 15.9 micromol/L, P < 0.05). Time domain HRV parameters were decreased in all patient groups. This was more prominent in group A. Additionally, HRV parameters were negatively correlated with ET-1 and TIMI frame counts. TIMI frame count was also significantly correlated with ET-1 and NOx levels (r = 0.61, P < 0.0001, r =-0.30, P < 0.05). Upon intravascular ultrasonography investigation, the common finding was longitudinally extended massive calcification throughout the epicardial arteries. Mean intimal thickness was 0.50 +/- 0.13 mm (group A; 0.58 +/- 0.11 mm, group B 0.47 +/- 0.12 mm, P = 0.029). CONCLUSIONS: The present study demonstrated that in patients with CSF, both increased plasma ET-1, decreased plasma NOx and diffuse atherosclerosis may cause the decrease in HRV by effecting myocardial blood flow.