Early Diagnosis Of Heart Disease Research Articles

CLASSIFICATION OF PHONOCARDIOGRAM SIGNALS BASED ON ENVELOPE OPTIMIZATION MODEL AND SUPPORT VECTOR MACHINE

The prevention and diagnosis of cardiovascular diseases have become one of the primary problems in the medical community since the mortality of this kind of diseases accounts for 31% of global deaths in 2016. Heart sound, which is an important physiological signal of human body, mainly comes from the pulsing of cardiac structures and blood turbulence. The analysis of heart sounds plays an irreplaceable role in early diagnosis of heart disease since they contain a large amount of pathological information about each part of human heart. Heart sounds can be detected and recorded by Phonocardiogram (PCG). As a noninvasive method to detect and diagnose heart disease, PCG signals have been paid more and more attention by researchers. In this paper, a novel envelope extraction model is proposed and used to estimate the cardiac cycle of each PCG signal. We present a strategy combining empirical mode decomposition (EMD) technique and the proposed envelope model to extract the time-domain features. After applying EMD process to each PCG signal, the second intrinsic mode function is chosen for further analysis. Based on the proposed envelope model, the cardiac cycles of PCG signals can be estimated and then the time-domain features can be extracted. Combining with the frequency-domain features and wavelet-domain features, the feature vectors are obtained. Finally, the support vector machine (SVM) classifier is used to detect the normal and abnormal PCG signals. Two public datasets are used to test our framework in this paper. And classification accuracies of more than [Formula: see text] on both datasets show the effectiveness of the proposed model.

Towards Domain Invariant Heart Sound Abnormality Detection Using Learnable Filterbanks.

Cardiac auscultation is the most practiced non-invasive and cost-effective procedure for the early diagnosis of heart diseases. While machine learning based systems can aid in automatically screening patients, the robustness of these systems is affected by numerous factors including the stethoscope/sensor, environment, and data collection protocol. This article studies the adverse effect of domain variability on heart sound abnormality detection and develops strategies to address this problem. We propose a novel Convolutional Neural Network (CNN) layer, consisting of time-convolutional (tConv) units, that emulate Finite Impulse Response (FIR) filters. The filter coefficients can be updated via backpropagation and be stacked in the front-end of the network as a learnable filterbank. On publicly available multi-domain datasets, the proposed method surpasses the top-scoring systems found in the literature for heart sound abnormality detection (a binary classification task). We utilized sensitivity, specificity, F-1 score and Macc (average of sensitivity and specificity) as performance metrics. Our systems achieved relative improvements of up to 11.84% in terms of MAcc, compared to state-of-the-art methods. The results demonstrate the effectiveness of the proposed learnable filterbank CNN architecture in achieving robustness towards sensor/domain variability in PCG signals. The proposed methods pave the way for deploying automated cardiac screening systems in diversified and underserved communities.

A neutrosophic clinical decision-making system for cardiovascular diseases risk analysis

Cardiovascular diseases are the leading cause of death worldwide. Early diagnosis of heart disease can reduce this large number of deaths so that treatment can be carried out. Many decision-making systems have been developed, but they are too complex for medical professionals. To target these objectives, we develop an explainable neutrosophic clinical decision-making system for the timely diagnose of cardiovascular disease risk. We make our system transparent and easy to understand with the help of explainable artificial intelligence techniques so that medical professionals can easily adopt this system. Our system is taking thirty-five symptoms as input parameters, which are, gender, age, genetic disposition, smoking, blood pressure, cholesterol, diabetes, body mass index, depression, unhealthy diet, metabolic disorder, physical inactivity, pre-eclampsia, rheumatoid arthritis, coffee consumption, pregnancy, rubella, drugs, tobacco, alcohol, heart defect, previous surgery/injury, thyroid, sleep apnea, atrial fibrillation, heart history, infection, homocysteine level, pericardial cysts, marfan syndrome, syphilis, inflammation, clots, cancer, and electrolyte imbalance and finds out the risk of coronary artery disease, cardiomyopathy, congenital heart disease, heart attack, heart arrhythmia, peripheral artery disease, aortic disease, pericardial disease, deep vein thrombosis, heart valve disease, and heart failure. There are five main modules of the system, which are neutrosophication, knowledge base, inference engine, de-neutrosophication, and explainability. To demonstrate the complete working of our system, we design an algorithm and calculates its time complexity. We also present a new de-neutrosophication formula, and give comparison of our the results with existing methods.

Using Neural Networks for Heart Sounds Classification: A Review

The high number of sudden deaths from heart diseases today makes early diagnosis of heart diseases very important in order to prevent these deaths. The first method that doctors use to diagnose heart disease is to listen to heart sounds caused by mechanical movements of the heart. This procedure is commonly referred to as auscultation of the heart. Over time, the irregularity of S1 and S2 sounds, which are components of heart sounds, may show some disturbances in heart function. For example, inadequate heart valves or murmurs. Early diagnosis of heart diseases is of great importance. However, not all doctors have the ability to interpret every heart sound and make an early diagnosis. Of course, the fact that their jobs are very busy and too many patients affect this. The status of each patient may be different during diagnosis and treatment. Assistive systems have been developed to enable doctors to diagnose patients with very different symptoms. These systems generally take diagnostics and evaluate all the data and suggest a diagnosis for the patient. In other words, these systems are decision-making mechanisms that classify all data. In the classification studies, researchers used different classification techniques in order to increase the classification success. Because the success of the classification means an increase in the diagnostic ability. For this purpose, many different techniques and mixed methods are used. In this study, a general evaluation of my classification studies of heart sounds with different neural networks such as Artificial Neural Networks (ANN), Convolutional Neural Network (CNN) and Autoencoder Neural Networks (AEN) was performed. PASCAL B-Training and Physiobank-PhysioNet A-Training data sets were used for the classification of heart sounds. The efficiency of the methods were compared by considering the common evaluation criteria in the studies examined. Keywords: Heart sounds classification, Re-sampled signal energy, Autoencoder neural networks, Artificial Neural Network, Convolutional Neural Network. DOI: 10.7176/JSTR/5-12-15

Towards Designing A Hierarchical Fuzzy System for Early Diagnosis of Heart Disease

Heart disease may represent a range of conditions that affect our heart. Disease under heart diseases umbrella include coronary heart disease, heart attack, congestive heart failure, and congenital heart disease, is the leading cause of death. Mor eover, heart disease not only attacks the elderly. In the present day, lots of younger people might be getting affected by the number of heart diseases. In order to decrease the mortality rate caused by heart disease, it is necessary for the disease, to be diagnosed at an early stage. In this paper, we have proposed the use of hierarchical fuzzy systems (HFSs) for early diagnosis of heart disease. However, to design the HFSs is challenging, especially for the complex system. Therefore, in this paper, we foc us on designing a hierarchical fuzzy system to handle the complex medical application. The designed HFS consists of six key main steps implemented on heart disease. The input variables of heart disease includes shortness of breath, discomfort, pressure, he aviness, or pain in the chest, arm, or below the breastbone, fatigue, nausea, difficulties in climbing stairs, swelling in ankles, difficulty to sleep at night, irregular heartbeats, fullness, sweating, take frequent break during the day, dizzy and depress ed. Additionally, the output of heart disease is to classify whether the patient is healthy or suspecting with heart disease. The study contributes to providing insight into a way of designing the HFSs, particularly for the complex medical application.

Spectrum of Cardiovascular Abnormalities in Infants Born to Diabetic Mother in a Tertiary Care Center

Abstract Background Diabetes mellitus is one of the most common medical problems among pregnant women. Now, gestational diabetes mellitus (GDM) is increasing and amounts to 17% in Asian women but only in 4% of American and European women. In southern India, the prevalence of GDM is 17% in urban women, 13.8% in semiurban, and 9.8% in rural women. Aim The aim of the study is to find the cardiovascular abnormalities in infants born to a diabetic mother (IDM) and the association between infant’s heart lesion and diabetes mellitus in pregnant mother in a tertiary care center. Materials and Methods All babies born to both pregestational and gestational diabetic mother were included. Information regarding maternal type of diabetes, treatment regimen, maternal glycemic control status, antenatal ultrasonogram, baby’s sex, birth weight, gestational age, and clinical features were collected. Echocardiogram was done for all the babies. Results Out of the 100 IDM, 28 babies had cardiac disease, 5 babies had cyanotic heart disease, and 23 babies had acyanotic heart disease. Out of 100 diabetic mothers, 66 were on meal plan, 21 were on oral hypoglycemic agent (OHA) metformin, and 13 were on insulin therapy. Among 66 babies whose mother was on the meal plan, 8 had cardiac abnormality. Among the 21 mothers on OHA, 7 babies had cardiac abnormality and all the 13 babies of mothers who were on insulin had cardiac abnormality which was a significant finding among the IDM. Conclusion Maternal diabetes is a significant risk factor for heart disease in the newborn. Careful evaluation and early diagnosis of heart diseases in this high-risk group is of great value. Both pregestational and gestational diabetic mothers should monitor their blood sugar and maintain it in a normal range at the time of conception and early in pregnancy to reduce the risk of congenital heart disease in IDM.

Expert System for Early Diagnosis of Heart Disease Using the Random Forest Method

In Indonesia, coronary heart disease continues to grow. However, the efforts to prevention it can still be done by diagnosing the initial symptoms caused by using an expert system. This study was designed to build an expert system application to diagnose early coronary disease by random forest methods. The application interface was built using the PHP programming language using framework bootstrap, and uses the python programming language to build a random forest. To make an early diagnosis of coronary heart disease, a decision tree was built by training data from the UCI Dataset Machine Learning Repository using the random forest method. Followed by patient classification data that has been collected through 13 questions to get the diagnosis. The diagnosis results were normal, stadium 1, stadium 2, stadium 3 and stadium 4. Based on the tests that had been carried out, the application was able to provide results in accordance with the sample data collected using a confusion matrix resulting in an accuracy of 92.25% +/- 0.62 with 70% precision, remember 46%, which obtained a score of f0,5 72%.

Detection of Murmur from Non-Stationarity of Heart Sounds

Early diagnosis of heart diseases bears a major role in saving lives. Presence of spurious extra-frequency components, termed as murmurs within the phonocardiography record may be indicative of valvular disorders like stenosis, lesions or regurgitation. It is difficult to identify the subtitle spectral components of murmurs through subjective audition. In this paper, a technique is proposed to detect the presence of murmur from the heart signal by analyzing their non-stationarity behavior by using autocorrelation based features namely, Standard Error (SE) of Auto-Correlation Function (ACF) and absolute deviation of SE from the reciprocal of the square root of number of samples (β). The selected features corresponding to normal and murmur differ with a ‘P’ value of 1.80 x10-14 (dataset 1) and 2.20 x10-76 (dataset 2) for SE and β, respectively. It is found that SE and β could effectively distinguish normal and murmur with 100% accuracy, sensitivity, and specificity.

Loss of Ccbe1 affects cardiac-specification and cardiomyocyte differentiation in mouse embryonic stem cells.

Understanding the molecular pathways regulating cardiogenesis is crucial for the early diagnosis of heart diseases and improvement of cardiovascular disease. During normal mammalian cardiac development, collagen and calcium-binding EGF domain-1 (Ccbe1) is expressed in the first and second heart field progenitors as well as in the proepicardium, but its role in early cardiac commitment remains unknown. Here we demonstrate that during mouse embryonic stem cell (ESC) differentiation Ccbe1 is upregulated upon emergence of Isl1- and Nkx2.5- positive cardiac progenitors. Ccbe1 is markedly enriched in Isl1-positive cardiac progenitors isolated from ESCs differentiating in vitro or embryonic hearts developing in vivo. Disruption of Ccbe1 activity by shRNA knockdown or blockade with a neutralizing antibody results in impaired differentiation of embryonic stem cells along the cardiac mesoderm lineage resulting in a decreased expression of mature cardiomyocyte markers. In addition, knockdown of Ccbe1 leads to smaller embryoid bodies. Collectively, our results show that CCBE1 is essential for the commitment of cardiac mesoderm and consequently, for the formation of cardiac myocytes in differentiating mouse ESCs.

The heart in systemic lupus erythematosus - A comprehensive approach by cardiovascular magnetic resonance tomography.

BackgroundIn systemic lupus erythematosus (SLE), cardiac manifestations, e.g. coronary artery disease (CAD) and myocarditis are leading causes of morbidity and mortality. The prevalence of subclinical heart disease in SLE is unknown. We studied whether a comprehensive cardiovascular magnetic resonance (CMR) protocol may be useful for early diagnosis of heart disease in SLE patients without known CAD.MethodsIn this prospective, observational, cross-sectional study CMR including cine, late gadolinium enhancement (LGE) and stress perfusion sequences, ECG, and blood sampling were performed in 30 consecutive SLE patients without known CAD. All patients fulfilled at least 4/11 American College of Rheumatology (ACR) Criteria for the classification of SLE.Results30 patients (83% female) were enrolled, mean age was 45±14 years and mean SLE disease duration was 10±8 years. 80% had low to moderate disease activity. All had a low SLE damage index. CMR was abnormal in 13/30 (43%), showing LGE in 9/13, stress perfusion deficits in 5/13 and pericardial effusion (PE) in 7/13. Patients with non-ischemic LGE had more often microalbuminuria while patients with stress perfusion deficits a history of hypertension, renal disorder as ACR criterion, repolarisation abnormalities on ECG and larger LV enddiastolic volume index. There was no correlation between clinical symptoms and CMR results.ConclusionOur study shows that cardiac involvement as observed by CMR is frequent in SLE and not necessarily associated with typical symptoms. CMR may thus help to detect subclinical cardiac involvement, which could lead to earlier treatment. Additionally we identify possible risk factors associated with cardiac involvement.

Robust ECG data compression method based on ε-insensitive Huber loss function

Electrocardiogram (ECG) signals are continuously monitored for early diagnosis of heart diseases. However, a long-term monitoring generates large amounts of data at a level that makes storage and transmission difficult. Moreover, these records may be subject to different types of noise distributions resulting from operating conditions. Therefore, an effective and reliable data compression technique is needed for ECG data transmission, storage and analysis without losing the clinical information content. This study proposes the ε-insensitive Huber loss based support vector regression for the compressing of ECG signals. Since the Huber loss function is a mixture of quadratic and linear loss functions, it can properly take into account the different noise types in the data set. Compression performance of the proposed method has been assessed using ECG records from the MIT-BIH arrhythmia database. Experimental results demonstrate that the proposed loss function is an attractive candidate for compressing ECG data.

Learning Front-end Filter-bank Parameters using Convolutional Neural Networks for Abnormal Heart Sound Detection.

Automatic heart sound abnormality detection can play a vital role in the early diagnosis of heart diseases, particularly in low-resource settings. The state-of-the-art algorithms for this task utilize a set of Finite Impulse Response (FIR) band-pass filters as a front-end followed by a Convolutional Neural Network (CNN) model. In this work, we propound a novel CNN architecture that integrates the front-end band-pass filters within the network using time-convolution (tConv) layers, which enables the FIR filter-bank parameters to become learnable. Different initialization strategies for the learnable filters, including random parameters and a set of predefined FIR filter-bank coefficients, are examined. Using the proposed tConv layers, we add constraints to the learnable FIR filters to ensure linear and zero phase responses. Experimental evaluations are performed on a balanced 4-fold cross-validation task prepared using the PhysioNet/CinC 2016 dataset. Results demonstrate that the proposed models yield superior performance compared to the state-of-the-art system, while the linear phase FIR filter-bank method provides an absolute improvement of 9.54% over the baseline in terms of an overall accuracy metric.

MicroRNA as Biomarkers and Regulator of Cardiovascular Development and Disease

MicroRNAs are small noncoding RNAs that have emerged as important regulators of many biological and pathological processes, including those relevant to the development of the heart and cardiovascular disease. Several recent studies using genetic models and profiling of microRNAs have established the important role of these novel molecules in a number of conditions of the heart. These studies have led to a flurry of research focussing on the identification of new therapeutic targets for the treatment of cardiac disease, as well as the identification of potential biomarkers for early diagnosis of heart disease. These early reports have stimulated much interest in microRNAs and indeed other non-coding RNAs in the broader context of cardiovascular disease. This work has been further investigated as a result of ease with which the levels of these molecules can be modulated both in vitro but also in animal disease models. Furthermore, a number of studies have specifically looked at the prognostic potential of these microRNAs as biomarkers of cardiovascular disease. This review is focused on highlighting some of the novel aspects of recent research in the area of the development of new therapeutics and better diagnostics for cardiovascular disease.

GA-NN APPROACH FOR ECG FEATURE SELECTION IN RULE BASED ARRHYTHMIA CLASSIFICATION

Computer-aided ECG analysis is very important for early diagnosis of heart diseases. Automated ECG analysis integrated with experts' opinions may provide more accurate and reliable results for detection of arrhythmia. In this study, a novel genetic algorithm-neural network (GA-NN) approach is proposed as a classifier, and compared with other classification methods. The GA-NN ap- proach was shown to perform better than alternative approaches (e.g. k-nn, SVM, na¨ ive Bayes, Bayesian networks) on the UCI Arrythmia and the novel TEPAS ECG datasets, where the GA resulted in a feature reduction of 95%. Based on the selected features, several rule extraction algorithms are applied to allow the interpretation of the classification results by the experts. In this application, the accuracy and interpretability of results are more important than processing speed. The results show that neural network based approaches benefit greatly from di- mensionality reduction, and by employing GA, we can train the NN reliably.

Image-based patient-specific simulation: a computational modelling of the human left heart haemodynamics

The demand for early diagnosis of heart disease and more generally for a better quantitative knowledge of the heart flow dynamics is a continuous source of motivation for the development of non-inv...

Cost-Sensitive Risk Stratification in the Diagnosis of Heart Disease

We investigate machine learning methods for diagnostic screening of heart disease. Coronary heart disease is the leading cause of death in the US, causing more deaths than all types of cancers combined. Early diagnosis of heart disease in women is harder than it is in men and typically requires the administration of several clinical tests on the patient. Most risk stratification methods aggregate the results of such tests, including the risky, invasive procedures that cannot be administered on all patients. In this paper, our goal is to identify patients who are under high-risk of having heart disease and related adverse events, using a minimal number of diagnostic tests, especially less invasive ones. The low frequency of patients with severe heart disease in the dataset is challenging for most conventional machine learning methods. To overcome this problem, we develop and apply a cost-sensitive k nearest neighbor algorithm. Our contributions are two fold: First, we compare the predictive value of several diagnostic procedures for heart disease, including electrocardiography, angiography, radionuclide perfusion and conclude that in womens heart disease, certain combinations of noninvasive techniques are more predictive than some of the widely used invasive procedures. Then, we evaluate held out data and achieve an AUROC over 0.70, signifying valuable clinical utility, using only the least costly and least invasive tests.

Advanced Pulse Oximetry System for Remote Monitoring and Management

Pulse oximetry data such as saturation of peripheral oxygen (SpO2) and pulse rate are vital signals for early diagnosis of heart disease. Therefore, various pulse oximeters have been developed continuously. However, some of the existing pulse oximeters are not equipped with communication capabilities, and consequently, the continuous monitoring of patient health is restricted. Moreover, even though certain oximeters have been built as network models, they focus on exchanging only pulse oximetry data, and they do not provide sufficient device management functions. In this paper, we propose an advanced pulse oximetry system for remote monitoring and management. The system consists of a networked pulse oximeter and a personal monitoring server. The proposed pulse oximeter measures a patient's pulse oximetry data and transmits the data to the personal monitoring server. The personal monitoring server then analyzes the received data and displays the results to the patient. Furthermore, for device management purposes, operational errors that occur in the pulse oximeter are reported to the personal monitoring server, and the system configurations of the pulse oximeter, such as thresholds and measurement targets, are modified by the server. We verify that the proposed pulse oximetry system operates efficiently and that it is appropriate for monitoring and managing a pulse oximeter in real time.

Clinical Study of Heart Disease Complicating Pregnancy

–Heart disease complicating pregnancy is considered as a high risk situation. Increased cardiac demands during the course of pregnancy potentially increase morbidity and mortality in women with underlying heart disease. Risk of adverse outcome is more in rural population as compared to its urban counterpart. A prospective clinical study of 35 cases of pregnancy complicated by heart disease, reporting to tertiary care hospital for delivery ,was carried out to find out the incidence and maternal and fetal outcome. The incidence of heart disease in pregnancy in the present study was 1.3%%.Most of the women (91%) belonged to low socioeconomic class in the rural population..Rheumatic heart lesions constituted 77% of the cases. .Mitral stenosis was the commonest lesion in 40% of cases. Twenty two (62.8%) women delivered spontaneously vaginally at term and 4 ( 11% ) delivered prematurely. There were 7 ( 20%) cases of prophylactic forceps delivery. Cesarean section was performed in 2 cases .There was no maternal death .The perinatal mortality was 40 per 1000 live births. Early diagnosis of heart disease ,regular antenatal check up ,institutional delivery, limiting family size can reduce the maternal and perinatal mortality and morbidity associated with heart disease. Keywords––Heart disease in pregnancy , Rheumatic heart disease, Maternal mortality,

Multi-Channel Magnetocardiogardiography System Based on Low-Tc SQUIDs in an Unshielded Environment

Magnetocardiography (MCG) using superconducting quantum interference devices (SQUIDs) is a new medical diagnostic tool measuring biomagnetic signals that are generated by the electrical activity of the human heart. This technique is completely passive, contactless, and it has an advantage in the early diagnosis of heart diseases. We developed the first unshielded four-channel MCG system based on low-Tc DC SQUIDs in China. Instead of using a costly magnetically shielded room, the environmental noise suppression was realized by using second-order gradiometers and three-axis reference magnetometer. The measured magnetic field resolution of the system is better than 1 pT, and multi-cycle human heart signals can be recorded directly. Also, with the infrared positioning system, 48 points data collection can be realized by moving the non-magnetic bed nine times.

Cardiac MR and CT: Prime focus for correlative imaging

Cardiac disease is recognized as a major worldwide health problem with significant morbidity and mortality. Early diagnosis and treatment coupled with aggressive preventive measures are essential for positive outcomes. Rapid technological development has focused prime consideration upon the relative and correlative roles of magnetic resonance and computed tomography in the early diagnosis of heart disease, including coronary artery disease. In addition, the research emphasis in biomedicine, with the advent of the National Institute of Biomedical Imaging and Bioengineering and with the current focus at the National Institutes of Health on the Roadmap for Biomedical Research in the next decade, has recognized that imaging does and will play a vital role in diagnostic imaging and in fundamental biomedical research. The accelerating energy and number of program initiatives involved with multimodality molecular imaging provide an added opportunity and responsibility for investigators in the field to describe and evaluate the relative roles of imaging modalities that will interdigitate with the growing capabilities in molecular biology, genomics, and proteomics. These new tools will enable new methodologies, which will be deployed in addressing major worldwide health problems including heart disease, cancer, and stroke. Our special issue on cardiac imaging, comparing and contrasting MR and CT, represents a serious effort to define the state-of-the-art in this field. In addition, this compilation of articles sets forth the model that MRI must increasingly be applied, interpreted, and extended in correlation with other modalities used in healthcare and in biomedical research. We are fortunate to have Pamela K. Woodard, MD, Assistant Professor of Radiology, Cardiovascular Imaging Laboratory, Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, Missouri, and Arthur E. Stillman, MD, PhD, Head, Section of Cardiovascular MRI, Division of Radiology, The Cleveland Clinic Foundation, Cleveland, Ohio, as guest editors of our special issue. The editorial board wishes to express its appreciation to them for a job very well done.