AttGRU-HMSI: enhancing heart disease diagnosis using hybrid deep learning approach.

Heart disease is a major global cause of mortality and a major public health problem for a large number of individuals. A major issue raised by regular clinical data analysis is the recognition of cardiovascular illnesses, including heart attacks and coronary artery disease, even though early identification of heart disease can save many lives. Accurate forecasting and decision assistance may be achieved in an effective manner with machine learning (ML). Big Data, or the vast amounts of data generated by the health sector, may assist models used to make diagnostic choices by revealing hidden information or intricate patterns. This paper uses a hybrid deep learning algorithm to describe a large data analysis and visualization approach for heart disease detection. The proposed approach is intended for use with big data systems, such as Apache Hadoop. An extensive medical data collection is first subjected to an improved k-means clustering (IKC) method to remove outliers, and the remaining class distribution is then balanced using the synthetic minority over-sampling technique (SMOTE). The next step is to forecast the disease using a bio-inspired hybrid mutation-based swarm intelligence (HMSI) with an attention-based gated recurrent unit network (AttGRU) model after recursive feature elimination (RFE) has determined which features are most important. In our implementation, we compare four machine learning algorithms: SAE + ANN (sparse autoencoder + artificial neural network), LR (logistic regression), KNN (K-nearest neighbour), and naïve Bayes. The experiment results indicate that a 95.42% accuracy rate for the hybrid model's suggested heart disease prediction is attained, which effectively outperforms and overcomes the prescribed research gap in mentioned related work.

Comprehensive evaluation and performance analysis of machine learning in heart disease prediction.

Heart disease is a leading cause of mortality on a global scale. Accurately predicting cardiovascular disease poses a significant challenge within clinical data analysis. The present study introduces a prediction model that utilizes various combinations of information and employs multiple established classification approaches. The proposed technique combines the genetic algorithm (GA) and the recursive feature elimination method (RFEM) to select relevant features, thus enhancing the model's robustness. Techniques like the under sampling clustering oversampling method (USCOM) address the issue of data imbalance, thereby improving the model's predictive capabilities. The classification challenge employs a multilayer deep convolutional neural network (MLDCNN), trained using the adaptive elephant herd optimization method (AEHOM). The proposed machine learning-based heart disease prediction method (ML-HDPM) demonstrates outstanding performance across various crucial evaluation parameters, as indicated by its comprehensive assessment. During the training process, the ML-HDPM model exhibits a high level of performance, achieving an accuracy rate of 95.5% and a precision rate of 94.8%. The system's sensitivity (recall) performs with a high accuracy rate of 96.2%, while the F-score highlights its well-balanced performance, measuring 91.5%. It is worth noting that the specificity of ML-HDPM is recorded at a remarkable 89.7%. The findings underscore the potential of ML-HDPM to transform the prediction of heart disease and aid healthcare practitioners in providing precise diagnoses, exerting a substantial influence on patient care outcomes.

Exertional breathlessness related to medical conditions in middle-aged people: the population-based SCAPIS study of more than 25,000 men and women.

BACKGROUND: Breathlessness is common in the population and can be related to a range of medical conditions. We aimed to evaluate the burden of breathlessness related to different medical conditions in a middle-aged population. METHODS: Cross-sectional analysis of the population-based Swedish CArdioPulmonary bioImage Study of adults aged 50-64 years. Breathlessness (modified Medical Research Council [mMRC] ≥ 2) was evaluated in relation to self-reported symptoms, stress, depression; physician-diagnosed conditions; measured body mass index (BMI), spirometry, venous haemoglobin concentration, coronary artery calcification and stenosis [computer tomography (CT) angiography], and pulmonary emphysema (high-resolution CT). For each condition, the prevalence and breathlessness population attributable fraction (PAF) were calculated, overall and by sex, smoking history, and presence/absence of self-reported cardiorespiratory disease. RESULTS: We included 25,948 people aged 57.5 ± [SD] 4.4; 51% women; 37% former and 12% current smokers; 43% overweight (BMI 25.0-29.9), 21% obese (BMI ≥ 30); 25% with respiratory disease, 14% depression, 9% cardiac disease, and 3% anemia. Breathlessness was present in 3.7%. Medical conditions most strongly related to the breathlessness prevalence were (PAF 95%CI): overweight and obesity (59.6-66.0%), stress (31.6-76.8%), respiratory disease (20.1-37.1%), depression (17.1-26.6%), cardiac disease (6.3-12.7%), anemia (0.8-3.3%), and peripheral arterial disease (0.3-0.8%). Stress was the main factor in women and current smokers. CONCLUSION: Breathlessness mainly relates to overweight/obesity and stress and to a lesser extent to comorbidities like respiratory, depressive, and cardiac disorders among middle-aged people in a high-income setting-supporting the importance of lifestyle interventions to reduce the burden of breathlessness in the population.

Clinical Guideline for Preimplantation Genetic Testing in Inherited Cardiac Diseases.

BACKGROUND: Preimplantation genetic testing (PGT) is a reproductive technology that selects embryos without (familial) genetic variants. PGT has been applied in inherited cardiac disease and is included in the latest American Heart Association/American College of Cardiology guidelines. However, guidelines selecting eligible couples who will have the strongest risk reduction most from PGT are lacking. We developed an objective decision model to select eligibility for PGT and compared its results with those from a multidisciplinary team. METHODS: All couples with an inherited cardiac disease referred to the national PGT center were included. A multidisciplinary team approved or rejected the indication based on clinical and genetic information. We developed a decision model based on published risk prediction models and literature, to evaluate the severity of the cardiac phenotype and the penetrance of the familial variant in referred patients. The outcomes of the model and the multidisciplinary team were compared in a blinded fashion. RESULTS: Eighty-three couples were referred for PGT (1997-2022), comprising 19 different genes for 8 different inherited cardiac diseases (cardiomyopathies and arrhythmias). Using our model and proposed cutoff values, a definitive decision was reached for 76 (92%) couples, aligning with 95% of the multidisciplinary team decisions. In a prospective cohort of 11 couples, we showed the clinical applicability of the model to select couples most eligible for PGT. CONCLUSIONS: The number of PGT requests for inherited cardiac diseases increases rapidly, without the availability of specific guidelines. We propose a 2-step decision model that helps select couples with the highest risk reduction for cardiac disease in their offspring after PGT.

Artificial intelligence framework for heart disease classification from audio signals.

As cardiovascular disorders are prevalent, there is a growing demand for reliable and precise diagnostic methods within this domain. Audio signal-based heart disease detection is a promising area of research that leverages sound signals generated by the heart to identify and diagnose cardiovascular disorders. Machine learning (ML) and deep learning (DL) techniques are pivotal in classifying and identifying heart disease from audio signals. This study investigates ML and DL techniques to detect heart disease by analyzing noisy sound signals. This study employed two subsets of datasets from the PASCAL CHALLENGE having real heart audios. The research process and visually depict signals using spectrograms and Mel-Frequency Cepstral Coefficients (MFCCs). We employ data augmentation to improve the model's performance by introducing synthetic noise to the heart sound signals. In addition, a feature ensembler is developed to integrate various audio feature extraction techniques. Several machine learning and deep learning classifiers are utilized for heart disease detection. Among the numerous models studied and previous study findings, the multilayer perceptron model performed best, with an accuracy rate of 95.65%. This study demonstrates the potential of this methodology in accurately detecting heart disease from sound signals. These findings present promising opportunities for enhancing medical diagnosis and patient care.

Enhancing heart disease prediction using a self-attention-based transformer model.

Cardiovascular diseases (CVDs) continue to be the leading cause of more than 17 million mortalities worldwide. The early detection of heart failure with high accuracy is crucial for clinical trials and therapy. Patients will be categorized into various types of heart disease based on characteristics like blood pressure, cholesterol levels, heart rate, and other characteristics. With the use of an automatic system, we can provide early diagnoses for those who are prone to heart failure by analyzing their characteristics. In this work, we deploy a novel self-attention-based transformer model, that combines self-attention mechanisms and transformer networks to predict CVD risk. The self-attention layers capture contextual information and generate representations that effectively model complex patterns in the data. Self-attention mechanisms provide interpretability by giving each component of the input sequence a certain amount of attention weight. This includes adjusting the input and output layers, incorporating more layers, and modifying the attention processes to collect relevant information. This also makes it possible for physicians to comprehend which features of the data contributed to the model's predictions. The proposed model is tested on the Cleveland dataset, a benchmark dataset of the University of California Irvine (UCI) machine learning (ML) repository. Comparing the proposed model to several baseline approaches, we achieved the highest accuracy of 96.51%. Furthermore, the outcomes of our experiments demonstrate that the prediction rate of our model is higher than that of other cutting-edge approaches used for heart disease prediction.

Cardiac involvement and its clinical significance in patients with anorexia nervosa.

Cardiac complications are a major concern in patients with anorexia nervosa (AN) which contribute to morbidity and mortality. However, limited information exists regarding risk factors for the development of these complications. Our objective was to investigate the prevalence and associated risk factors of cardiac involvement among children and adolescents with AN admitted to a tertiary pediatric hospital. We collected demographic, clinical, and laboratory data from individuals with AN hospitalized between 2011 and 2020 in Schneider Children's Medical Center in Israel. Diagnosis was based on established criteria (DSM-5). Patients with other co-morbidities were excluded. Cardiac investigations included electrocardiograms (ECG) and echocardiograms. We conducted correlation tests between cardiac findings and clinical and laboratory indicators. A total of 403 AN patients (81.4% were females) with a median age of 15 ± 2 years were included in the study. Sinus bradycardia was the most common abnormality, observed in 155 (38%) participants. Echocardiogram was performed in 170 (42.2%) patients, of whom 37 (22%) demonstrated mild cardiac aberrations. Among those aberrations, 94.6% could be attributed to the current metabolic state, including pericardial effusion (15.3%) and valve dysfunction (8.8%). Systolic or diastolic cardiac dysfunction, tachyarrhythmias, or conduction disorders were not observed. Patients with new echocardiographic aberration had significantly lower body mass index (BMI) at admission, and the prevalence of amenorrhea and hypotension was higher in this group. CONCLUSIONS: The prevalence of cardiac involvement, except for sinus bradycardia, was notably low in our cohort. The presence of cardiac aberrations is correlated with several clinical variables: lower body mass index (BMI) and the presence of amenorrhea and hypotension at admission. Patients presenting with these variables may be at high risk for cardiac findings per echocardiography. Dividing the patients into high and low risk groups may enable targeted evaluation, while avoiding unnecessary cardiac investigations in low-risk patients. WHAT IS KNOWN: • Cardiac involvement in anorexia nervosa (AN) patients is a major concern, which contributes to morbidity and mortality. • It is unknown which patients are prone to develop this complication. WHAT IS NEW: • Cardiac complications in our cohort are less frequent compared to previous studies, and it is correlated with lower body mass index (BMI) at admission, and the prevalence of amenorrhea and hypotension.

Role of cardiac computed tomography in hyperacute stroke assessment.

BACKGROUND: Incorporating cardiac CT with hyperacute stroke imaging may increase the yield for cardioembolic sources. It is not clarified whether stroke severity influences on rates of intracardiac thrombus. We aimed to investigate a National Institutes of Health Stroke Scale (NIHSS) threshold below which acute cardiac CT was unnecessary. METHODS: Consecutive patients with suspected stroke who underwent multimodal brain imaging and concurrent non-gated cardiac CT with delayed timing were prospectively recruited from 1st December 2020 to 30th November 2021. We performed receiver operating characteristics analysis of the NIHSS and intracardiac thrombus on hyperacute cardiac CT. RESULTS: A total of 314 patients were assessed (median age 69 years, 61% male). Final diagnoses were ischemic stroke (n=205; 132 etiology-confirmed stroke, independent of cardiac CT and 73 cryptogenic), transient ischemic attack (TIA) (n=21) and stroke-mimic syndromes (n=88). The total yield of cardiac CT was 8 intracardiac thrombus and 1 dissection. Cardiac CT identified an intracardiac thrombus in 6 (4.5%) with etiology-confirmed stroke, 2 (2.7%) with cryptogenic stroke, and none in patients with TIA or stroke-mimic. All of those with intracardiac thrombus had NIHSS ≥4 and this was the threshold below which hyperacute cardiac CT was not justified (sensitivity 100%, specificity 38%, positive predictive value 4.0%, negative predictive value 100%). CONCLUSIONS: A cutoff NIHSS ≥4 may be useful to stratify patients for cardiac CT in the hyperacute stroke setting to optimize its diagnostic yield and reduce additional radiation exposure.

[Screening for heart disease in kids and adolescents (Prevencar Program)]. / Screening de cardiopatías en niños y adolescentes (Prevencar Program).

OBJECTIVE: The objective was to develop a screening for heart disease detection in primary care, to identify pathological electrocardiographic changes and underlying heart disease in adolescents. DESIGN: The study was carried out for one year using multistage sampling. SITE: Primary care centers in a health area that had digital ECG equipment (12 centers) were selected. PARTICIPANTS: Initially, 718 (16.6%) 14-year-old adolescents were recruited and those with a previous diagnosis of heart disease were excluded. INTERVENTIONS: Screening consisted of including a health questionnaire in the mandatory 14-year-old check-up. MAIN MEASUREMENTS: Screening included a questionnaire, cardiac auscultation, ECG and echocardiography. Abnormality criteria were established to refer for a second evaluation by a cardiologist. RESULTS: Finally, the sample was made up of 698 adolescents, with a mean age of 13.7±0.5 years, and 354 (50.7%) were boys. A total of 149 (21.3%) were selected for a second review by cardiology: 88 (12.6%) due to a positive questionnaire, 11 (2.2%) due to abnormal cardiac auscultation, and 66 (9.5%) due to ECG findings. Adolescents with evidence of heart disease were 24 (3.4%). Of these, 14 (2.0%) had suggestive alterations and follow-up was recommended, 6 (0.9%) had a definitive diagnosis of heart disease, and 4 (0.6%) had other pathological findings related to the cardiovascular system. CONCLUSIONS: The screening allowed us to identify 1% of adolescents with heart disease and another 2% will remain in follow-up. The ECG detected more pathological cases than the questionnaire.

Worldwide trends in mortality for hypertensive heart disease from 1990 to 2019 with projection to 2034: data from the Global Burden of Disease 2019 study.

AIMS: This study aims to analyse the worldwide trends in hypertensive heart disease (HHD) mortality and associations with age, period, and birth cohort and predict the future burden of HHD deaths. METHODS AND RESULTS: Mortality estimates were obtained from Global Burden of Disease 2019 study. We used age-period-cohort (APC) model to examine the age, period, and cohort effects on HHD mortality between 1990 and 2019. Bayesian APC model was utilized to predict HHD deaths to 2034. The global HHD deaths were 1.16 million in 2019 and were projected to increase to 1.57 million in 2034, with the largest increment in low- and middle-income countries (LMICs). Between 1990 and 2019, middle/high-middle socio-demographic index (SDI) countries had the largest mortality reductions (annual percentage change = -2.06%), whereas low SDI countries saw a lagging performance (annual percentage change = -1.09%). There was a prominent transition in the age distribution of deaths towards old-age population in middle/high-middle SDI countries, while the proportion of premature deaths (aged under 60 years) remained at 24% in low SDI countries in 2019. Amongst LMICs, Brazil, China, and Ethiopia showed typically improving trends both over time and in recent birth cohorts, whereas 63 countries including Indonesia, the Philippines, and Pakistan had unfavourable or worsening risks for recent periods and birth cohorts. CONCLUSION: The HHD death burden in 2019 is vast and is expected to increase rapidly in the next decade, particularly for LMICs. Limited progress in HHD management together with high premature mortality would exact huge human and medical costs in low SDI countries. The examples from Brazil, China, and Ethiopia suggest that efficient health systems with action on improving hypertension care can reduce HHD mortality effectively in LMICs.

This study provides the first comprehensive analysis of the age, period, and cohort trends in mortality for hypertensive heart disease (HHD) across 204 countries and territories from 1990 to 2019, with projection to 2034. The death burden of HHD is substantial and growing rapidly in most of the world, particularly in low- and middle-income countries (LMICs). Wide disparities exist within LMICs in HHD management, with most low socio-demographic index countries showing little progress in reducing HHD mortality. The examples from Brazil, China, and Ethiopia suggest that prevention policies for HHD can reduce risks for younger birth cohorts and shift the risks for all age groups over time.

Assessment of anthracycline-induced cardiotoxicity in childhood cancer survivors during long-term follow-up using strain analysis and intraventricular pressure gradient measurements.

BACKGROUND: Cardiac dysfunction due to cardiotoxicity from anthracycline chemotherapy is a leading cause of morbidity and mortality in childhood cancer survivors (CCS), and the cumulative incidence of cardiac events has continued to increase. This study identifies an adequate indicator of cardiac dysfunction during long-term follow-up. PROCEDURE: In total, 116 patients (median age: 15.5 [range: 4.7-40.2] years) with childhood cancer who were treated with anthracycline were divided into three age groups for analysis (C1: 4-12 years of age, C2: 13-18 years of age, C3: 19-40 years of age), and 116 control patients of similar ages were divided into three corresponding groups (N1, N2, and N3). Layer-specific strains were assessed for longitudinal strain (LS) and circumferential strain (CS). The total and segmental intraventricular pressure gradients (IVPG) were also calculated based on Doppler imaging of the mitral inflow using Euler's equation. RESULTS: Conventional echocardiographic parameters were not significantly different between the patients and controls. All layers of the LS and inner and middle layers of the basal and papillary CS in all ages and all IVPGs in C2 and C3 decreased compared to those of corresponding age groups. Interestingly, basal CS and basal IVPG in CCS showed moderate correlation and both tended to rapidly decrease with aging. Furthermore, basal IVPG and anthracycline dose showed significant correlations. CONCLUSIONS: Basal CS and total and basal IVPGs may be particularly useful indicators of cardiotoxicity in long-term follow-up.

Artificial intelligence in detecting left atrial appendage thrombus by transthoracic echocardiography and clinical features: the Left Atrial Thrombus on Transoesophageal Echocardiography (LATTEE) registry.

AIMS: Transoesophageal echocardiography (TOE) is often performed before catheter ablation or cardioversion to rule out the presence of left atrial appendage thrombus (LAT) in patients on chronic oral anticoagulation (OAC), despite associated discomfort. A machine learning model [LAT-artificial intelligence (AI)] was developed to predict the presence of LAT based on clinical and transthoracic echocardiography (TTE) features. METHODS AND RESULTS: Data from a 13-site prospective registry of patients who underwent TOE before cardioversion or catheter ablation were used. LAT-AI was trained to predict LAT using data from 12 sites (n = 2827) and tested externally in patients on chronic OAC from two sites (n = 1284). Areas under the receiver operating characteristic curve (AUC) of LAT-AI were compared with that of left ventricular ejection fraction (LVEF) and CHA2DS2-VASc score. A decision threshold allowing for a 99% negative predictive value was defined in the development cohort. A protocol where TOE in patients on chronic OAC is performed depending on the LAT-AI score was validated in the external cohort. In the external testing cohort, LAT was found in 5.5% of patients. LAT-AI achieved an AUC of 0.85 [95% confidence interval (CI): 0.82-0.89], outperforming LVEF (0.81, 95% CI 0.76-0.86, P < .0001) and CHA2DS2-VASc score (0.69, 95% CI: 0.63-0.7, P < .0001) in the entire external cohort. Based on the proposed protocol, 40% of patients on chronic OAC from the external cohort would safely avoid TOE. CONCLUSION: LAT-AI allows accurate prediction of LAT. A LAT-AI-based protocol could be used to guide the decision to perform TOE despite chronic OAC.

[Beating heart surgical treatment of atrio-esophageal fistula after radiofrequency ablation of atrial fibrillation]. / Trattamento chirurgico a cuore battente di una fistola atrio-esofagea post-ablazione tramite radiofrequenza di fibrillazione atriale.

Atrio-esophageal fistula (AEF) is a rare (0.02-0.1%) complication of radiofrequency ablation for atrial fibrillation and is associated with high mortality. It typically presents between 2 and 6 weeks after catheter ablation. AEF was reported to be the second complication as cause of death after radiofrequency ablation with a mortality rate of 71%. Common clinical features of AEF include dysphagia, nausea, heartburn, hematemesis or melena, high fever, sepsis, pericardial or pleural effusions, mediastinitis, seizures, and stroke. Once the diagnosis of AEF is made, early surgical repair is mandatory. Herein, we report a case of a AEF treated surgically without extracorporeal circulation.

Interplay of inflammatory biomarkers in heart disease patients with depressive symptoms: An update.

The pathophysiological mechanisms that connect heart disease and depressive disorders have been identified as abnormal endothelial function, dysregulation of the Hypothalamic Pituitary Adrenal (HPA) axis and abnormal platelet activities. Among these mechanisms, both endothelial dysfunction and HPA axis dysregulation are influenced by low grade inflammation and play significant roles in both conditions. Consequently, it is hypothesized that inflammation is an integral part of the formation of atherosclerotic plaques, linking the occurrence of heart diseases to the activation and shedding of intercellular adhesion molecules (ICAMs), especially soluble ICAM-1. This process is accompanied by the local and systemic secretion of various inflammatory markers like interleukin-6, Tumour Necrosis Factor, and C-reactive protein. Therefore, this review primarily focuses on defining the potential role of different inflammatory biomarkers in depression and heart disease and assessing whether mediators could serve as predictive biomarkers for detecting depressive symptoms in patients with heart disease.