Coronary heart disease classification using deep learning approach with feature selection for improved accuracy.

BACKGROUND: Coronary heart disease (CHD) is one of the deadliest diseases and a risk prediction model for cardiovascular conditions is needed. Due to the huge number of features that lead to heart problems, it is often difficult for an expert to evaluate these huge features into account. So, there is a need of appropriate feature selection for the given CHD dataset. For early CHD detection, deep learning modes (DL) show promising results in the existing studies. OBJECTIVE: This study aimed to develop a deep convolution neural network (CNN) model for classification with a selected number of efficient features using the LASSO (least absolute shrinkage and selection operator) technique. Also, aims to compare the model with similar studies and analyze the performance of the proposed model using accuracy measures. METHODS: The CHD dataset of NHANES (National Health and Nutritional Examination Survey) was examined with 49 features using LASSO technique. This research work is an attempt to apply an improved CNN model for the classification of the CHD dataset with huge features CNN model with feature extractor consists of a fully connected layer with two convolution 1D layers, and classifier part consists of two fully connected layers with SoftMax function was trained on this dataset. Metrics like accuracy recall, specificity, and ROC were used for the evaluation of the proposed model. RESULTS: The feature selection was performed by applying the LASSO model. The proposed CNN model achieved 99.36% accuracy, while previous studies model achieved over 80 to 92% accuracy. CONCLUSION: The application of the proposed CNN with the LASSO model for the classification of CHD can speed up the diagnosis of CHD and appears to be effective in predicting cardiovascular disease based on risk features.

Urinary metabolomic profiling reveals difference between two traditional Chinese medicine subtypes of coronary heart disease.

The World Health Organization has shown that coronary heart disease (CHD) is a more common cause of death than cancer. In traditional Chinese medicine (TCM), CHD is classified as a form of thoracic obstruction that can be divided in different subtypes including Qi stagnation with blood stasis (QS) and Qi deficiency with blood stasis (QD). Different treatment strategies are used based on this subtyping. Owing to the lack of scientific markers in the diagnosis of these subtypes, subjective judgments made by clinicians have limited the objective manner for utility of TCM in the treatment of CHD. Untargeted (UHPLC-QTOF-MS) and targeted (UHPLC-MS/MS) metabolomics approaches were employed to search significantly different metabolites related to the QS or QD subtypes of CHD with angina pectoris in this study. A total of 42 metabolites were obtained in the untargeted metabolomics analysis and 34 amino acids were detected in the targeted metabolomics analysis. In total, 16 metabolites were found significantly different among different groups. The results showed distinct metabolic profiles of urine samples not only between CHD patients and healthy controls, but also between the two subtypes of CHD. Pathway analysis of the significantly varied metabolites revealed that there were subtype-related differences in the activity of pathways. Therefore, urinary metabolomics can reveal the pathological changes of CHD in different subtypes, make the diagnosis of CHD in different subtypes in an objective manner and comprehensive and contribute to personalized treatment by providing scientific evidence.

Non-invasive characterization of complex coronary lesions.

Conventional invasive diagnostic imaging techniques do not adequately resolve complex Type B and C coronary lesions, which present unique challenges, require personalized treatment and result in worsened patient outcomes. These lesions are often excluded from large-scale non-invasive clinical trials and there does not exist a validated approach to characterize hemodynamic quantities and guide percutaneous intervention for such lesions. This work identifies key biomarkers that differentiate complex Type B and C lesions from simple Type A lesions by introducing and validating a coronary angiography-based computational fluid dynamic (CFD-CA) framework for intracoronary assessment in complex lesions at ultrahigh resolution. Among 14 patients selected in this study, 7 patients with Type B and C lesions were included in the complex lesion group including ostial, bifurcation, serial lesions and lesion where flow was supplied by collateral bed. Simple lesion group included 7 patients with lesions that were discrete, [Formula: see text] long and readily accessible. Intracoronary assessment was performed using CFD-CA framework and validated by comparing to clinically measured pressure-based index, such as FFR. Local pressure, endothelial shear stress (ESS) and velocity profiles were derived for all patients. We validates the accuracy of our CFD-CA framework and report excellent agreement with invasive measurements ([Formula: see text]). Ultra-high resolution achieved by the model enable physiological assessment in complex lesions and quantify hemodynamic metrics in all vessels up to 1mm in diameter. Importantly, we demonstrate that in contrast to traditional pressure-based metrics, there is a significant difference in the intracoronary hemodynamic forces, such as ESS, in complex lesions compared to simple lesions at both resting and hyperemic physiological states [n = 14, [Formula: see text]]. Higher ESS was observed in the complex lesion group ([Formula: see text] Pa) than in simple lesion group ([Formula: see text] Pa). Complex coronary lesions have higher ESS compared to simple lesions, such differential hemodynamic evaluation can provide much the needed insight into the increase in adverse outcomes for such patients and has incremental prognostic value over traditional pressure-based indices, such as FFR.

A module of multifactor-mediated dysfunction guides the molecular typing of coronary heart disease.

BACKGROUND: Coronary atherosclerotic heart disease (CHD) is the most common cardiovascular disease and has become a leading cause of death globally. Various molecular typing methods are available for the diagnosis and treatment of tumors. However, molecular typing results are not routinely used for CHD. METHODS AND RESULTS: Aiming to uncover the underlying molecular features of different types of CHD, we screened the differentially expressed genes (DEGs) associated with CHD based on the Gene Expression Omnibus (GEO) data and expanded those with the NCBI-gene and OMIM databases to finally obtain 2021 DEGs. The weighted gene co-expression analysis (WGCNA) was performed on the candidate genes, and six distinctive WGCNA modules were identified, two of which were associated with CHD. Moreover, DEGs were mined as key genes for co-expression based on the module network relationship. Furthermore, the differentially expressed miRNAs in CHD and interactions in the database were mined in the GEO data set to build a multifactor regulatory network of key genes for co-expression. Based on the network, the CHD samples were further classified into five clusters and we defined FTH1, HCAR3, RGS2, S100A9, and TYROBP as the top genes of the five subgroups. Finally, the mRNA levels of FTH1, S100A9, and TYROBP were found to be significantly increased, while the expression of HCAR3 was decreased in the blood of CHD patients. We did not detect measurable levels of RGS2. CONCLUSION: The screened core clusters of genes may be a target for the diagnosis and treatment of CHD as a molecular typing module.

Classification of Patients with Coronary Microvascular Dysfunction.

While coronary microvascular dysfunction (CMD) is a major cause of ischemia, it is very challenging to diagnose due to lack of CMD-specific screening measures. CMD has been identified as one of the five priority areas of investigation in a 2014 National Research Consensus Conference on Gender-Specific Research in Emergency Care. In this study, we utilized methods from machine learning that leverage structured and unstructured narratives in clinical notes to detect patients with CMD. We have shown that structured data are not sufficient to detect CMD and integrating unstructured data in the computational model boosts the performance significantly.

Immunoglobulin E-mediated severe allergy to hyoscine butylbromide

No disponible

Kounis syndrome associated with selective anaphylaxis to cefazolin

No disponible

Association of high-density lipoprotein cholesterol concentration with different types of stroke and coronary heart disease: The Japan Public Health Center-based prospective (JPHC) study.

BACKGROUND AND AIMS: Although low high-density lipoprotein (HDL) cholesterol concentration is an established risk factor for coronary heart disease (CHD), information regarding subtypes of stroke is very limited, especially in Asian populations. METHODS: A prospective study was conducted among 30,736 individuals aged 40-69 years, who lived in nine communities in Japan and did not have a history of cardiovascular disease (CVD). CHD and stroke, including its subtypes, were assessed, and sex-specific hazard ratios (HRs) and 95% confidence intervals (CIs) for outcomes were estimated according to quintiles of HDL cholesterol using Cox proportional models adjusted for other CVD risk factors. RESULTS: We identified 296 CHD and 1712 stroke events over a median 15 yr of follow-up. HDL cholesterol concentration showed an inverse association with CHD in men and women. A low HDL cholesterol concentration slightly raised the risk for total strokes in men, but not in women. When analyzed by subtypes, we observed an inverse relationship between HDL cholesterol concentration and the incidence of lacunar infarction, with an adjusted HR for the lowest quintile of HDL cholesterol concentration compared with the highest quintile of 1.63 (95% CI, 1.00-2.66) in men and 1.97 (95% CI, 1.19-3.26) in women. HDL cholesterol concentration was positively associated with the risk of intracerebral hemorrhage (ICH) in a linear manner in women (p for trend = 0.028), but not in men. CONCLUSIONS: The associations of HDL cholesterol concentration with lacunar infarction and ICH may be related to different functional properties of HDL rather than to its protective function against lipid-rich atherosclerosis.

Trends in mortality rates by subtypes of heart disease in Mississippi, 1980-2013.

BACKGROUND: Heart disease (HD) is the leading cause of death among Mississippians. However, trends in mortality rates for HD subtypes in Mississippi have not been adequately described. This study examined trends in mortality rates for HD subtypes among adults in Mississippi from 1980 through 2013. METHODS: We used Mississippi Vital Statistics data to calculate age-specific mortality rates for HD subtypes for Mississippians age 35 and older. Cases were identified via underlying cause of death codes from the International Classification of Diseases, Ninth Revision (ICD-9) and Tenth Revision (ICD-10). We used Joinpoint software to calculate the average annual percent change (AAPC) in mortality rates for HD subtypes by race, sex, and age group. RESULTS: Overall, the age-adjusted coronary heart disease (CHD) mortality rate among Mississippi adults decreased by 62.7% between 1980 and 2013, with an AAPC of -3.0% (95% CI -3.7 to -2.3), while the age-adjusted heart failure mortality rate increased by 66.7%, with an AAPC of 1.4% (95% CI 0.5 to 2.3). Trends varied across HD subtypes: Annual rates of hypertensive HD mortality increased significantly for men, for individuals age 35 to 54, and for individuals age 75 and older. CHD mortality experienced a significant annual decrease among all race, sex, and age subgroups, while heart failure increased significantly among women, whites, and individuals age 75 and older. CONCLUSIONS: From 1980 to 2013, CHD mortality decreased significantly while heart failure mortality increased significantly among adult Mississippians. However, HD subtype trends differed by race, sex, and age group.

The Variation in Recovery: Role of Gender on Outcomes of Young AMI Patients (VIRGO) Classification System: A Taxonomy for Young Women With Acute Myocardial Infarction.

BACKGROUND: Current classification schemes for acute myocardial infarction (AMI) may not accommodate the breadth of clinical phenotypes in young women. METHODS AND RESULTS: We developed a novel taxonomy among young adults (≤55 years) with AMI enrolled in the Variation in Recovery: Role of Gender on Outcomes of Young AMI Patients (VIRGO) study. We first classified a subset of patients (n=600) according to the Third Universal Definition of MI using a structured abstraction tool. There was heterogeneity within type 2 AMI, and 54 patients (9%; including 51 of 412 women) were unclassified. Using an inductive approach, we iteratively grouped patients with shared clinical characteristics, with the aims of developing a more inclusive taxonomy that could distinguish unique clinical phenotypes. The final VIRGO taxonomy classified 2802 study participants as follows: class 1, plaque-mediated culprit lesion (82.5% of women; 94.9% of men); class 2, obstructive coronary artery disease with supply-demand mismatch (2a: 1.4% women; 0.9% men) and without supply-demand mismatch (2b: 2.4% women; 1.1% men); class 3, nonobstructive coronary artery disease with supply-demand mismatch (3a: 4.3% women; 0.8% men) and without supply-demand mismatch (3b: 7.0% women; 1.9% men); class 4, other identifiable mechanism (spontaneous dissection, vasospasm, embolism; 1.5% women, 0.2% men); and class 5, undetermined classification (0.8% women, 0.2% men). CONCLUSIONS: Approximately 1 in 8 young women with AMI is unclassified by the Universal Definition of MI. We propose a more inclusive taxonomy that could serve as a framework for understanding biological disease mechanisms, therapeutic efficacy, and prognosis in this population.

Performance criteria based on true and false classification and clinical outcomes. Influence of analytical performance on diagnostic outcome using a single clinical component.

BACKGROUND: In the general classical model for diagnoses based on a single analytic component, distributions of healthy and diseased are compared and several investigations of varying analytical performance on the percentage of misclassifications have been published. A new concept based on an alternative type of diagnosing, based on sharp decision limits has been introduced in diagnostic guidelines, but only a few publications on investigation of analytical performance have been seen. METHODS: The two diagnostic models (bimodal and unimodal) based on natural logarithmic Gaussian distributions are simulated. RESULTS: In the bimodal model it is possible to evaluate the influence of prevalence of disease in combination with varying analytical performances. In the unimodal model the prevalence is pre-decided by the chosen decision limit. In this model the influence of analytical performance is investigated for diagnosing diabetes using haemoglobin A1c (HbA1c), and for patients with high and low risk for coronary heart disease defined by serum-cholesterol concentrations. CONCLUSIONS: For HbA1c the guidelines and recommendations define a maximum inter-laboratory coefficient of variation of 3.5%, but this is in DCCT units (without a true zero-point), so after transformation to IFCC units (which are proportional) it was 5.2%, which allows for analytical bias as high as approximately ±9%. Consequently, analytical quality specifications should be separated as maximum bias and imprecision.

An analysis of chemical ingredients network of Chinese herbal formulae for the treatment of coronary heart disease.

As a complex system, the complicated interactions between chemical ingredients, as well as the potential rules of interactive associations among chemical ingredients of traditional Chinese herbal formulae are not yet fully understood by modern science. On the other hand, network analysis is emerging as a powerful approach focusing on processing complex interactive data. By employing network approach in selected Chinese herbal formulae for the treatment of coronary heart disease (CHD), this article aims to construct and analyze chemical ingredients network of herbal formulae, and provide candidate herbs, chemical constituents, and ingredient groups for further investigation. As a result, chemical ingredients network composed of 1588 ingredients from 36 herbs used in 8 core formulae for the treatment of CHD was produced based on combination associations in herbal formulae. In this network, 9 communities with relative dense internal connections are significantly associated with 14 kinds of chemical structures with P<0.001. Moreover, chemical structural fingerprints of network communities were detected, while specific centralities of chemical ingredients indicating different levels of importance in the network were also measured. Finally, several distinct herbs, chemical ingredients, and ingredient groups with essential position in the network or high centrality value are recommended for further pharmacology study in the context of new drug development.

Guía de práctica clínica de la ESC sobre revascularización miocárdica, 2014 / No disponible

No disponible

Coronary artery calcification scoring with state-of-the-art CT scanners from different vendors has substantial effect on risk classification.

PURPOSE: To determine the intervendor variability of Agatston scoring determined with state-of-the-art computed tomographic (CT) systems from the four major vendors in an ex vivo setup and to simulate the subsequent effects on cardiovascular risk reclassification in a large population-based cohort. MATERIALS AND METHODS: Research ethics board approval was not necessary because cadaveric hearts from individuals who donated their bodies to science were used. Agatston scores obtained with CT scanners from four different vendors were compared. Fifteen ex vivo human hearts were placed in a phantom resembling an average human adult. Hearts were scanned at equal radiation dose settings for the systems of all four vendors. Agatston scores were quantified semiautomatically with software used clinically. The ex vivo Agatston scores were used to simulate the effects of different CT scanners on reclassification of 432 individuals aged 55 years or older from a population-based study who were at intermediate cardiovascular risk based on Framingham risk scores. The Friedman test was used to evaluate overall differences, and post hoc analyses were performed by using the Wilcoxon signed-rank test with Bonferroni correction. RESULTS: Agatston scores differed substantially when CT scanners from different vendors were used, with median Agatston scores ranging from 332 (interquartile range, 114-1135) to 469 (interquartile range, 183-1381; P < .05). Simulation showed that these differences resulted in a change in cardiovascular risk classification in 0.5%-6.5% of individuals at intermediate risk when a CT scanner from a different vendor was used. CONCLUSION: Among individuals at intermediate cardiovascular risk, state-of the-art CT scanners made by different vendors produced substantially different Agatston scores, which can result in reclassification of patients to the high- or low-risk categories in up to 6.5% of cases.

South American Guidelines for Cardiovascular Disease Prevention and Rehabilitation / Diretriz Sul-Americana de Prevenção e Reabilitação Cardiovascular

In this document, the Inter-American Committee of Cardiovascular Prevention and Rehabilitation, together with the South American Society of Cardiology, aimed to formulate strategies, measures, and actions for cardiovascular disease prevention and rehabilitation (CVDPR). In the context of the implementation of a regional and national health policy in Latin American countries, the goal is to promote cardiovascular health and thereby decrease morbidity and mortality. The study group on Cardiopulmonary and Metabolic Rehabilitation from the Department of Exercise, Ergometry, and Cardiovascular Rehabilitation of the Brazilian Society of Cardiology has created a committee of experts to review the Portuguese version of the guideline and adapt it to the national reality. The mission of this document is to help health professionals to adopt effective measures of CVDPR in the routine clinical practice. The publication of this document and its broad implementation will contribute to the goal of the World Health Organization (WHO), which is the reduction of worldwide cardiovascular mortality by 25% until 2025. The study group's priorities are the following: • Emphasize the important role of CVDPR as an instrument of secondary prevention with significant impact on cardiovascular morbidity and mortality; • Join efforts for the knowledge on CVDPR, its dissemination, and adoption in most cardiovascular centers and institutes in South America, prioritizing the adoption of cardiovascular prevention methods that are comprehensive, practical, simple and which have a good cost/benefit ratio; • Improve the education of health professionals and patients with education programs on the importance of CVDPR services, which are directly targeted at the health system, clinical staff, patients, and community leaders, with the aim of decreasing the barriers to CVDPR implementation.

Com este documento, o Comitê Interamericano de Prevenção e Reabilitação Cardiovascular, em posição conjunta com a Sociedade Sul-Americana de Cardiologia, mostra seu interesse no desenvolvimento de estratégias, medidas e intervenções para a prevenção e a reabilitação cardiovascular. Com o objetivo de implementar na América Latina uma política de saúde regional e nacional dos países membros, tem-se o objetivo de promover a saúde cardiovascular e, consequentemente, diminuir a morbimortalidade. O grupo de estudos em Reabilitação Cardiopulmonar e Metabólica do Departamento de Exercício, Ergometria e Reabilitação Cardiovascular de Sociedade Brasileira de Cardiologia (DERC/SBC) criou uma comissão de experts para revisar a versão em português e adaptá-la à realidade nacional. Este documento tem como missão principal auxiliar os profissionais de saúde a alcançarem medidas efetivas de prevenção e reabilitação cardiovascular (RCV) na prática clínica diária. Com a difusão deste documento, bem como com a sua implementação de forma mais abrangente, contribuiremos com a meta da Organização Mundial de Saúde de diminuir a mortalidade cardiovascular no mundo em 25% até o ano de 2025. As prioridades deste grupo de trabalho são: • Enfatizar o caráter prioritário da RCV como instrumento de prevenção secundária com importante impacto na morbimortalidade cardiovascular; • Unir esforços para melhorar o conhecimento da RCV, sua difusão e aplicação na maioria dos centros e institutos cardiovasculares da América do Sul, priorizando a utilização de um método de prevenção cardiovascular integral, prático, de fácil aplicação e de custo/benefício comprovado; • Melhorar a educação do pessoal da saúde e dos pacientes por meio de programas educativos dirigidos, que permitam envolver diretamente os sistemas de saúde, pessoal médico, pacientes e líderes comunitários sobre a importância dos serviços de RCV, a fim de diminuir as barreiras para a sua implantação.

Acute effects of outdoor air pollution on emergency department visits due to five clinical subtypes of coronary heart diseases in shanghai, china.

BACKGROUND: Air pollution can be a contributing cause to the development and exacerbation of coronary heart disease (CHD), but there is little knowledge about the acute effects of air pollution on different clinical subtypes of CHD. METHODS: We conducted a time-series study to investigate the association of air pollution (particulate matter with an aerodynamic diameter < 10 µm [PM10], sulfur dioxide [SO2], and nitrogen dioxide [NO2]) on emergency department (ED) visits due to five different subtypes of CHD in Shanghai, China, from 2010 to 2012. We applied an over-dispersed Poisson generalized addictive model to analyze the associations after controlling for the seasonality, day of the week, and weather conditions. RESULTS: We identified a total of 47 523 ED visits for CHD. A 10-µg/m(3) increase in the present-day concentrations of PM10, SO2, and NO2 was associated with respective increases of 1.10% (95% confidence interval [CI] 0.33%-1.87%), 0.90% (95% CI -0.14%-1.93%), and 1.44% (95% CI 0.63%-2.26%) for total ED visits for CHD. These associations varied greatly by clinical type, with strong effects on sudden cardiac death, moderate effects on acute myocardial infarction and angina, weak effects on ischemic cardiomyopathy, and no effect on occult CHD. The associations were stronger among people aged 65 years or more than in younger individuals and in the cool season versus the warm one. CONCLUSIONS: Outdoor air pollution may have different effects of air pollution on 5 subtypes of CHD. Our results might be useful for the primary prevention of various subtypes of CHD exacerbated by air pollution.

The diagnostic criteria of blood-stasis syndrome: considerations for standardization of pattern identification.

Pattern identification (PI), also called Bian Zheng ([symbols; see text]), syndrome differentiation, pattern diagnosis, or pattern classification, is the basic principle and the key concept of Chinese medicine (CM). The core of PI is CM syndrome, on which CM theory, therapeutic method, prescribing formula and the use of Chinese herbal medicine are basically based. PI, in fact, is another classification method anticipated to improve the clinical efficacy. How to make an exact PI seems to be very important for taking full advantage of PI in clinical practice. Therefore, the establishment of diagnostic criterion of pattern has been the prerequisite for the standardization of PI. In recent years, a lot of diagnostic criteria of different CM patterns have been formulated. Taking the diagnostic criteria for blood-stasis syndrome as a model, the methodologies and considerations in establishing a pattern diagnostic criterion were discussed in this paper, which might be of great reference value in future PI standardization research.