Nonlinear transient chirp signal modeling of the aortic and pulmonary components of the second heart sound

Second heart sound splitting as an indicator of interventricular mechanical dyssynchrony using a novel splitting detection algorithm

Second heart sound (S2) splitting results from nonsimultaneous closures between aortic (A2) and pulmonic valves (P2) and may be used to detect timing differences (dyssynchrony) in relaxation between right (RV) and left ventricle (LV). However, overlap of A2 and P2 and the change in heart sound morphologies have complicated detection of the S2 splitting interval. This study introduces a novel S-transform amplitude ridge tracking (START) algorithm for estimating S2 splitting interval and investigates the relationship between S2 splitting and interventricular relaxation dyssynchrony (IRD). First, the START algorithm was validated in a simulated model of heart sound. It showed small errors (<5 ms) in estimating splitting intervals from 10 to 70 ms, with A2/P2 amplitude ratios from 0.2 to 5, and signal-to-noise ratios from 10 to 30 dB. Subsequently, the START algorithm was evaluated in a porcine model employing a wide range of paced RV-LV delays. IRD was quantified by the time difference between invasively measured LV and RV pressure downslopes. Between LV pre-excitation to RV pre-excitation, mean S2 splitting interval decreased from 47 ms to 23 ms (p < .001), accompanied by a decrease in mean IRD from 8 ms to -18 ms (p < .001). S2 splitting interval was significantly correlated with IRD in each experiment (p < .001). In conclusion, the START algorithm can accurately assess S2 splitting and may serve as a useful tool to assess interventricular dyssynchrony.

Deep Layer Kernel Sparse Representation Network for the Detection of Heart Valve Ailments from the Time-Frequency Representation of PCG Recordings

The heart valve ailments (HVAs) are due to the defects in the valves of the heart and if untreated may cause heart failure, clots, and even sudden cardiac death. Automated early detection of HVAs is necessary in the hospitals for proper diagnosis of pathological cases, to provide timely treatment, and to reduce the mortality rate. The heart valve abnormalities will alter the heart sound and murmurs which can be faithfully captured by phonocardiogram (PCG) recordings. In this paper, a time-frequency based deep layer kernel sparse representation network (DLKSRN) is proposed for the detection of various HVAs using PCG signals. Spline kernel-based Chirplet transform (SCT) is used to evaluate the time-frequency representation of PCG recording, and the features like L1-norm (LN), sample entropy (SEN), and permutation entropy (PEN) are extracted from the different frequency components of the time-frequency representation of PCG recording. The DLKSRN formulated using the hidden layers of extreme learning machine- (ELM-) autoencoders and kernel sparse representation (KSR) is used for the classification of PCG recordings as normal, and pathology cases such as mitral valve prolapse (MVP), mitral regurgitation (MR), aortic stenosis (AS), and mitral stenosis (MS). The proposed approach has been evaluated using PCG recordings from both public and private databases, and the results demonstrated that an average sensitivity of 100%, 97.51%, 99.00%, 98.72%, and 99.13% are obtained for normal, MVP, MR, AS, and MS cases using the hold-out cross-validation (CV) method. The proposed approach is applicable for the Internet of Things- (IoT-) driven smart healthcare system for the accurate detection of HVAs.

Synthesis of Normal Heart Sounds Using Generative Adversarial Networks and Empirical Wavelet Transform

Currently, there are many works in the literature focused on the analysis of heart sounds, specifically on the development of intelligent systems for the classification of normal and abnormal heart sounds. However, the available heart sound databases are not yet large enough to train generalized machine learning models. Therefore, there is interest in the development of algorithms capable of generating heart sounds that could augment current databases. In this article, we propose a model based on generative adversary networks (GANs) to generate normal synthetic heart sounds. Additionally, a denoising algorithm is implemented using the empirical wavelet transform (EWT), allowing a decrease in the number of epochs and the computational cost that the GAN model requires. A distortion metric (mel–cepstral distortion) was used to objectively assess the quality of synthetic heart sounds. The proposed method was favorably compared with a mathematical model that is based on the morphology of the phonocardiography (PCG) signal published as the state of the art. Additionally, different heart sound classification models proposed as state-of-the-art were also used to test the performance of such models when the GAN-generated synthetic signals were used as test dataset. In this experiment, good accuracy results were obtained with most of the implemented models, suggesting that the GAN-generated sounds correctly capture the characteristics of natural heart sounds.

An Approach for Automatic Identification of Fundamental and Additional Sounds from Cardiac Sounds Recordings

This paper presents an approach for automatic segmentation of cardiac events from non-invasive sounds recordings, without the need of having an auxiliary signal reference. In addition, methods are proposed to subsequently differentiate cardiac events which correspond to normal cardiac cycles, from those which are due to abnormal activity of the heart. The detection of abnormal sounds is based on a model built with parameters which are obtained following feature extraction from those segments that were previously identified as normal fundamental heart sounds. The proposed algorithm achieved a sensitivity of 91.79% and 89.23% for the identification of normal fundamental, S₁ and S₂ sounds, and a true positive (TP) rate of 81.48% for abnormal additional sounds. These results were obtained using the PASCAL Classifying Heart Sounds challenge (CHSC) database.

HEART SOUND MODEL BASED ON CASCADED AND LOSSLESS ACOUSTIC TUBES

In order to further understand the generation mechanism of Heart Sound, we introduce a new method for simulating Heart Sound by using cascaded and lossless acoustic tubes. Based on the theory of acoustics, we abstract the ventricles and arteries inside of the heart as multistage tubes with equal length and different radii. By controlling the radii of tubes, we simulate the process of relaxation and constriction of the ventricles and arteries. Then, we calculate the transfer function of the tubes based on the theory of reflective transmission line. To gain the tubes’ radii, we use formant frequency as the model target parameters and put forward an approximation method. Finally, the experimental results show that compared with traditional model, the model based on cascaded and lossless acoustic tubes could better reflect the state of the ventricles and arteries. Meanwhile, by comparing the model tube radius of normal Heart Sound and pathological Heart Sound, we can give a better explanation to the cause of pathological Heart Sound.

Data assimilation and multisource decision-making in systems biology based on unobtrusive Internet-of-Things devices

Biological and medical diagnoses depend on high-quality measurements. A wearable device based on Internet of Things (IoT) must be unobtrusive to the human body to encourage users to accept continuous monitoring. However, unobtrusive IoT devices are usually of low quality and unreliable because of the limitation of technology progress that has slowed down at high peak. Therefore, advanced inference techniques must be developed to address the limitations of IoT devices. This review proposes that IoT technology in biological and medical applications should be based on a new data assimilation process that fuses multiple data scales from several sources to provide diagnoses. Moreover, the required technologies are ready to support the desired disease diagnosis levels, such as hypothesis test, multiple evidence fusion, machine learning, data assimilation, and systems biology. Furthermore, cross-disciplinary integration has emerged with advancements in IoT. For example, the multiscale modeling of systems biology from proteins and cells to organs integrates current developments in biology, medicine, mathematics, engineering, artificial intelligence, and semiconductor technologies. Based on the monitoring objectives of IoT devices, researchers have gradually developed ambulant, wearable, noninvasive, unobtrusive, low-cost, and pervasive monitoring devices with data assimilation methods that can overcome the limitations of devices in terms of quality measurement. In the future, the novel features of data assimilation in systems biology and ubiquitous sensory development can describe patients' physical conditions based on few but long-term measurements.

A Phonocardiographic-Based Fiber-Optic Sensor and Adaptive Filtering System for Noninvasive Continuous Fetal Heart Rate Monitoring

This paper focuses on the design, realization, and verification of a novel phonocardiographic- based fiber-optic sensor and adaptive signal processing system for noninvasive continuous fetal heart rate (fHR) monitoring. Our proposed system utilizes two Mach-Zehnder interferometeric sensors. Based on the analysis of real measurement data, we developed a simplified dynamic model for the generation and distribution of heart sounds throughout the human body. Building on this signal model, we then designed, implemented, and verified our adaptive signal processing system by implementing two stochastic gradient-based algorithms: the Least Mean Square Algorithm (LMS), and the Normalized Least Mean Square (NLMS) Algorithm. With this system we were able to extract the fHR information from high quality fetal phonocardiograms (fPCGs), filtered from abdominal maternal phonocardiograms (mPCGs) by performing fPCG signal peak detection. Common signal processing methods such as linear filtering, signal subtraction, and others could not be used for this purpose as fPCG and mPCG signals share overlapping frequency spectra. The performance of the adaptive system was evaluated by using both qualitative (gynecological studies) and quantitative measures such as: Signal-to-Noise Ratio—SNR, Root Mean Square Error—RMSE, Sensitivity—S+, and Positive Predictive Value—PPV.

Quantitative Measurement of Split of the Second Heart Sound (S2)

This study proposes a quantitative measurement of split of the second heart sound (S2) based on nonstationary signal decomposition to deal with overlaps and energy modeling of the subcomponents of S2. The second heart sound includes aortic (A2) and pulmonic (P2) closure sounds. However, the split detection is obscured due to A2-P2 overlap and low energy of P2. To identify such split, HVD method is used to decompose the S2 into a number of components while preserving the phase information. Further, A2s and P2s are localized using smoothed pseudo Wigner-Ville distribution followed by reassignment method. Finally, the split is calculated by taking the differences between the means of time indices of A2s and P2s. Experiments on total 33 clips of S2 signals are performed for evaluation of the method. The mean ± standard deviation of the split is 34.7 ± 4.6 ms. The method measures the split efficiently, even when A2-P2 overlap is ≤ 20 ms and the normalized peak temporal ratio of P2 to A2 is low (≥ 0.22). This proposed method thus, demonstrates its robustness by defining split detectability (SDT), the split detection aptness through detecting P2s, by measuring up to 96 percent. Such findings reveal the effectiveness of the method as competent against the other baselines, especially for A2-P2 overlaps and low energy P2.

Denoising and segmentation of the second heart sound using matching pursuit

We propose a denoising and segmentation technique for the second heart sound (S2). To denoise, Matching Pursuit (MP) was applied using a set of non-linear chirp signals as atoms. We show that the proposed method can be used to segment the phonocardiogram of the second heart sound into its two clinically meaningful components: the aortic (A2) and pulmonary (P2) components.

Algorithm for detection of the internal components of the heart sounds and their split using a Hilbert transform

Valvular heart disease is a serious heart condition that is difficult to diagnose in ambulatory settings. Heart sounds is one of the most relevant diagnosis signals in this context. The time interval between the two internal components of the two heart sounds in the medical field known as 'split' was considered by many researchers and one study is described as the key medical diagnosis by many clinicians. Compared to the energy envelope Shannon Hilbert envelope is greater awareness of the internal components of the first and second heart sound. The morphology of this envelope will allow one to apply the necessary tests for the temporal localization of the internal components of the two heart sounds. According to the results obtained, the Hilbert envelope is an approach and representation taking into account the physiological attenuation and giving a good separation.

Detection of the valvular split within the second heart sound using the reassigned smoothed pseudo Wigner-Ville distribution

Background

In this paper, we developed a novel algorithm to detect the valvular split between the aortic and pulmonary components in the second heart sound which is a valuable medical information.

Methods

The algorithm is based on the Reassigned smoothed pseudo Wigner–Ville distribution which is a modified time–frequency distribution of the Wigner–Ville distribution. A preprocessing amplitude recovery procedure is carried out on the analysed heart sound to improve the readability of the time–frequency representation. The simulated S2 heart sounds were generated by an overlapping frequency modulated chirp–based model at different valvular split durations.

Results

Simulated and real heart sounds are processed to highlight the performance of the proposed approach. The algorithm is also validated on real heart sounds of the LGB–IRCM (Laboratoire de Génie biomédical–Institut de recherches cliniques de Montréal) cardiac valve database. The A2–P2 valvular split is accurately detected by processing the obtained RSPWVD representations for both simulated and real data.

A dynamical model for generating synthetic Phonocardiogram signals

In this paper we introduce a dynamical model for Phonocardiogram (PCG) signal which is capable of generating realistic synthetic PCG signals. This model is based on PCG morphology and consists of three ordinary differential equations and can represent various morphologies of normal PCG signals. Beat-to-beat variation in PCG morphology is significant so model parameters vary from beat to beat. This model is inspired of Electrocardiogram (ECG) dynamical model proposed by McSharry et al. and can be employed to assess biomedical signal processing techniques.

Modeling of heart systolic murmurs based on multivariate matching pursuit for diagnosis of valvular disorders

Heart murmurs are pathological sounds produced by turbulent blood flow due to certain cardiac defects such as valves disorders. Detection of murmurs via auscultation is a task that depends on the proficiency of physician. There are many cases in which the accuracy of detection is questionable. The purpose of this study is development of a new mathematical model of systolic murmurs to extract their crucial features for identifying the heart diseases. A high resolution algorithm, multivariate matching pursuit, was used to model the murmurs by decomposing them into a series of parametric time-frequency atoms. Then, a novel model-based feature extraction method which uses the model parameters was performed to identify the cardiac sound signals. The proposed framework was applied to a database of 70 heart sound signals containing 35 normal and 35 abnormal samples. We achieved 92.5% accuracy in distinguishing subjects with valvular diseases using a MLP classifier, as compared to the matching pursuit-based features with an accuracy of 77.5%.

Time-frequency analysis of phonocardiogram signals using wavelet transform: a comparative study

Analysis of phonocardiogram (PCG) signals provides a non-invasive means to determine the abnormalities caused by cardiovascular system pathology. In general, time-frequency representation (TFR) methods are used to study the PCG signal because it is one of the non-stationary bio-signals. The continuous wavelet transform (CWT) is especially suitable for the analysis of non-stationary signals and to obtain the TFR, due to its high resolution, both in time and in frequency and has recently become a favourite tool. It decomposes a signal in terms of elementary contributions called wavelets, which are shifted and dilated copies of a fixed mother wavelet function, and yields a joint TFR. Although the basic characteristics of the wavelets are similar, each type of the wavelets produces a different TFR. In this study, eight real types of the most known wavelets are examined on typical PCG signals indicating heart abnormalities in order to determine the best wavelet to obtain a reliable TFR. For this purpose, the wavelet energy and frequency spectrum estimations based on the CWT and the spectra of the chosen wavelets were compared with the energy distribution and the autoregressive frequency spectra in order to determine the most suitable wavelet. The results show that Morlet wavelet is the most reliable wavelet for the time-frequency analysis of PCG signals.

Forecasting the evolution of nonlinear and nonstationary systems using recurrence-based local Gaussian process models

An approach based on combining nonparametric Gaussian process (GP) modeling with certain local topological considerations is presented for prediction (one-step look ahead) of complex physical systems that exhibit nonlinear and nonstationary dynamics. The key idea here is to partition system trajectories into multiple near-stationary segments by aligning the boundaries of the partitions with those of the piecewise affine projections of the underlying dynamic system, and deriving nonparametric prediction models within each segment. Such an alignment is achieved through the consideration of recurrence and other local topological properties of the underlying system. This approach was applied for state and performance forecasting in Lorenz system under different levels of induced noise and nonstationarity, synthetic heart-rate signals, and a real-world time-series from an industrial operation known to exhibit highly nonlinear and nonstationary dynamics. The results show that local Gaussian process can significantly outperform not just classical system identification, neural network and nonparametric models, but also the sequential Bayesian Monte Carlo methods in terms of prediction accuracy and computational speed.

Separation of heart sound signal from noise in joint cycle frequency-time-frequency domains based on fuzzy detection

Noise is generally unavoidable during recordings of heart sound signal. Therefore, noise reduction is one of the important preprocesses in the analysis of heart sound signal. This was achieved in joint cycle frequency-time-frequency domains in this study. Heart sound signal was decomposed into components (called atoms) characterized by time delay, frequency, amplitude, time width, and phase. It was discovered that atoms of heart sound signal congregate in the joint domains. On the other hand, atoms of noise were dispersed. The atoms of heart sound signal could, therefore, be separated from the atoms of noise based on fuzzy detection. In a practical experiment, heart sound signal was successfully separated from lung sounds and disturbances due to chest motion. Computer simulations for various clinical heart sound signals were also used to evaluate the performance of the proposed noise reduction. It was shown that heart sound signal can be reconstructed from simulated complex noise (perhaps non-Gaussian, nonstationary, and colored). The proposed noise reduction can recover variations in the both waveform and time delay of heart sound signal during the reconstruction. Correlation coefficient and normalized residue were used to indicate the closeness of the reconstructed and noise-free heart sound signal. Correlation coefficient may exceed 0.90 and normalized residue may be around 0.10 in 0-dB noise environment, even if the phonocardiogram signal covers only ten cardiac cycles.

Computer aided analysis of phonocardiogram

In the present paper analysis of phonocardiogram (PCG) records are presented. The analysis has been carried out in both time and frequency domains with the aim of detecting certain correlations between the time and frequency domain representations of PCG. The analysis is limited to first and second heart sounds (S1 and S2) only. In the time domain analysis the moving window averaging technique is used to determine the occurrence of S1 and S2, which helps in determination of cardiac interval and absolute and relative time duration of individual S1 and S2, as well as absolute and relative duration between them. In the frequency domain, fast Fourier transform (FFT) of the complete PCG record, and short time Fourier transform (STFT) and wavelet transform of individual heart sounds have been carried out. The frequency domain analysis gives an idea about the dominant frequency components in individual records and frequency spectrum of individual heart sounds. A comparative observation on both the analyses gives some correlation between time domain and frequency domain representations of PCG.

Time-Frequency Representations for second heart sound analysis

Several researches have tried to provide a means to analyze the second heart sound (S2) in an attempt to understand the functional mechanisms in its genesis and for diagnosis purposes. In this work we tested Time-Frequency Representation (TFR) for simulated S2 selecting and applying classical and modern TFRs such as the Spectrogram, the Wigner-Ville Distribution, the Time Varying Autoregressive (TVAR) model, the Scalogram, and the Hilbert-Huang Spectrum (HHS) by Empirical Mode Decomposition. Two performance measures are proposed, the first one based on local 2D correlations (rho) between the ideal and the estimated TFRs images, while the second one based on time moments of the TFR images to provide the normalized root-mean-square error (NRMSE). Under no noise conditions, the TFRs by HHS and the TVAR modeling, by the Burg algorithm, resulted in a rho(average) of 0.788 and 0.812, and NRMSE of 0.172 and 0.195, respectively. Therefore, based on the lowest NRMSE, HHS was considered the TFR with the best performance. Afterward, HHS was applied to real S2 acquired at the aortic and pulmonary focal points.

Knowledge based system with embedded intelligent heart sound analyser for diagnosing cardiovascular disorders

Cardiovascular disease (CVD) is the leading cause of death worldwide, and due to the lack of early detection techniques, the incidence of CVD is increasing day by day. In order to address this limitation, a knowledge based system with embedded intelligent heart sound analyser (KBHSA) has been developed to diagnose cardiovascular disorders at early stages. The system analyses digitized heart sounds that are recorded from an electronic stethoscope using advanced digital signal processing and artificial intelligence techniques. KBHSA takes into account data including the patient's personal and past medical history, clinical examination, auscultation findings, chest x-ray and echocardiogram, and provides a list of diseases that it has diagnosed. The system can assist the general physician in making more accurate and reliable diagnosis under emergency conditions where expert cardiologists and advanced equipment are not readily available. To test the validity of the system, abnormal heart sound samples and medical data from 40 patients were recorded and analysed. The diagnoses made by the system were counter checked by four senior cardiologists in Malaysia. The results show that the findings of KBHSA coincide with those of cardiologists.

A robust method to estimate time split in second heart sound using instantaneous frequency analysis

Closure of the aortic valve (A2) and the pulmonary valve (P2) generates the second heart sound (S2). The time separation between A2 and P2 is known as the A2-P2 split and it has very important diagnostic potential. Methods proposed in the past to measure the split noninvasively are limited either by prior signal modeling assumptions or by reliance on manual processing in key steps. In this work, we propose a new method that is devised to noninvasively provide an automated measurement of the time split between A2 and P2 with minimal prior assumptions on signal models. Our method is based on tracking the changes of the instantaneous frequency (IF) of S2 via time frequency representation of the S2 obtained by smoothed Wigner-Ville Distribution. The cues provided by the changes in the IF trajectory are analyzed using an automated procedure to identify the onset of the P2 pulse. Simulations are carried out to demonstrate the effectiveness of the procedure in estimating the split. The performance of the method in the presence of noise varying between 6 dB and 8 dB for several trials and interference is investigated and the robustness of the method is demonstrated.

A procedure to extract the aortic and the pulmonary sounds from the phonocardiogram

The time interval between the aortic (A2) and pulmonary (P2) components of the second heart sound (S2) is an indicator of the presence and severity of several cardiac abnormalities. However, in many cases identification of the A2 and P2 components is difficult due to their temporal overlap and significant spectral similarity. In this work, we present a method to extract the A2 and P2 components from the S2 sound, by assuming their mutual statistical independence. Once extracted, the A2 and P2 components are identified by using a physiological reference signal. Results obtained from real data are encouraging, and show promise for utilizing the proposed method in a clinical setting to non-invasively tract the A2-P2 time interval.

Backpropagation artificial neural network classifier to detect changes in heart sound due to mitral valve regurgitation

The phonocardiograph (PCG) can provide a noninvasive diagnostic ability to the clinicians and technicians to compare the heart acoustic signal obtained from normal and that of pathological heart (cardiac patient). This instrument was connected to the computer through the analog to digital (A/D) converter. The digital data stored for the normal and diseased (mitral valve regurgitation) heart in the computer were decomposed through the Coifman 4th order wavelet kernel. The decomposed phonocardiographic (PCG) data were tested by backpropagation artificial neural network (ANN). The network was containing 64 nodes in the input layer, weighted from the decomposed components of the PCG in the input layer, 16 nodes in the hidden layer and an output node. The ANN was found effective in differentiating the wavelet components of the PCG from mitral valve regurgitation confirmed person (93%) to normal subjects (98%) with an overall performance of 95.5%. This system can also be used to detect the defects in cardiac valves especially, and other several cardiac disorders in general.

Automated extraction of aortic and pulmonary components of the second heart sound for the estimation of pulmonary artery pressure

The second heart sound, S2, is generally believed to be comprised of aortic (A2) and pulmonary (P2) components. Previously, the normalized splitting interval (NSI) between the A2 and P2 components has been shown to be proportional to the pulmonary artery pressure (PAP). A set of fully automated algorithms based on adaptive modeling of A2/P2 components using chirplets were developed to provide real-time estimates of PAP. The method was tested on 16 pigs which were administered drugs to induce pulmonary hypertension. Simultaneous reference pressure measurements were obtained with a pulmonary artery catheter (PAC). Estimation of PAP in pigs using the new techniques resulted in a correlation coefficient (r) of 0.84 and standard error (SEE) of 9.2 mm Hg. This is in line with echocardiography studies, which have a performance ranging from r=0.69-0.91 and SEE from 5 to 12 mm Hg when compared to PAC measurements. It is also consistent with previous results based on a manual estimation of PAP derived through image processing methods. Based on these findings, this method has the potential to offer continuous noninvasive monitoring of PAP.

Classification of homomorphic segmented phonocardiogram signals using grow and learn network

A segmentation algorithm, which detects a single cardiac cycle (S1-Systole-S2-Diastole) of Phonocardiogram (PCG) signals using Homomorphic filtering and K-means clustering and a three way classification of heart sounds into Normal (N), Systolic murmur (S) and Diastolic murmur (D) using Grow and Learn (GAL) neural network, are presented. Homomorphic filtering converts a non-linear combination of signals (multiplied in time domain) into a linear combination by applying logarithmic transformation. It involves the retrieval of the envelope, a(n) of the PCG signal by attenuating the contribution of fast varying component, f(n) using an appropriate low pass filter. K-means clustering is a nonhierarchical partitioning method, which helps to indicate single cardiac cycle in the PCG signal. Segmentation performance of 90.45% was achieved using the proposed algorithm. Feature vectors were formed after segmentation by using Daubechies-2 wavelet detail coefficients at the second decomposition level. Grow and Learn network was used for classification of the segmented PCG signals and a classification accuracy of 97.02% was achieved. It is concluded that Homomorphic filtering and GAL network could be used for segmentation and classification of PCG signals without using a reference signal.

A dynamic method to estimate the time split between the A2 and P2 components of the S2 heart sound

The time interval between the aortic (A2) and the pulmonary (P2) components of the second heart sound (S2) is an indicator of pulmonary arterial pressure. However, knowledge of the A2 and P2 components of the S2 sound is difficult to obtain due to their temporal overlap and significant spectral similarity. In this work, we aim to extract the A2 and P2 components from the phonocardiogram to estimate the time interval between them. We attain our objective by first isolating the S2 sound from the phonocardiogram by utilizing the mode complexity of the heart. Then, we assume the statistical independence of the A2 and P2 components and extract them from the S2 sound by the application of blind source separation techniques. Once separated, the time interval between the A2 and P2 components is estimated with a time-centroid-based method. Experimental results using simulated data show excellent performance of the proposed algorithm to extract the A2 and the P2 components from the S2 sound and to estimate the time interval between them. Results obtained from real data are also encouraging and show promise for utilizing the proposed method in a clinical setting to non-invasively tract pulmonary hypertension.

Haemodynamic determinants of the mitral valve closure sound: a finite element study

Automatic acoustic classification and diagnosis of mitral valve disease remain outstanding biomedical problems. Although considerable attention has been given to the evolution of signal processing techniques, the mechanics of the first heart sound generation has been largely overlooked. In this study, the haemodynamic determinants of the first heart sound were examined in a computational model. Specifically, the relationship of the transvalvular pressure and its maximum derivative to the time-frequency content of the acoustic pressure was examined. To model the transient vibrations of the mitral valve apparatus bathed in a blood medium, a dynamic, non-linear, fluid-coupled finite element model of the mitral valve leaflets and chordae tendinae was constructed. It was found that the root mean squared (RMS) acoustic pressure varied linearly (r2= 0.99) from 0.010 to 0.259 mmHg, following an increase in maximum dP/dt from 415 to 12470 mm Hg s(-1). Over that same range, peak frequency varied non-linearly from 59.6 to 88.1 Hz. An increase in left-ventricular pressure at coaptation from 22.5 to 58.5mm Hg resulted in a linear (r2= 0.91) rise in RMS acoustic pressure from 0.017 to 1.41mm Hg. This rise in transmitral pressure was accompanied by a non-linear rise in peak frequency from 63.5 to 74.1 Hz. The relationship between the transvalvular pressure and its derivative and the time-frequency content of the first heart sound has been examined comprehensively in a computational model for the first time. Results suggest that classification schemes should embed both of these variables for more accurate classification.

Detection of the third heart sound using a tailored wavelet approach

The third heart sound is normally heard during auscultation of younger individuals but disappears with increasing age. However, this sound can appear in patients with heart failure and is thus of potential diagnostic use in these patients. Auscultation of the heart involves a high degree of subjectivity. Furthermore, the third heart sound has low amplitude and a low-frequency content compared with the first and second heart sounds, which makes it difficult for the human ear to detect this sound. It is our belief that it would be of great help to the physician to receive computer-based support through an intelligent stethoscope, to determine whether a third heart sound is present or not. A precise, accurate and low-cost instrument of this kind would potentially provide objective means for the detection of early heart failure, and could even be used in primary health care. In the first step, phonocardiograms from ten children, all known to have a third heart sound, were analysed, to provide knowledge about the sound features without interference from pathological sounds. Using this knowledge, a tailored wavelet analysis procedure was developed to identify the third heart sound automatically, a technique that was shown to be superior to Fourier transform techniques. In the second step, the method was applied to phonocardiograms from heart patients known to have heart failure. The features of the third heart sound in children and of that in patients were shown to be similar. This resulted in a method for the automatic detection of third heart sounds. The method was able to detect third heart sounds effectively (90%), with a low false detection rate (3.7%), which supports its clinical use. The detection rate was almost equal in both the children and patient groups. The method is therefore capable of detecting, not only distinct and clearly visible/audible third heart sounds found in children, but also third heart sounds in phonocardiograms from patients suffering from heart failure.

A new, simple, and accurate method for non-invasive estimation of pulmonary arterial pressure

OBJECTIVE

To develop and validate a new non-invasive method for the estimation of pulmonary arterial pressure (PAP) based on advanced signal processing of the second heart sound.

DESIGN

Prospective comparative study.

SETTING

Referral cardiology centre.

PATIENTS

This method was first tested in 16 pigs with experimentally induced pulmonary hypertension and then in 23 patients undergoing pulmonary artery catheterisation.

METHODS

The heart sounds were recorded at the surface of the thorax using a microphone connected to a personal computer. The splitting time interval between the aortic and the pulmonary components of the second heart sound was measured using a computer assisted spectral dechirping method and was normalised for heart rate.

RESULTS

The systolic PAP varied between 14-73 mm Hg in pigs and between 20-70 mm Hg in patients. The normalised splitting interval was measurable in 97% of the recordings made in pigs and 91% of the recordings made in patients. There was a strong relation between the normalised splitting interval and the systolic PAP (pigs: r = 0.94, standard error of the estimate (SEE) = 5.3 mm Hg; patients: r = 0.84, SEE = 7.8 mm Hg) or the mean pulmonary pressure (pigs: r = 0.94, SEE = 4.1 mm Hg; patients: r = 0.85, SEE = 5.8 mm Hg).

CONCLUSIONS

This study shows that this new non-invasive method based on advanced signal processing of the second heart sound provides an accurate estimation of the PAP.

A virtual instrument for acquisition and analysis of the phonocardiogram and its internet-based application

The objective of this study is to develop a phonocardiogram (PCG) acquisition and analysis instrument using virtual instrumentation technology and investigate its Internet-based application. The PCG instrument was developed using a Pentium 200 computer, a data acquisition board, and a two-channel custom designed bio-signal preamplifier. LabVIEW was used to create the instrument's front panels. Spectral and joint time-frequency analyses were implemented into the instrument. This instrument can be used to display the PCG and to analyze the individual heart sound and murmur for the detection of heart valve diseases. Using a test-bed, the PCG data acquisition and analysis were performed remotely over the Internet. Through the main PCG panel, an operator can control the acquisition and analysis of PCG signals. In the remote test, real-time transmission of the PCG signal over the Internet was possible. Remote operators were able to view smoothly scrolling PCG waveforms and could control all the acquisition parameters and perform spectral and time-frequency analyses on the acquired heart sound. This study demonstrated that a LabVIEW-based medical virtual instrument provides a low-cost and flexible solution for data acquisition and analysis of PCG. It also showed that the current Internet supports the transmission of real-time PCG signals. Compared with other telemedicine systems, this application transfers not only the medical data, but also the virtual instrument and its signal processing capability through the Internet.

Extraction of the aortic and pulmonary components of the second heart sound using a nonlinear transient chirp signal model

The objective of this paper is to adapt and validate a nonlinear transient chirp signal modeling approach for the analysis and synthesis of overlapping aortic (A2) and pulmonary (P2) components of the second heart sound (S2). The approach is based on the time-frequency representation of multicomponent signals for estimating and reconstructing the instantaneous phase and amplitude functions of each component. To evaluate the accuracy of the approach, a simulated S2 with A2 and P2 components having different overlapping intervals (5-30 ms) was synthesized. The simulation results show that the technique is very effective for extracting the two components, even in the presence of noise (-15 dB). The normalized root-mean-squared error between the original A2 and P2 components and their reconstructed versions varied between 1% and 6%, proportionally to the duration of the overlapping interval, and it increased by less than 2% in the presence of noise. The validated technique was then applied to S2 components recorded in pigs under normal or high pulmonary artery pressures. The results show that this approach can successfully isolate and extract overlapping A2 and P2 components from successive S2 recordings obtained from different heartbeats of the same animal as well from different animals.