Diagnosing aortic valve stenosis by correlation analysis of wavelet filtered heart sounds

Traditional auscultation performed by the general practitioner remains problematic and often gives significant results only in a late stage of heart valve disease. Valve stenoses and insufficiencies are nowadays diagnosed with accurate but expensive ultrasonic devices. This studyaimed to develop a new heart sound analysis method for diagnosing aortic valve stenoses (AVS) based on a wavelet and correlation technique approach. Heart sounds recorded from 373 patients (107 AVS patients, 61 healthy controls (REF) and 205 patients with other valve diseases (OVD)) with an electronic stethoscope were wavelet filtered, and envelopes were calculated. Three correlations on the basis of these envelopes were performed: within the AVS group, between the groups AVS and REF and between the groups AVS and OVD, resulting in the mean correlation coefficients r_AVS, r_AVSv.REF and r_AVSv.OVD. These results showed that r_AVS (0.783±0.097) is significantly higher (p<0.0001) than r_AVSv.REF (0.590±0.056) and r_AVSv.OVD (0.516±0.056), leading to a highly significant discrimination between the groups. The wavelet and correlation-based heart sound analysis system should be useful to general practitioners for low-cost, easy-to-use automatic diagnosis of aortic valve stenoses.     

Rate of progression of severity of valvular aortic stenosis

Twenty-six patients with valvular aortic stenosis were followed up for an average period of 9 years after the initial evaluation when the valvular disease had been considered too mild for surgical treatment. The valve area was 0.7-1.9 (mean 1.2) cm2 at the first study and 0.3-2.0 (mean 0.9) cm2 at the second. The mean annual decrease was about 0.1 cm2 in ten and less in the remaining patients. Advanced age and low physical working capacity at the first investigation were associated with rapid progression of the severity of the stenosis, but rapid progression was not predictable. At follow-up the combination of 1) calcifications of the valve on chest X-ray, 2) low physical working capacity and 3) negative/biphasic T wave in V6 after exercise was present in 100% of the severe stenoses (much less than 0.6 cm2) and in 10% of the mild (much greater than 1.0 cm2). The rate of progression of valvular aortic stenosis in adults is usually slow, but moderate stenoses may become severe within a few years.     

Automatic detection of sounds and murmurs in patients with lonescu-Shiley aortic bioprostheses

The problems encountered in the automatic detection of cardiac sounds and murmurs are numerous. The phonocardiogram (PCG) is a complex signal produced by deterministic events such as the opening and closing of the heart valves, and by random phenomena such as blood-flow turbulence. In addition, background noise and the dependence of the PCG on the recording sites render automatic detection a difficult task. In the paper we present an iterative automatic detection algorithm based on the a priori knowledge of spectral and temporal characteristics of the first and second heart sounds, the valve opening clicks, and the systolic and diastolic murmurs. The algorithm uses estimates of the PCG envelope and noise level to identify iteratively the position and duration of the significant acoustic events contained in the PCG. The results indicate that it is particularly effective in detecting the second heart sound and the aortic component of the second heart sound in patients with lonescu-Shiley aortic valve bioprostheses. It has also some potential for the detection of the first heart sound, the systolic murmur and the diastolic murmur.     

Cardiac sound murmurs classification with autoregressive spectral analysis and multi-support vector machine technique

In this paper, a novel cardiac sound spectral analysis method using the normalized autoregressive power spectral density (NAR-PSD) curve with the support vector machine (SVM) technique is proposed for classifying the cardiac sound murmurs. The 489 cardiac sound signals with 196 normal and 293 abnormal sound cases acquired from six healthy volunteers and 34 patients were tested. Normal sound signals were recorded by our self-produced wireless electric stethoscope system where the subjects are selected who have no the history of other heart complications. Abnormal sound signals were grouped into six heart valvular disorders such as the atrial fibrillation, aortic insufficiency, aortic stenosis, mitral regurgitation, mitral stenosis and split sounds. These abnormal subjects were also not included other coexistent heart valvular disorder. Considering the morphological characteristics of the power spectral density of the heart sounds in frequency domain, we propose two important diagnostic features Fmax and Fwidth, which describe the maximum peak of NAR-PSD curve and the frequency width between the crossed points of NAR-PSD curve on a selected threshold value (THV), respectively. Furthermore, a two-dimensional representation on (Fmax, Fwidth) is introduced. The proposed cardiac sound spectral envelope curve method is validated by some case studies. Then, the SVM technique is employed as a classification tool to identify the cardiac sounds by the extracted diagnostic features. To detect abnormality of heart sound and to discriminate the heart murmurs, the multi-SVM classifiers composed of six SVM modules are considered and designed. A data set was used to validate the classification performances of each multi-SVM module. As a result, the accuracies of six SVM modules used for detection of abnormality and classification of six heart disorders showed 71-98.9% for THVs=10-90% and 81.2-99.6% for THVs=10-50% with respect to each of SVM modules. With the proposed cardiac sound spectral analysis method, the high classification performances were achieved by 99.9% specificity and 99.5% sensitivity in classifying normal and abnormal sounds (heart disorders). Consequently, the proposed method showed relatively very high classification efficiency if the SVM module is designed with considering THV values. And the proposed cardiac sound murmurs classification method with autoregressive spectral analysis and multi-SVM classifiers is validated for the classification of heart valvular disorders.     

Utilizing wavelet transform and support vector machine for detection of the paradoxical splitting in the second heart sound

Paradoxical splitting occurs when pulmonic valve (P2) closes before the aortic valve (A2). This causes second heart sound (S2) to be a single sound during inspiration and split during exhalation. Etiology delay in aortic closure: aortic stenosis, volume overload of left ventricle (LV), conduction defects in LV, and left bundle branch block (LBBB). In this article, a method was proposed in early detection of a reverse in the appearance of A2 and P2 within S2. This method is based on the time–frequency maps obtained with the continuous wavelet transform (CWT), namely, the Meyer wavelet. A number of patients with LBBB and others with fitted pacemakers were studied. The above method is combined with the support vector machine (SVM) and performance of this method is evaluated using classification accuracy (Ca), sensitivity (Se), specificity, positive, and negative predicted values. Results show that it is relatively easy to detect the reverse in A2 and P2 and the Ca and Se is 90.97 and 94.44%, respectively, for the sample of 42 patients whose data were collected from the Cardiology Department at Brighton and Sussex University Hospital in England.     

A metric for the stiffness of calcified aortic valves using a combined computational and experimental approach

Calcific aortic valve disease is the most common heart valve disease. It is associated with a significant increase in cardiovascular morbidity and mortality and independently increases the cardiovascular risk. It is then important to develop parameters that can estimate the stiffness of the valve. Such parameters may contribute to early detection of the disease or track its progression and optimize the timing for therapy. In this study, we introduce a metric representing the stiffness of the native aortic calcified valve over a wide range of stenosis severities. Our approach is based on three-dimensional structural finite-element simulations and in vitro measurements. The proposed method is developed first in a pulse duplicator; its clinical applicability is then evaluated in three patients with severe aortic stenosis. Our results indicate that the value of the proposed metric varies considerably between healthy valves and valves with very severe aortic stenosis, from 0.001 to 7.38 MPa, respectively. The method introduced in this study could give useful information regarding the stiffness of the valve leaflets with potential application to the evaluation of aortic sclerosis and aortic stenosis.     

Echocardiogram analysis in a pattern recognition framework

Echocardiogram analysis is treated in a pattern recognition framework. Anterior mitral leaflet waveforms are classified for the four-class problem consisting of the classes "normal," "mitral stenosis," "mitral valve prolapse," and "idiopathic hypertrophic subaortic stenosis." In addition, aortic root waveforms and left ventricular wall waveforms are classified for the two-class problem consisting of the classes "normal" and "idiopathic hypertrophic subaortic stenosis." One common method of analysis (Fourier analysis) underlies each classification scheme. Classification accuracy is sufficiently good to warrant the inference that successful automated decision-making based on the algorithms investigated is feasible.     

Automatic measure of the split in the second cardiac sound by using the wavelet transform technique

This paper is concerned with the identification and automatic measure of the split in the second heart sound (S2) of the phonocardiogram signal (PCGs) for normal or pathological case. The second heart sound S2 consists of two acoustic components A2 and P2, the former is due to the closure of the aortic valve and the latter is due to the closure of the pulmonary valve. The aortic valve usually closes before the pulmonary valve, introducing a time delay known as "split". A automatic technique based on the discrete wavelet transform (DWT) and the continuous wavelet transform (CWT) is developed in this paper to measure the split of the second cardiac sound (S2) for the normal and pathological cases of the PCG signals. To quantify the splitting, the two components in S2 (i.e. A2 and P2) are identified and, the delay between the two components can be estimated. It is shown that the wavelet transform can provide best information and features of the split of S2 and the major components (A2 and P2) and consequently aid in medical diagnosis.     

基于冠脉造影图像血管树分割的血管狭窄自动识别方法

针对冠状动脉造影图像中的血管狭窄位置进行自动识别,并且定量评估其狭窄程度,为临床医生提供一种计算机辅助诊断方法,从而提高对冠状动脉狭窄的诊断准确率,同时减轻医生的劳动强度。所提出的基于冠脉造影图像的血管狭窄自动识别方法包括血管树分割以及血管狭窄识别两部分。在血管树分割部分,首先通过基于Frangi Hessian的改进模型进行图像增强,随后利用基于统计学区域融合方法对血管区域进行分割。在血管狭窄识别部分,首先利用水平集算法对分割结果进行细化获得血管骨架,随后提取血管边缘进行血管直径测量,最后采用局部最小点法计算整幅图像血管段狭窄的百分比,对狭窄段进行定位并分级。实验在153例患者的血管造影图像中检测出狭窄共计208段,其中轻度84段,中度42段,重度82段。统计分析结果显示,血管狭窄识别平均准确率为93.59%,敏感性为88.76%,特异性为95.58%,阳性预测值为90.51%,表明该方法能够有效地检测和定量评价动脉血管的狭窄程度,有助于心血管疾病的临床诊断。     

A comparison of different feature extraction methods for diagnosis of valvular heart diseases using PCG signals

This article presents a novel method for diagnosis of valvular heart disease (VHD) based on phonocardiography (PCG) signals. Application of the pattern classification and feature selection and reduction methods in analysing normal and pathological heart sound was investigated. After signal preprocessing using independent component analysis (ICA), 32 features are extracted. Those include carefully selected linear and nonlinear time domain, wavelet and entropy features. By examining different feature selection and feature reduction methods such as principal component analysis (PCA), genetic algorithms (GA), genetic programming (GP) and generalized discriminant analysis (GDA), the four most informative features are extracted. Furthermore, support vector machines (SVM) and neural network classifiers are compared for diagnosis of pathological heart sounds. Three valvular heart diseases are considered: aortic stenosis (AS), mitral stenosis (MS) and mitral regurgitation (MR). An overall accuracy of 99.47% was achieved by proposed algorithm.     

一种新的HHT在心音包络提取中的应用

目的：心音包络比原始心音可以更好地显示心音的特征,是进行心音识别的基础。希尔伯特一黄变换（HHT）是一种提取心音包络的有效方法,它首先利用经验模态分解算法提取心音信号的固有模态函数,然后利用希尔伯特变换提取心音包络。常规的希尔波特一黄变换在分解过程中会引起端点效应和过冲等问题。方法：本文提出了一种基于改进型希尔伯特一黄变换的心音包络提取新方法。结果：该方法首先采用包络线性延拓法抑制端点飞翼问题,然后采用l一次贝塞尔分段插值算法替代原始经验模态分解算法中的三次样条插值算法减小分解过程中的误差。结论：仿真实验和实际采集的心音信号实验证明了该方法的有效性。     

Spectral analysis of second heart sound in normal children by selective linear prediction coding

A spectral analysis technique using selective linear prediction (SLP) coding based on an all pole model is applied to determine the spectral distribution of second heart sounds (SII) in 17 normal children. The SLP spectra are compared with the conventional spectra obtained using the fast Fourier transform (FFT) technique. It is observed that the SLP technique produces spectra with better definition of spectral peaks. Average spectral energy distribution of second heart sound in normal children is presented. Spectral energies in different frequency bandwidths are correlated with the aortic valve size parameter obtained echocardiographically. It is found that the best correlation is obtained in the 120–140 Hz bandwidth. A possible interpretation in terms of documented second heart sound determinants is also discussed.     

Autosomal dominant inheritance of left ventricular outflow tract obstruction

Most nonsyndromic congenital heart malformations (CHMs) in humans are multifactorial in origin, although an increasing number of monogenic cases have been reported recently. We describe here four new families with presumed autosomal dominant inheritance of left ventricular outflow tract obstruction (LVOTO), consisting of hypoplastic left heart (HLHS) or left ventricle (HLV), aortic valve stenosis (AS) and bicuspid aortic valve (BAV), hypoplastic aortic arch (HAA), and coarctation of the aorta (CoA). LVOTO in these families shows a wide clinical spectrum with some family members having severe anomalies such as hypoplastic left heart, and others only minor anomalies such as mild aortic valve stenosis. This supports the suggestion that all anomalies of the LVOTO spectrum are developmentally related and can be caused by a single gene defect.     

Feature Extraction for Systolic Heart Murmur Classification

Heart murmurs are often the first signs of pathological changes of the heart valves, and they are usually found during auscultation in the primary health care. Distinguishing a pathological murmur from a physiological murmur is however difficult, why an “intelligent stethoscope” with decision support abilities would be of great value. Phonocardiographic signals were acquired from 36 patients with aortic valve stenosis, mitral insufficiency or physiological murmurs, and the data were analyzed with the aim to find a suitable feature subset for automatic classification of heart murmurs. Techniques such as Shannon energy, wavelets, fractal dimensions and recurrence quantification analysis were used to extract 207 features. 157 of these features have not previously been used in heart murmur classification. A multi-domain subset consisting of 14, both old and new, features was derived using Pudil’s sequential floating forward selection (SFFS) method. This subset was compared with several single domain feature sets. Using neural network classification, the selected multi-domain subset gave the best results; 86% correct classifications compared to 68% for the first runner-up. In conclusion, the derived feature set was superior to the comparative sets, and seems rather robust to noisy data.     

Noninvasive detection of mechanical prosthetic heart valve disorder

Auscultation is a widely used efficient technique by cardiologists for detecting the heart conditions. Since the mechanical prosthetic heart valves are widely used today, it is important to develop a simple and efficient method to detect abnormal mechanical valves. In this paper, the mechanical prosthetic heart valve sounds are analyzed by using different power spectral density (PSD) estimation techniques. To improve the classification accuracy of heart sounds, we propose two different feature extraction schemes, i.e., a modified local discriminant bases (LDB) scheme and a Hilbert-Huang Transform (HHT)-based scheme. A database of 150 heart sounds is used in this study and an average classification accuracy of 97.3% is achieved for both the two feature extraction schemes, when a generic linear discriminant analysis (LDA) classifier is used in the classification stage.     

Regression of valvular aortic stenosis due to homozygous familial hypercholesterolemia following plasmapheresis

Summary A 39-year-old male with homozygous familial hypercholesterolemia confirmed by tissue culture suffered from mild aortic insufficiency and valvular stenosis with a gradient of 20 mm Hg across the aortic valve. Plasmapheresis carried out every 2 weeks for 4 years resulted in a marked reduction in the serum cholesterol level and in a regression of the valvular stenosis, as shown by echocardiography and by left heart catheter.Abbreviations ECG electrocardiogram - LVH left ventricular hypertrophy - USP US pharmacopoea These studies were partly supported by a grant from the Deutsche Forschungsgemeinschaft     

Implications of third heart sounds in patients with valvular heart disease. The Veterans Affairs Cooperative Study on Valvular Heart Disease.

BACKGROUND. The presence of third heart sounds in patients with valvular heart disease is often regarded as a sign of heart failure, but it may also depend on the type of valvular disease. METHODS. We assessed the prevalence of third heart sounds and the relation between third heart sounds and cardiac function in 1281 patients with six types of valvular heart disease. RESULTS. The prevalence of third heart sounds was higher in patients with mitral regurgitation (46 percent) or aortic regurgitation (28 percent) than in those with aortic stenosis (11 percent) or mitral stenosis (8 percent). The left ventricular ejection fraction was significantly lower (P less than 0.001) when a third heart sound was detected in patients with aortic stenosis (0.38, vs. 0.56 in those without third heart sounds) or mixed aortic valve disease (0.40 vs. 0.55). However, the ejection fraction was only slightly lower in patients with mitral regurgitation and third heart sounds (0.51 vs. 0.57, P = 0.03). The pulmonary-capillary wedge pressure was higher (P less than 0.001) when a third heart sound was detected in patients with aortic stenosis (18.6 mm Hg, vs. 12.1 mm Hg in those without third heart sounds). There was no association between the wedge pressure and third heart sounds in patients with mitral regurgitation. The prevalence of third heart sounds increased with the severity of mitral regurgitation. CONCLUSIONS. In patients with mitral regurgitation, third heart sounds are common but do not necessarily reflect left ventricular systolic dysfunction or increased filling pressure. In patients with aortic stenosis, third heart sounds are uncommon but usually indicate the presence of systolic dysfunction and elevated filling pressure.     

Severe aortic valve stenosis in a 14-year-old boy with sitosterolemia

We report a 14-year-old boy finally diagnosed with sitosterolemia, presenting with severe aortic valve stenosis. Genetic analysis revealed homozygous null mutation c.1336 C > T (p.R446X) in ABCG5 gene. His cardiac ultrasound presented aortic valve stenosis and moderate aortic regurgitation. His whole aorta computed tomography angiogram scan revealed aortic stenosis superior to the aortic valve, followed by ascending aorta dilation, whereas his coronary and peripheral arteries appeared normal. His maximum total cholesterol and low-density lipoprotein-cholesterol levels dropped dramatically after diet control, and ezetimibe was prescribed for treatment. The current case indicated that sitosterolemia may be a heterogeneous disease in clinical phenotype.     

射血分数-压差比值评价伴左心功能不全的主动脉瓣狭窄程度

目的初步探讨射血分数-压差比值评价伴左心功能不全的主动脉瓣狭窄程度可行性。方法80例左心室收缩功能不全的主动脉瓣狭窄患者，其中男32例，女性48例，年龄38～85岁，平均年龄42岁。用彩色多普勒超声测量主动脉瓣口面积（AVA）、左心室射血分数（EF），Bernoulli方程计算主动脉瓣口跨瓣压差（△P），Simpson容积描记法计算射血分数压差比值即EFPR（EFPR=EF／△P），分析AVA与△P、EFPR之间的相关性；用ROC曲线比较△P、EFPR两参数评价主动脉瓣狭窄程度的敏感度和特异度。结果对主动脉瓣狭窄伴左心室收缩功能不全患者，用Simpson容积描记法计算ERPR估测AVA较Bemoulli方程计算的△P法更准确（r=0.9172对r=-0.6796，P〈0.001）；将EFPR小于1.0、△P大于10.7kda（80mmHg）来估测重度主动脉瓣狭窄伴左心功能不全时，EFPR和△uP的敏感度和特异度分别为87.5％、68.6％（P〈0.05）和98.3％、37.2％（P〈0.01），表明EFPR估测重度主动脉瓣狭窄伴左心功能不全患者的特异度及敏感度较高。结论EFPR能准确估测主动脉瓣狭窄患者主动脉瓣狭窄程度，特别对伴左心功能不全的重度主动脉瓣狭窄患者瓣膜狭窄程度的评价。EFPR较传统参数有更高敏感性和特异性。