Predictor Of Coronary Disease Research Articles

Classification and Prediction of Heart Disease using Novel Random Forest Algorithm by Comparing Logistic Regression for Obtaining Better Accuracy

Aim: Heart attacks are usually caused due to blockages, partially or completely, of the heart’s veins or arteries that constrict the flow of blood from or to the heart. The primary objective of this review aims to be seen as the most appropriate algorithm to give us the ideal prediction. We will be comparing the novel Random forest with Logistic regression to find out which of these can give us the best accuracy. Material and Methods: The study used 143 samples with novel Random Forest and Logistic Regression is executed with varying training and testing splits for foreseeing the accuracy of coronary disease prediction with the 80% of G-power value and heart disease data were gathered from multiple web sources, including latest The study’s findings and criterion were 0.05%, with a 95% probability value, average, and confidence interval. The performance accuracy rate of the classifiers is used to evaluate the coronary disease dataset. There was a statistically significant value test between the novel Random Forest and Logistic Regression is 0.046 (p<0.05). Results and Discussion: The accuracy of predicting coronary disease in the novel Random Forest 90.16 % and Logistic Regression 85.25 % is obtained. Conclusion: This study concludes that the Prediction of Coronary disease using the novel Random Forest (RF) algorithm looks to be fundamentally superior to the Logistic Regression (LR) with increased precision.

Analysis and Comparison of Prediction of Heart Disease Using Novel Support Vector Machine and Logistic Regression Algorithm

Aim: prediction of coronary disease using novel support vector machine and comparing its accuracy with logistic regression algorithm. Materials and methods: Two social affairs are proposed for predicting the accuracy (%) of coronary disease. To be explicit, the novel supports vector machine and logistic regression algorithms. Here we take 20 samples each for appraisal and compare. The sample size was calculated using G power with pretest power at 80% and the alpha of 0.05 value. Result: The logistic regression gives better precision (87.82%) than the novel support vector machine (SVM) accuracy (81.30%). Thus the real significance of logistic regression is better than novel support vector machine algorithms. Conclusion: From the result, it might be gathered that logistic regression helps in expecting the coronary sickness with more accuracy to appear differently in relation to novel support vector machine algorithms.

Coronary disease prediction by using upgraded deep learning CNN

The determination of coronary failure has transformed into troublesome analytic effort in the present analytical examination. This finding turn to the point-by-point and accurate examination of the victim’s analytical facts on a single health report. The tremendous improvements in occupied deep literacy look to construct robotized structure which aid expert the couple to foresee and identify the weakness with the internet of things (IoT) help. In this way, the magnify machine learning by neural networks helped Convolutional Neural Network has been build to help and work on persistent forecast of heart disease. The Upgraded Deep CNN model is concentrated throughout deep plan that occupy multi-facet perceptron's model with training about normalization draws near. Besides, the structured implementation is accepted with full elements and limited high points. Henceforth, the reduced in the high points influences the fertility divides as far as pick up beat, and precision has been differentially examined with concluded outcomes. The Upgraded Deep CNN structure one time carried out on the Internet of Medical Things Platform for option inner concerned webs, which assists experts with successfully diagnosing cardiac sufferers information in auxiliary storage all over the globe.

Leveraging the Fog based Machine Learning Model for ECG based Coronary disease prediction

Leveraging the Fog based Machine Learning Model for ECG based Coronary disease prediction

P4575UA and NSTEMI in the era of high-sensitivity Troponin: impact on patient risk profile and management

Abstract Aim High-sensitivity troponin assays (HST) entered the clinical arena to facilitate exclusion of ACS in the emergency department (ER) in patients presenting with chest pain. Due to its higher sensitivity there is the potential for an overestimation of the diagnosis of NSTEMI, and possibly ACS overall. We assessed the impact of HST in the classification of ACS (NSTEMI vs UA) and its ability to predict obstructive coronary disease (CAD), in a population of pts referred to coronary angiography (ICA). Methods Retrospective analysis of 1844 pts with suspected NSTEMI or UA referred for ICA from a single ER between Feb 2013 and Nov 2018. Standard Troponin-I was used until Feb 2016 and HST thereafter. The characteristics of UA and NSTEMI pts before and after the introduction of HST were compared. Multivariate binary logistic regression models were used to access the association of different troponin assays with CAD (>50% for LM and >70% for the remaining). Sensitivity, specificity, NPV and PPV for angiographic CAD were also determined. Results The relative proportion of patients with UA and NSTEMI was similar between study periods: 31% vs 29% and 69% vs 71%, respectively (p=0.3). Clinical and angiographic characteristics did not differ in UA pts before and after the use of HST. NSTEMI patients in the HST era were less frequently women (39% vs 32%, p=0.026), had higher creatinine (0.93 IQR 0.75–1.3 vs 1.0 IQR 0.82–1.38), higher number of lesions (2 IQR 1–4 vs 3 IQR 1–4) and a lower rate of normal coronary arteries (10.5% vs 3.9%, p<0.001). The prevalence of significant CAD in this population, before and after HST, was 65% and 73%, respectively (p=0.001). However, when clinically relevant characteristics and judgement were accounted for, both standard troponin (OR 0.99, 95% CI 0.99–1.01) and HST (1.0, 95% CI 1.0–1.0) were poor predictors of significant CAD. Sensitivity was 69% vs 72%, specificity 30% vs 30%, PPV 65% vs 73% and NNP 34% vs 28%, respectively. Finally, rates of percutaneous intervention did not differ between the two periods (30% vs 33.5%, p=0.157), nor between ACS types within each period. CAD/PCI in ACS within each period Conclusion The introduction of HST did not result in an increase of the diagnosis of NSTEM vs UA, suggesting that clinical judgment remains an important determinant of the diagnosis of ACS. Also there was no evidence of an increase in PCI rates, despite worse CAD severity in NSTEMI patients.

Likelihood of obstructive coronary disease in metabolic syndrome patients with abnormal stress echocardiography

BackgroundMetabolic syndrome (MetSx) encompasses several risk factors for macrovascular coronary artery disease. An association between MetSx and coronary syndrome X has also been reported, suggesting that patients with MetSx are more likely to have endothelial dysfunction in the setting of angiographically normal coronary arteries. It remains unknown whether MetSx patients with abnormal stress echocardiography (SE) are more likely to have obstructive coronary disease (CAD) compared to patients without MetSx. MethodsWe identified symptomatic patients without known CAD and abnormal SE who underwent coronary angiography within 4weeks after the SE. Patients were grouped according to their MetSx and impaired fasting glucose (IFG) status. We compared the proportion of patients with obstructive CAD in each subgroup using the x2 test. Multivariate regression analysis was used to adjust for the pre-test probability of underlying coronary artery disease. ResultsAmong 583 consecutive symptomatic patients who had an abnormal SE and were referred for angiography, 158 (36%) met the NCEP definition of MetSx. MetSx patients had a trend towards having more obstructive CAD than those without MetSx (OR 1.44, p=0.07). After adjusting for pre-test probability of coronary disease, smoking and LDL-C, MetSx/IFG combination was an independent predictor of obstructive CAD (OR 2.06 [1.24-3.44], p<0.001) but MetSx with normal fasting blood glucose was not (OR 0.91 [0.47-1.70], p 0.09). ConclusionSymptomatic patients with MetSx and IFG are more likely to have angiographically significant CAD after abnormal SE than patients without MetSx or those with normal fasting blood glucose.

Progressing From Risk Factors to Omics

Many factors contribute to the development of clinical atherosclerotic disease in adults. Observational studies conducted from the late 1940s onward have helped us to identify cigarette smoking, cholesterol levels, diabetes, blood pressure, and other factors as important determinants of cardiovascular disease (CVD) outcomes.1,2 The effects are multiplicative. For example, smoking, hypertension, and diabetes each double the risk of a heart attack, and having all 3 factors can lead to a risk that was ≈8 times that of an adult of similar age and sex who did not have any of the factors.3 A major focus in the earlier population and clinical studies was identification of persons at increased risk before the clinical atherosclerotic event. Less attention has been directed toward other types of events, such as occurrence of a myocardial infarction in persons presenting with chest pain, recurrent CVD events, and long-term vascular disease complications such as cardiac failure. The determinants of these vascular events are likely to include some of the classical risk factors, but new factors will no doubt be important as well. Improvements in outpatient and inpatient care, diagnosis, and biomarker discovery have reshaped the landscape. It is possible to visualize subclinical CVD with modern atherosclerotic imaging techniques such as carotid intima-media thickness and arterial calcification assessments. Clinical chemists and geneticists identify new biomarkers that promise to help refine assessments of CVD risk, but it is not clear how such tests should be used for research or for clinical care. This article addresses several of the questions posed above and takes the perspective of research and care for clinical atherosclerotic disease, emphasizing the progress we have made from traditional risk factor assessment to the present time that includes newer assessment methods such as genomics, metabolomics, and predictive medicine. ### Traditional Risk Factors for Cardiovascular Disease The traditional risk factors include cholesterol, blood …

Trials and Tribulations of CRP as a Predictor of Coronary Disease

Even as interest grows in using C-reactive protein (CRP) for cardiac risk stratification, a new report might dampen enthusiasm for this test. As part of a prospective study of cardiovascular risk in 18,000 residents of Iceland, researchers measured CRP levels in stored frozen sera that were collected between 1967 and 1991. During an …

The value of C-reactive protein in cardiovascular risk prediction: the Rotterdam Study.

Epidemiologic studies have shown that C-reactive protein (CRP) is a risk factor for coronary heart disease. Whether routine measurement of CRP has a role in the prediction of future coronary disease in everyday clinical practice has not yet been investigated. Within the Rotterdam Study, a population-based cohort study of 7983 men and women 55 years and older, we conducted a nested case-control study to investigate the value of CRP in coronary disease prediction. Data are based on 157 participants who experienced a myocardial infarction during follow-up and 500 randomly selected controls. High-sensitivity CRP and traditional cardiovascular risk factors were measured at baseline. The age- and sex-adjusted relative risk of myocardial infarction for subjects in the highest quartile of the population distribution of CRP compared with the lowest quartile was 2.0 (95% confidence interval, 1.1-3.4). After additional adjustment for traditional cardiovascular risk factors, the increase in risk largely disappeared (odds ratio, 1.2; 95% confidence interval, 0.6-2.2). Adding CRP to a coronary disease risk function based on risk factors that are routinely assessed in clinical practice or to the Framingham risk function did not improve the area under the receiver operating characteristic curve of these risk functions. Sensitivity and specificity of both risk functions, computed after dichotomizing the estimated disease probabilities using prespecified cutoff points, hardly improved when CRP was added. Measurement of CRP in elderly people has no additional value in coronary disease risk prediction when traditional cardiovascular risk factors are known.

PREDICTORS OF CORONARY DISEASE IN PATIENTS WITH END STAGE RENAL DISEASE

Patients with end stage renal disease have a high prevalence of cardiovascular disease and coronary arteriography is often routinely performed prior to kidney transplantation. However, the value of the conventional risk factors and non-invasive markers of coronary artery disease (CAD) in triaging patients for coronary arteriography has not been fully examined. 116 patients with end stage renal disease were evaluated. Coronary arteriography was performed in all patients either for a suspicion of CAD or as part of a routine pre-transplant evaluation. Lesions causing ≥ 50% luminal diameter stenosis in any of the three major coronary artery systems were considered significant. The mean age was 53.3 ± 9.3 years. Significant CAD was present in 69 patients (60%). Increasing age, family history of premature ischemic heart disease, the presence of angina, abnormal Q waves on the ECG or abnormal ST segment depression and the presence of coronary calcification were significant markers of coronary artery disease. However male gender, diabetes mellitus and obesity did not correlate with coronary disease. Even though hypertension, hypercholesterolemia and smoking were also not useful predictors these could have been modified by the renal failure. In conclusion increasing age, a family history of premature ischemic heart disease and some non-invasive markers were useful predictors of coronary disease.

Aortic Stiffness Versus Framingham Score as Independent Predictors of Coronary Heart Disease in Hypertensive Patients

P113 Background : Although various studies reported that pulse pressure, an indirect index of arterial stiffness, was an independent risk factor for coronary heart disease (CHD), a direct relationship between arterial stiffness and CHD remained to be established in patients with essential hypertension. Methods : A cohort of 1212 essential hypertensives patients, who had a measurement of arterial stiffness between 1980 and 1996, was studied. At entry, aortic stiffness was assessed from the carotid-femoral pulse wave velocity (PWV). A coronary disease prediction algorithm (Wilson P et al. Circulation 1998), based on the Framingham Heart Study (Framingham algorithm, FA), was calculated according to categories of sex, age, blood pressure, cholesterol, diabetes, and smoking, but not PWV. The ranges of FA and PWV values, included within the 1st and the 9th deciles, were 2-11 points and 8-16 m/s, respectively. CHD included fatal and non fatal myocardial infarction, coronary revascularization, and angina pectoris. The Cox proportional hazard regression model was used to estimate the relative risk (RR) of CHD. Results : Mean age at entry was 52±13 years (mean±SD). The mean delay to the first CHD event was 69±63 months. Seventy-three fatal and non fatal CHD events occurred. In this French population, the FA significantly predicted the occurence of CHD in the whole population (RR=1.10 (1.03-1.17) for 1 point of FA, P Conclusion : This study provides the first direct evidence that aortic stiffness is an independent predictor of CHD in patients with essential hypertension. Aortic stiffness alone has a similar predictive value than the Framingham algorithm for CHD, and a better predictive value for primary CHD events.

Aortic Stiffness Versus Framingham Score as Independent Predictors of Coronary Heart Disease in Hypertensive Patients

P113 Background : Although various studies reported that pulse pressure, an indirect index of arterial stiffness, was an independent risk factor for coronary heart disease (CHD), a direct relationship between arterial stiffness and CHD remained to be established in patients with essential hypertension. Methods : A cohort of 1212 essential hypertensives patients, who had a measurement of arterial stiffness between 1980 and 1996, was studied. At entry, aortic stiffness was assessed from the carotid-femoral pulse wave velocity (PWV). A coronary disease prediction algorithm (Wilson P et al. Circulation 1998), based on the Framingham Heart Study (Framingham algorithm, FA), was calculated according to categories of sex, age, blood pressure, cholesterol, diabetes, and smoking, but not PWV. The ranges of FA and PWV values, included within the 1st and the 9th deciles, were 2-11 points and 8-16 m/s, respectively. CHD included fatal and non fatal myocardial infarction, coronary revascularization, and angina pectoris. The Cox proportional hazard regression model was used to estimate the relative risk (RR) of CHD. Results : Mean age at entry was 52±13 years (mean±SD). The mean delay to the first CHD event was 69±63 months. Seventy-three fatal and non fatal CHD events occurred. In this French population, the FA significantly predicted the occurence of CHD in the whole population (RR=1.10 (1.03-1.17) for 1 point of FA, P&lt;0.01), but not in patients devoid of cardiovascular disease (other than hypertension) at entry. PWV was a significant independent predictor of CHD not only in the whole population (RR=1.07(1.02-1.12) for 1 m/s PWV, P&lt;0.01), but also in patients devoid of previous cardiovascular disease at entry (primary events) (RR=1.11 (1.02-1.20), P=0.01). The predictive value of PWV remained unchanged after adjustment for FA and pulse pressure. Conclusion : This study provides the first direct evidence that aortic stiffness is an independent predictor of CHD in patients with essential hypertension. Aortic stiffness alone has a similar predictive value than the Framingham algorithm for CHD, and a better predictive value for primary CHD events.

Assessing the cause of T wave inversion in precordial leads with ECG mapping

Inversion of the T wave in precordial leads in patients with angina pectoris is a predictor of coronary disease; however, it may also be seen in normal adults. The aim of this study was to assess the cause of T wave inversion by carrying out precordial electrocardiographic (ECG) mapping in 51 patients, who also underwent echocardiography and coronary angiography. The 37 patients in group A had atypical symptoms. They included 11 patients who showed M pattern mapping, of whom 7 had noncoronary cardiac disease and 4 were normal. In 23 other group A patients, whose mappings were in the N pattern, the angiography was normal. In the remaining three patients of this group, mappings were in the I pattern, with angiography revealing coronary disease in two of them and no disease in the third. The 14 group B patients all had typical angina; mappings were in the I pattern in 8 of the patients and in the N pattern in the remaining 6. Angiography revealed coronary artery disease in all patients with the I pattern mapping, while all those with the N pattern were found to be normal. Sensitivity, specificity, and positive predictive value for detecting normal subjects were all 100% for N pattern mapping; for detecting coronary disease, they were 100%, 90%, and 90% for I pattern mapping, respectively. It is concluded that precordial ECG mapping is an accurate method for the assessment of T wave inversion in precordial leads.

Goals of antihypertensive therapy.

Antihypertensive therapy has been used for almost 40 years to reduce blood pressure and to prevent morbidity and mortality related to the hypertensive state. Cardiovascular events are related to the initial elevation of blood pressure; the benefits of treating malignant, severe or moderate hypertension are well established. Although large scale clinical trials have demonstrated a decrease in morbid events when mildly elevated blood pressures is treated, the benefits are neither universal or dramatic and treatment is certainly less cost effective than no treatment. Recently it has been emphasised that the absolute risk of cardiovascular events is determined only in part by blood pressure, and that it is also influenced by age, gender, race and the presence of other cardiovascular risk factors. For example, in older individuals where the absolute risk of vascular complications is greater than in younger individuals for any given level of blood pressure, the benefits of therapy will be greater. It has been suggested that in younger individuals with mild hypertension and a low absolute risk of developing cardiovascular morbid events it may be more appropriate to monitor the effects of drug therapy on measures of cardiac and vascular damage that are associated with the hypertensive state. Drug therapy has been shown to be extremely effective in reducing the incidence of stroke, congestive cardiac failure and renal failure associated with elevated blood pressure. Meta-analysis of randomised large scale clinical trials indicates that drug therapy may not reduce coronary events to the extent expected in patients with hypertension. One plausible explanation is that the trials have been of insufficient duration to detect the benefit of blood pressure lowering on coronary heart disease. It has also been suggested that certain adverse metabolic effects associated with the use of thiazide diuretics and beta-blockers employed in these trials may have partially offset the benefits of blood pressure reduction. However, the clinical significance of these drug-induced metabolic disturbances remains unclear. Experimental data suggesting differences in the ability of antihypertensive drugs to inhibit atherosclerosis in animal models are also of interest, but again the relation of the findings to the clinical situation is unknown. Thiazide diuretics, beta-blockers, calcium antagonists, angiotensin-converting enzyme (ACE) inhibitors and alpha-blockers can produce regression of left ventricular hypertrophy (LVH). While LVH is clearly a strong and independent predictor for coronary disease, it remains to be shown that a lower risk for coronary morbid events exists in patients whose LVH has undergone regression over and above that attributable to blood pressure reduction.(ABSTRACT TRUNCATED AT 400 WORDS)

Relation of high-density lipoprotein subfractions and apolipoprotein E isoforms to coronary disease

Although a variety of methods have become available for the determination of high-density lipoprotein (HDL) subfractions in plasma, a review of published data from nine studies of coronary disease outcomes and 10 investigations of coronary artery disease severity do no suggest that measurement of HDL2-cholesterol (C) and HDL3-C offer any advantage in the prediction of coronary disease over the determination of total HDL-C alone. Apolipoprotein E is typically present in plasma as one of six isoforms, the six being encoded by three common alleles, epsilon 2, epsilon 3, and epsilon 4. The epsilon 3 allele is the most common, the epsilon 4 allele has been reported to be associated with higher cholesterol concentrations, and the epsilon 2 and epsilon 4 alleles are both associated with higher triglyceride concentrations. Clinical and arteriographic studies of coronary disease suggest that vascular disease risk is increased among persons with the epsilon 4 allele.

Lipid factors as predictors of coronary disease

Journal Article Lipid factors as predictors of coronary disease Get access A Ruelland, A Ruelland Search for other works by this author on: Oxford Academic Google Scholar P Guillo, P Guillo Search for other works by this author on: Oxford Academic Google Scholar G Gallou, G Gallou Search for other works by this author on: Oxford Academic Google Scholar B Legras, B Legras Search for other works by this author on: Oxford Academic Google Scholar F Paillard, F Paillard Search for other works by this author on: Oxford Academic Google Scholar L Cloarec L Cloarec Search for other works by this author on: Oxford Academic Google Scholar Clinical Chemistry, Volume 39, Issue 8, 1 August 1993, Pages 1755–1756, https://doi.org/10.1093/clinchem/39.8.1755 Published: 01 August 1993

Efficacy of lipid profiles in prediction of coronary disease

National guidelines in the United States and Europe have stimulated interest in controlling blood lipid levels to prevent CHD. In this review, the effciency of lipid profiles in predicting CHD has been examined, and total cholesterol, HDL and LDL cholesterol, and triglyceride values have been compared on the basis of 12 to 14 years of surveillance in the Framingham Study. The average value of total cholesterol and LDL cholesterol in patients who had coronary disease was at or below values that are considered dangerous, which indicates the need for more specific and sensitive lipid profiles. Measurement of LDL cholesterol levels predicted CHD only marginally better than measurement of serum total cholesterol. Measurement of triglyceride levels was the weakest predictor. The total cholesterol to HDL cholesterol ratio was the most efficient predictor both in those with apparently safe and those with abnormal cholesterol values. Measurement of HDL cholesterol was the best single lipid predictor and use of this measurement avoids needlessly alarming or falsely reassuring persons at risk for CHD who have high total cholesterol values. Since the risk associated with any serum cholesterol value varies over a 10-fold range depending on coexistent cardiovascular risk factors, these lipid factors must be taken into account in judging the hazards and efficacy of treatment needed. Evidence is available that controlling elevated cholesterol by diet and administration of pharmaceutical agents can reduce the rate of coronary events, slow progression of angiographically visualized lesions, and regress xanthomata. Hence persons at high risk for CHD who have adverse lipid and cardiovascular risk profiles can be efficiently selected for and can benefit from dietary and drug therapy.

Lipoproteins in the Elderly

Changes in lipid metabolism with age result in lower total serum cholesterol and low-density lipoprotein concentrations. There is no evidence that longevity and lipid profiles are influenced by genetic make-up. It is difficult to establish an optimum total serum cholesterol in the elderly but values established in younger subjects give a guide. High-density lipoprotein may be even more protective in the elderly and could turn out to be a better predictor of coronary disease. Screening for the treatment of hypercholesterolaemia should be carried out in the elderly. Although death is an inevitable fact, intervention in, for example, recently retired, apparently disease-free subjects is important. The first approach should be the introduction of changes in life style (increased exercise, stopping smoking, improved diet). Drugs may also be introduced if these interventions fail. Although drug therapy in the elderly may pose immediate problems due to poor renal and hepatic function, the adverse effects of long-term use have less relevance in the elderly.

Coronary disease prediction using a new atherogenic index

This report demonstrates the utilization of a new serum factor, Toxicity Preventing Activity (TxPA) in the diagnosis of coronary disease prone individuals. Our laboratory has recently identified TxPA, which offsets the toxicity of very low density lipoproteins (VLDL) upon arterial cells in vitro. In the present study, we measured TxPA activity and serum lipoprotein levels in 73 individuals undergoing coronary angiography. Serum from control subjects demonstrated 270% more TxPA than aged matched individuals with angiographically demonstrable coronary disease (CHD). When TxPA was combined with serum lipoprotein values, a new atherogenic index was generated which further distinguished these individuals with CHD from non-angiographed controls. These results demonstrate that TxPA is a new protective factor in coronary artery disease, and that the new atherogenic index provides for the first time an accurate classification of individuals with coronary artery disease.

Correlations of systolic time intervals and radionuclide angiography at rest and during exercise

Systolic time intervals (STI) were correlated with radionuclide angiography studies (RAS) in 57 patients at rest, during maximal semisitting bicycle exercise, and at 4 minutes following the cessation of exercise. Eleven were judged as being free of coronary artery disease (group 1), while 14 had coronary artery disease without (group 2A), and 27 (group 2B) with a previous transmural myocardial infarction. For RAS, resting radionuclide ejection fraction (REF), the changes in REF and end-systolic volume, and the development of a wall motion abnormality at peak exercise were each highly correlated with the presence of coronary disease ( p < 0.001). The accuracy of STI parameters in predicting the presence of coronary disease was poor (<60%). Changes in end-diastolic volume (EDV) correlated significantly with PEP LVET and LVET, changes following exercise. Moreover, patients with an abnormal (>25%) increase in EDV at peak exercise had a greater increase in LVET, in the postexercise period ( p < 0.01). We conclude that STI is not accurate enough a predictor of coronary disease or left ventricular function to serve as a useful screening test. Changes in STI parameters appear to be more related to changes in ventricular volume than to ventricular function.