Detection and Classification of electrocardiography using hybrid deep learning models.

BACKGROUND: Electrocardiography (ECGs) has been a vital tool for cardiovascular disease (CVD) diagnosis, which visually depicts the heart's electrical activity. To enhance automatic classification between normal and diseased ECG, it is essential to extract consistent and qualitative features. METHODS: Precision of ECG classification through hybrid Deep Learning (DL) approach leverages both Convolutional Neural Network (CNN) architecture and Variational Autoencoder (VAE) techniques. By combining these methods, we aim to achieve more accurate and robust ECG interpretation. The method is trained and tested over PTB-XL dataset, which contains 21,799 with 12-lead ECGs from 18,869 patients, each spanning 10 seconds. The classification evaluation of 5 super-classes and 23 sub-classes of CVD, with the proposed CNN-VAE model is compared. RESULTS: The classification of various CVD had resulted with the highest accuracy of 98.51%, specificity of 98.12%, sensitivity 97.9% and F1-score 97.95%. We have also achieved the minimum false positive and false negative rates as 2.07 and 1.87 respectively during validation. The results are validated upon the annotations given by individual cardiologists, who assigned potentially multiple ECG statements to each record. CONCLUSION: When compared to other deep learning methods, our suggested CNN-VAE model performs significantly better in testing phase. This study proposes a new architecture of combining CNN-VAE for CVD classification from ECG data, this can help the clinicians to identify the disease earlier and carry further treatment. The CNN-VAE model can better characterize input signals due to its hybrid architecture.

Cardiovascular disease detection from cardiac arrhythmia ECG signals using artificial intelligence models with hyperparameters tuning methodologies.

Cardiovascular disease (CVD) is connected with irregular cardiac electrical activity, which can be seen in ECG alterations. Due to its convenience and non-invasive aspect, the ECG is routinely exploited to identify different arrhythmias and automatic ECG recognition is needed immediately. In this paper, enhancement for the detection of CVDs such as Ventricular Tachycardia (VT), Premature Ventricular Contraction (PVC) and ST Change (ST) arrhythmia using different dimensionality reduction techniques and multiple classifiers are presented. Three-dimensionality reduction methods, such as Local Linear Embedding (LLE), Diffusion Maps (DM), and Laplacian Eigen (LE), are employed. The dimensionally reduced ECG samples are further feature selected with Cuckoo Search (CS) and Harmonic Search Optimization (HSO) algorithms. A publicly available MIT-BIH (Physionet) - VT database, PVC database, ST Change database and NSR database were used in this work. The cardiac vascular disturbances are classified by using seven classifiers such as Gaussian Mixture Model (GMM), Expectation Maximization (EM), Non-linear Regression (NLR), Logistic Regression (LR), Bayesian Linear Discriminant Analysis (BDLC), Detrended Fluctuation Analysis (Detrended FA), and Firefly. For different classes, the average overall accuracy of the classification techniques is 55.65 % when without CS and HSO feature selection, 64.36 % when CS feature selection is used, and 75.39 % when HSO feature selection is used. Also, to improve the performance of classifiers, the hyperparameters of four classifiers (GMM, EM, BDLC and Firefly) are tuned with the Adam and Grid Search Optimization (GSO) approaches. The average accuracy of classification for the CS feature-based classifiers that used GSO and Adam hyperparameter tuning was 79.92 % and 85.78 %, respectively. The average accuracy of classification for the HSO feature-based classifiers that used GSO and Adam hyperparameter tuning was 86.87 % and 93.77 %, respectively. The performance of the classifier is analyzed based on the accuracy parameter for both with and without feature selection methods and with hyperparameter tuning techniques. In the case of ST vs. NSR, a higher accuracy of 98.92 % is achieved for the LLE dimensionality reduction with HSO feature selection for the GMM classifier with Adam's hyperparameter tuning approach. The GMM classifier with the Adam hyperparameter tuning approach with 98.92 % accuracy in detecting ST vs. NSR cardiac disease is outperforming all other classifiers and methodologies.

Cardiovascular mortality in bipolar disorder: Population-based cohort study.

BACKGROUND: Limited evidence base on cause-specific excess cardiovascular disease (CVD) mortality in bipolar disorder (BD) is a barrier to developing preventive interventions aimed at reducing the persistent mortality gap in BD. OBJECTIVE: To investigate cause-specific CVD mortality in BD. METHODS: We identified all individuals aged 15+ years during 2004-2018 with a diagnosis of BD using Finnish nationwide routine data. Standardised mortality ratios (SMR) with 95% confidence intervals (CI) were calculated using the mortality rates in the general population as weights. RESULTS: 53,273 individuals with BD (57% women; median age at BD diagnosis, 40 years), were followed up for 428,426 person-years (median, 8.2 years). There were 5988 deaths due to any cause, of which 26% were due to CVD. The leading cause of absolute excess CVD mortality was coronary artery disease (CAD). The leading causes of relative excess mortality were cardiomegaly (SMR, 4.51; 95% CI, 3.58-5.43), venous thromboembolism (3.03; 2.26-3.81), cardiomyopathy (2.46; 1.95-2.97), and hypertensive heart disease (2.12; 1.71-2.54). The leading causes of absolute CVD mortality showed markedly lower relative excess, including CAD (1.47; 1.34-1.61), ischaemic stroke (1.31; 1.06-1.54), and acute myocardial infarction (1.12; 0.98-1.25). Due to the higher relative excess mortality, structural and functional heart disorders contributed as much as atherosclerotic and ischaemic disorders to the absolute excess mortality. CONCLUSIONS: Cardiomyopathy and hypertensive heart disease as the leading causes of relative excess mortality emphasise the contribution of structural and functional heart disorders to the overall excess mortality alongside coronary artery disease. Interventions targeted at these modifiable causes of death should be priorities in the prevention of premature excess CVD mortality in BD.

Bisphenol A accelerates the vascular complications in patients with Type 2 diabetes mellitus through vascular calcification-a molecular approach.

PURPOSE: Environmental pollutant Bisphenol A (BPA) strongly interacts with insulin resistance, which leads to type 2 diabetes mellitus (T2DM). Uncontrolled glucose levels in both blood and urine develops vascular complications in T2DM patients. However, glucose-controlled diabetic patients are also affected by vascular complications due to vascular calcification, and there is a lack of clinically relevant data on BPA levels available in patients with T2DM-associated vascular complications due to vascular calcification. Therefore, we measured BPA levels in T2DM-associated vascular complications and correlated systemic BPA levels with vascular calcification-related gene expression. METHODS: This study included 120 participants with T2DM and its associated vascular complications. Serum and urinary BPA were estimated using an ELISA kit, and gene expression of the study participants in peripheral blood mononuclear cells (PBMCs) was studied with quantitative real-time PCR. RESULTS: Serum and urinary BPA levels were higher in T2DM and its associated vascular complications with CVD and DN patients compared to control. Both Serum and urinary BPA had higher significance with Sirt1 (p < 0.001, p < 0.001), Runx2 (p < 0.01, p < 0.001) and IL-1beta (p < 0.001, p < 0.02) gene expression in the study groups, but, TNF-alpha significant with Serum BPA (p < 0.04), not urinary BPA (p < 0.31). CONCLUSION: BPA levels were positively correlated with lower Sirt1 and increased Runx2 in T2DM-associated vascular complications patients. Also, higher expression of IL-1beta and TNF-alpha was observed in T2DM-associated vascular complications patients. Our study is the first to associate BPA levels with vascular calcification in patients with T2DM and its associated vascular complications.

Metformin: Expanding the Scope of Application-Starting Earlier than Yesterday, Canceling Later.

Today the area of application of metformin is expanding, and a wealth of data point to its benefits in people without carbohydrate metabolism disorders. Already in the population of people leading an unhealthy lifestyle, before the formation of obesity and prediabetes metformin smooths out the adverse effects of a high-fat diet. Being prescribed at this stage, metformin will probably be able to, if not prevent, then significantly reduce the progression of all subsequent metabolic changes. To a large extent, this review will discuss the proofs of the evidence for this. Another recent important change is a removal of a number of restrictions on its use in patients with heart failure, acute coronary syndrome and chronic kidney disease. We will discuss the reasons for these changes and present a new perspective on the role of increasing lactate in metformin therapy.

[Senescence-associated secretory phenotype and inflammaging: the role in cardiovascular diseases.]

Senescent cells take part into development the age-related diseases by formation the SASP: senescence-associated secretory phenotype. SASP is characterized by synthesis of signal molecules include proinflammatory cytokines. SASP promotes the inflammaging - chronic, low-grade, subclinical inflammatory process, that is the one of cardio-vascular diseases risk factor in older age-groups. In the review we describe the key SASP molecules of cardiomyocytes, endotheliocytes and vascular smooth muscle cells and its role in the pathogenesis of age-associated cardiovascular diseases.

[Schizophrenia and cardiometabolic disorders]. / Shizofreniya i kardiometabolicheskie narusheniya.

The aim of this review is to analyze the basic biological mechanisms of comorbidity of schizophrenia and metabolic, cardiovascular diseases, which are not directly associated with external risk factors. The study of the general pathophysiological mechanisms of schizophrenia and metabolic disorders can provide a significant basis not only for the fundamentally novel therapeutic, preventive and diagnostic measures, but also for a better understanding of the etiopathogenesis of these diseases. It seems likely that schizophrenia represents a heterogeneous group with a varying genetic basis for both mental symptoms and neuroendocrine, inflammatory processes that form concomitant somatic disorders. Thus, the new integrated approaches to the study of this problem with the latest methods of genetic and molecular research are relevant.

High Variability in Implementation of Selective-Prevention Services for Cardiometabolic Diseases in Five European Primary Care Settings.

(1) Background: Cardiometabolic diseases are the most common cause of death worldwide. As part of a collaborative European study, this paper aims to explore the implementation of primary care selective-prevention services in five European countries. We assessed the implementation process of the selective-prevention services, participants' cardiometabolic profile and risk and participants' evaluation of the services, in terms of feasibility and impact in promoting a healthy lifestyle. (2) Methods: Eligible participants were primary care patients, 40-65 years of age, without any diagnosis of cardiometabolic disease. Two hundred patients were invited to participate per country. The extent to which participants adopted and completed the implementation of selective-prevention services was recorded. Patient demographics, lifestyle-related cardiometabolic risk factors and opinions on the implementation's feasibility were also collected. (3) Results: Acceptance rates varied from 19.5% (n = 39/200) in Sweden to 100% (n = 200/200) in the Czech Republic. Risk assessment completion rates ranged from 65.4% (n = 70/107) in Greece to 100% (n = 39/39) in Sweden. On a ten-point scale, the median (25-75% quartile) of participant-reported implementation feasibility ranged from 7.4 (6.9-7.8) in Greece to 9.2 (8.2-9.9) in Sweden. Willingness to change lifestyle exceeded 80% in all countries. (4) Conclusions: A substantial variation in the implementation of selective-prevention receptiveness and patient risk profile was observed among countries. Our findings suggest that the design and implementation of behavior change cardiometabolic programmes in each country should be informed by the local context and provide some background evidence towards this direction, which can be even more relevant during the current pandemic period.

Classification Techniques for Cardio-Vascular Diseases Using Supervised Machine Learning.

INTRODUCTION: The World Health Organization has estimated that 12 million deaths occur worldwide, every year due to Heart diseases. Half the deaths in the developed countries are due to cardiovascular diseases. The early prognosis of cardiovascular diseases can aid in making decisions on lifestyle changes in high risk patients. AIM: The aim of this paper is to build and compare classification techniques for cardiovascular diseases. METHODS: The dataset contained 4270 patients and 14 attributes and it is available on the UCI data repository. The prediction is a binary outcome (event and no event). Variables of each attribute is a potential risk factor. There are both demographic, behavioral and medical risk factors. The classification goal is to predict whether the patient has 10-year risk of future coronary heart disease (CHD). RESULTS: Different classifiers were tested. The SMOTE technique was used in order to solve the class imbalance. The cross-validation method was used in order to estimate how accurately our predictive models will perform. We evaluate our classifiers by using the following metrics: precision, recall, F1-score, Accuracy, AUC (Area Under Curve). CONCLUSIONS: Based on the resluts, the best scores have the Random Forest and Decision Tree classifiers.

Long-term metabolic and cardiovascular effects of antipsychotic drugs. A meta-analysis of randomized controlled trials.

Most of the randomized controlled trials (RCTs) on antipsychotics (APs) have efficacy as their primary endpoint, leading to a lack of evidence on long-term metabolic effects of APs. The aim of the present meta-analysis is to compare different APs for the long-term modification of risk of major adverse cardiovascular events (MACE) and related mortality, in patients with schizophrenia and bipolar disorder. All RCTs found on Medline/Embase of at least 52 weeks up to 19 December 2017, enrolling patients with bipolar disorder or schizophrenia and comparing an AP with another AP or placebo were included. The primary outcome of this analysis was the association of APs with the incidence of cardiovascular death, myocardial infarction (MI), and stroke. 3013 studies were screened, 92 met the selection criteria. MI, stroke and cardiovascular death were reported in 11, 6 and 24 studies, respectively. No significant difference was observed with respect to MI and Stroke; a significantly higher cardiovascular mortality was observed for sertindole when compared to risperidone (Mantel-Haenszel Odds Ratio: 2.56, 95% CI: 1.33 - 5). Long-term cardiovascular effects of APs deserve to be studied more extensively. The request by regulatory authorities of cardiovascular safety data from specifically designed trials would be useful.

[Smoking in People Living with HIV (PLHA) and followed up in the Outpatient Department of the Hospital Fann of Dakar]. / Le tabagisme chez les patients vivant avec le VIH (PvVIH) suivis au Centre de Traitement Ambulatoire de l'Hôpital Fann de Dakar.

INTRODUCTION: PLHA who smoke have twice the never-smoker mortality rate and have an increased risk of developing non-AIDS diseases. The prevalence of tobacco smoking is higher among PLHA than in the general population. The purpose of this study was to assess the prevalence of smoking among PLHA, to describe the clinical and spirometric features of smokers and ex-smokers and to assess their knowledge and attitudes toward smoking. METHODS: We conducted a cross-sectional, descriptive and analytical study among PLHA followed up in the Outpatient Department of the National University Hospital Center of Fann from 15 July to 15 December 2015. RESULTS: Three hundred (300) PLHA were included in the study. Sex ratio was 0.8. Out of the study population, 15% were smokers and 23.7% were ex-smokers. The average age of patients was 44.38±9.55 years. The quasi-totality of the smokers (91.1%) had already started smoking before the detection of the serological status and 35.6% of them had increased tobacco use after. Respiratory symptoms among smokers were dominated by respiratory distress (64.4%). Smokers who underwent spirometry had obstructive ventilatory impairment not improved by beta-2-mimetic agents (67%) and restrictive disease (28.1%). Out of ex-smokers, 40.8% reported that their serological status was the reason for smoking cessation. CONCLUSION: People may begin or increase smoking after knowledge of serological status. In PLHA, smoking causes cardiovascular and respiratory diseases as well as complications.

Meta-analysis of natural, unnatural and cause-specific mortality rates following discharge from in-patient psychiatric facilities.

BACKGROUND: People discharged from in-patient psychiatric facilities have highly elevated rates of suicide, and there is increasing concern about natural mortality among the seriously mentally ill. METHOD: A meta-analysis of English-language, peer-reviewed longitudinal studies of mortality among patients discharged from in-patient psychiatric facilities was conducted using papers published in MEDLINE, PsycINFO or EMBASE (from 1 January 1960 to 1 April 2018) located using the terms ((suicid*).ti AND (hospital OR discharg* OR inpatient OR in-patient OR admit*)).ab and ((mortality OR outcome* OR death*) AND (psych* OR mental*)).ti AND (admit* OR admis* OR hospital* OR inpatient* OR in-patient* OR discharg*).ab. Pooled mortality rates for aggregated natural and unnatural causes, and the specific causes of suicide, accident, homicide, vascular, neoplastic, respiratory, gastrointestinal, infectious and metabolic death were calculated using a random-effects meta-analytic model. Between-study heterogeneity was investigated using subgroup analysis and metaregression. RESULTS: The pooled natural death rate of 1128 per 100 000 person-years exceeded the pooled unnatural deaths of 479 per 100 000 person-year among studies with varying periods of follow-up. Natural deaths significantly exceeded unnatural deaths among studies with a mean follow-up of longer than 2 years, and vascular deaths exceeded suicide deaths among studies with mean period of follow-up of 5 years or longer. CONCLUSION: Suicide may be the largest single cause of death in the short term after discharge from in-patient psychiatric facilities but vascular disease is the major cause of mortality in the medium- and long-term.

[Is There an Effect of Dietary Fructose on Development and Prognosis of Chronic Diseases?] / Diyetle Alinan Fruktozun Kronik Hastaliklarin Gelismesinde ve Prognozunda Etkisi Var midir?

Dietary sources of fructose are not only honey, fruit, sucrose, but also high fructose corn syrup in various foods and beverages. Total amount of daily fructose intake is rising by especially increasing use of high fructose corn syrup in the food industry. Fructose can lead to obesity by contributing to high-energy intake and lipogenesis in the body. Depending on the source of fructose, dose and duration, it was involved in de-novo lipid synthesis. Fructose may increase the risk of insulin resistance, non-alcoholic fatty liver and kidney diseases by affecting blood glucose and insulin levels. On the other hand, fructose may initiate inflammatory processes in the organism. In addition to these, fat or salt consisting typical western type diet with high fructose consumption, can increase the potential effect of fructose on chronic diseases. As a result, although it is not fully supported by clinical studies, it is thought that high amounts of fructose intake may increase the risk of chronic disease shown by experimental studies. Also it should be noted that beside high fructose, typical western-style high-fat and high-salt diet may increase the risk of chronic diseases such as obesity, cardiovascular diseases and worsen metabolic syndrome parameters. Furthermore, synthetic fructose, is able to cause some adverse metabolic effects when taken in large amounts; consumption of high amounts of fructose by fruit or honey these negative effects can be either not seen or less observed based on the amount.

Masked uncontrolled hypertension: Prevalence and predictors.

BACKGROUND: There are limited data on 'masked uncontrolled hypertension' (MUCH) in patients with treated and apparently well-controlled BP is unknown. OBJECTIVES: To define the prevalence and predictors of MUCH among hypertensive patients with controlled office blood pressure. METHODS: One hundred ninety-nine hypertensive patients presented to the specialized hypertension clinics at two University Hospitals. All patients had controlled office blood pressure (less than 140/90 mmHg). Patients were assessed regarding history, clinical examination, and laboratory data. All patients underwent ambulatory blood pressure monitoring (ABPM) for 24 h, within a week after the index office visit. MUCH was diagnosed if average 24-h ABPM was elevated (systolic BP ≥ 130 mmHg and/or diastolic BP ≥ 80 mmHg) despite controlled clinic BP. RESULTS: Sixty-six patients (33.2%) had MUCH according to 24-h ABPM criteria (mean age 53.5 ±â€¯9.3 years, 60.6% men). MUCH was mostly caused by the poor control of nocturnal BP; with the percentage of patients in whom MUCH was solely attributable to an elevated nocturnal BP almost double that due to daytime BP elevation (57.3% vs. 27.1%, P < 0.001). The most common predictors of MUCH were smoking, DM and positive family history of DM. CONCLUSION: The prevalence of masked suboptimal BP control is high. Office BP monitoring alone is thus inadequate to ascertain optimal BP control because many patients have an elevated nocturnal BP. ABPM is needed to confirm proper BP control, especially in patients with high cardiovascular risk profile. Smoking, DM and positive family history of DM were the most common predictors of MUCH.

[Metabolomic Profiling of Patients With Cardiovascular Diseases].

Cardiovascular diseases (CVD) are the main cause of death worldwide. A broad study of the pathogenetic mechanisms of the CVD onset and progression has led to understanding of the importance of endothelial dysfunction (ED) in these processes. During recent years intensive work has been conducted in the direction of searching for markers of ED. Metabolomics is an intensively advancing approach to early diagnostics of diseases. Metabolomic analysis based on mass spectrometry allows to study complete metabolic profiles and their deviations resulting from changes in expression of genes and RNA, protein activity, or environmental factors. Metabolomic analysis has already demonstrated significant results in the solving of different scientific and clinical problems. It appears to be a promising method for detecting early biomarkers of CVD. Various aspects of application of metabolomic profiling in the field of cardiovascular diseases are discussed in this article.

Interaction between a variant of chromosome 9p21.3 locus and diet antioxidant capacity on metabolic syndrome in Tehrani adults.

BACKGROUND: Genome-wide association studies have shown that risk alleles on chromosome 9p21.3 locus, are associated with increasing the risk of cardiovascular diseases (CVDs). Several epidemiological studies have found that metabolic syndrome (MetS) is associated with CVDs. Dietary antioxidants also have shown to have potential favorable effects on MetS prevention. This study examined the interactions between rs1333048 genotypes on 9p21 genetic region and Total antioxidant capacity (TAC) on odds of MetS. METHODS: 263 Tehrani adults were enrolled in this cross-sectional study. The MetS was defined according to the ATPIII. Dietary intake was assessed daily using a FFQ with 147 items. Dietary TAC was assessed according to United States Department of Agriculture database for oxygen radical absorbance capacity (ORAC). Bioelectrical impedance analysis method was used for body analysis and rs1333048 were genotyped by restriction fragment length polymorphism method. Participants were categorized into three groups based on rs1333048 genotypes. RESULTS: The results demonstrate that, prevalence of C allele was 52.85% and A allele was 47.15%. After adjustment for confunder variable, this study demonstrated an interaction between AA genotype and high Lyophilic oxygen radical absorbance capacity (L-ORAC) and high Hydrophilic oxygen radical absorbance capacity (H-ORAC) intake on low odds of MetS (OR = 0.24, 95% CI = 0.06-0.94, P for interaction = 0.04, OR = 0.26, 95% CI = 0.06-0.99, P for interaction = 0.04). Also, our result indicated, there was no interaction between AA genotype and high total oxygen radical absorbance capacity (T-ORAC) and total phenolic intakes on reduce odds of MetS (OR = 0.07, 95% CI = 0.07-1.10, P for interaction = 0.07, OR = 0.58, 95% CI = 0.16-2.07, P for interaction = 0.40) respectively. CONCLUSION: The results of the present study indicate that high L-ORAC and high H-ORAC intake may modify the elevated odds of MetS in AA genotype of rs1333048 on the 9p21 genetic locus.

Comorbidities and Treatment Strategies in Bullous Pemphigoid: An Appraisal of the Existing Litterature.

Bullous Pemphigoid is an autoimmune skin blistering disease. It is caused by deposition of auto antibodies along the dermal-epidermal border leading to inflammation. The antibodies are directed against anchoring filaments in the epidermis, but these antigens are also present in the neurological tissues and this has led to speculation of an association between multiple sclerosis and bullous pemphigoid. Additionally recent epidemiological studies have pointed at an increased risk of cardio-vascualr diseases and an increased moratality among the patients with bullous pemphigoid. In this mini review we present the recent findings in this area and as well as the treatment strategies when comorbidities are taken into consideration.