Screening of neonatal congenital heart diseases based on heart sound acquisition system / 上海预防医学

ObjectiveTo investigate the value of remote consultation of heart sound acquisition in screening and referral of neonates with congenital heart diseases （CHD） in primary hospitals. MethodsA total of 4 030 neonates with non-critical diseases were selected. They were born in Shanghai Pudong New Area Maternal and Child Health Hospital from November 5， 2019 to March 31， 2021. After birth， routine cardiac auscultation was performed and remote consultation of heart sound collection were performed at the same time in combination with percutaneous oxygen saturation measurement to screen CHD. The children with any positive screening index were advised to verify the diagnosis by cardiac ultrasound examination in Shanghai Children's Medical Center. The diagnostic value of different screening methods was compared. ResultsA total of 110 cases were detected positive by routine screening. Among them， 16 cases were lost to follow-up， and 46 cases were confirmed by cardiac ultrasound examination， with a positive diagnosis rate of 48.94% （46/94）. A total of 51 cases were detected positive by routine screening and remote consultation of heart sound collection simultaneously. Among them， 42 cases were confirmed by cardiac ultrasound examination， with a positive diagnosis rate of 82.35% （42/51）. The difference between the two positive diagnosis rates was statistically significant （P<0.001）. ConclusionRemote consultation of heart sound acquisition on the basis of routine neonatal CHD screening can effectively improve the positive diagnosis rate of CHD screening in primary hospitals， and reduce unnecessary referrals. This method is simple and feasible. It has practical value in primary hospitals that lack professional technicians for the diagnosis and treatment of CHD.

Heart sound classification based on improved mel frequency cepstrum coefficient and integrated decision network method / 生物医学工程学杂志

Heart sound analysis is significant for early diagnosis of congenital heart disease. A novel method of heart sound classification was proposed in this paper, in which the traditional mel frequency cepstral coefficient (MFCC) method was improved by using the Fisher discriminant half raised-sine function (F-HRSF) and an integrated decision network was used as classifier. It does not rely on segmentation of the cardiac cycle. Firstly, the heart sound signals were framed and windowed. Then, the features of heart sounds were extracted by using improved MFCC, in which the F-HRSF was used to weight sub-band components of MFCC according to the Fisher discriminant ratio of each sub-band component and the raised half sine function. Three classification networks, convolutional neural network (CNN), long and short-term memory network (LSTM), and gated recurrent unit (GRU) were combined as integrated decision network. Finally, the two-category classification results were obtained through the majority voting algorithm. An accuracy of 92.15%, sensitivity of 91.43%, specificity of 92.83%, corrected accuracy of 92.01%, and F score of 92.13% were achieved using the novel signal processing techniques. It shows that the algorithm has great potential in early diagnosis of congenital heart disease.

A heart sound classification method based on complete ensemble empirical modal decomposition with adaptive noise permutation entropy and support vector machine / 生物医学工程学杂志

Heart sound signal is a kind of physiological signal with nonlinear and nonstationary features. In order to improve the accuracy and efficiency of the phonocardiogram (PCG) classification, a new method was proposed by means of support vector machine (SVM) in which the complete ensemble empirical modal decomposition with adaptive noise (CEEMDAN) permutation entropy was as the eigenvector of heart sound signal. Firstly, the PCG was decomposed by CEEMDAN into a number of intrinsic mode functions (IMFs) from high to low frequency. Secondly, the IMFs were sifted according to the correlation coefficient, energy factor and signal-to-noise ratio. Then the instantaneous frequency was extracted by Hilbert transform, and its permutation entropy was constituted into eigenvector. Finally, the accuracy of the method was verified by using a hundred PCG samples selected from the 2016 PhysioNet/CinC Challenge. The results showed that the accuracy rate of the proposed method could reach up to 87%. In comparison with the traditional EMD and EEMD permutation entropy methods, the accuracy rate was increased by 18%-24%, which demonstrates the efficiency of the proposed method.

Recognition of S1 and S2 heart sounds with two-stream convolutional neural networks / 生物医学工程学杂志

Auscultation of heart sounds is an important method for the diagnosis of heart conditions. For most people, the audible component of heart sound are the first heart sound (S1) and the second heart sound (S2). Different diseases usually generate murmurs at different stages in a cardiac cycle. Segmenting the heart sounds precisely is the prerequisite for diagnosis. S1 and S2 emerges at the beginning of systole and diastole, respectively. Locating S1 and S2 accurately is beneficial for the segmentation of heart sounds. This paper proposed a method to classify the S1 and S2 based on their properties, and did not take use of the duration of systole and diastole. S1 and S2 in the training dataset were transformed to spectra by short-time Fourier transform and be feed to the two-stream convolutional neural network. The classification accuracy of the test dataset was as high as 91.135%. The highest sensitivity and specificity were 91.156% and 92.074%, respectively. Extracting the features of the input signals artificially can be avoid with the method proposed in this article. The calculation is not complicated, which makes this method effective for distinguishing S1 and S2 in real time.

A heart sound classification method based on joint decision of extreme gradient boosting and deep neural network / 生物医学工程学杂志

Heart sound is one of the common medical signals for diagnosing cardiovascular diseases. This paper studies the binary classification between normal or abnormal heart sounds, and proposes a heart sound classification algorithm based on the joint decision of extreme gradient boosting (XGBoost) and deep neural network, achieving a further improvement in feature extraction and model accuracy. First, the preprocessed heart sound recordings are segmented into four status, and five categories of features are extracted from the signals based on segmentation. The first four categories of features are sieved through recursive feature elimination, which is used as the input of the XGBoost classifier. The last category is the Mel-frequency cepstral coefficient (MFCC), which is used as the input of long short-term memory network (LSTM). Considering the imbalance of the data set, these two classifiers are both improved with weights. Finally, the heterogeneous integrated decision method is adopted to obtain the prediction. The algorithm was applied to the open heart sound database of the PhysioNet Computing in Cardiology(CINC) Challenge in 2016 on the PhysioNet website, to test the sensitivity, specificity, modified accuracy and F score. The results were 93%, 89.4%, 91.2% and 91.3% respectively. Compared with the results of machine learning, convolutional neural networks (CNN) and other methods used by other researchers, the accuracy and sensibility have been obviously improved, which proves that the method in this paper could effectively improve the accuracy of heart sound signal classification, and has great potential in the clinical auxiliary diagnosis application of some cardiovascular diseases.

Heart sound classification based on sub-band envelope and convolution neural network / 生物医学工程学杂志

Automatic classification of heart sounds plays an important role in the early diagnosis of congenital heart disease. A kind of heart sound classification algorithms based on sub-band envelope feature and convolution neural network was proposed in this paper, which did not need to segment the heart sounds according to cardiac cycle accurately. Firstly, the heart sound signal was divided into some frames. Then, the frame level heart sound signal was filtered with Gammatone filter bank to obtain the sub-band signals. Next, the sub-band envelope was extracted by Hilbert transform. After that, the sub-band envelope was stacked into a feature map. Finally, type Ⅰ and type Ⅱ convolution neural network were selected as classifier. The result shown that the sub-band envelope feature was better in type Ⅰ than type Ⅱ. The algorithm is tested with 1 000 heart sound samples. The test results show that the overall performance of the algorithm proposed in this paper is significantly improved compared with other similar algorithms, which provides a new method for automatic classification of congenital heart disease, and speeds up the process of automatic classification of heart sounds applied to the actual screening.

Heart sound denoising by dynamic noise estimation / 生物医学工程学杂志

Denoising methods based on wavelet analysis and empirical mode decomposition cannot essentially track and eliminate noise, which usually cause distortion of heart sounds. Based on this problem, a heart sound denoising method based on improved minimum control recursive average and optimally modified log-spectral amplitude is proposed in this paper. The proposed method uses a short-time window to smoothly and dynamically track and estimate the minimum noise value. The noise estimation results are used to obtain the optimal spectrum gain function, and to minimize the noise by minimizing the difference between the clean heart sound and the estimated clean heart sound. In addition, combined with the subjective analysis of spectrum and the objective analysis of contribution to normal and abnormal heart sound classification system, we propose a more rigorous evaluation mechanism. The experimental results show that the proposed method effectively improves the time-frequency features, and obtains higher scores in the normal and abnormal heart sound classification systems. The proposed method can help medical workers to improve the accuracy of their diagnosis, and also has great reference value for the construction and application of computer-aided diagnosis system.

Segmentation of heart sound signals based on duration hidden Markov model / 生物医学工程学杂志

Heart sound segmentation is a key step before heart sound classification. It refers to the processing of the acquired heart sound signal that separates the cardiac cycle into systolic and diastolic, etc. To solve the accuracy limitation of heart sound segmentation without relying on electrocardiogram, an algorithm based on the duration hidden Markov model (DHMM) was proposed. Firstly, the heart sound samples were positionally labeled. Then autocorrelation estimation method was used to estimate cardiac cycle duration, and Gaussian mixture distribution was used to model the duration of sample-state. Next, the hidden Markov model (HMM) was optimized in the training set and the DHMM was established. Finally, the Viterbi algorithm was used to track back the state of heart sounds to obtain S

Design and Implementation of Heart Sound Detection Device Based on MEMS MIC / 中国医疗器械杂志

The paper describes how to develop a digital heart sound signal detection device based on high gain MEMS MIC that can accurately collect and store human heart sounds. According to the method of collecting heart sound signal by traditional stethoscope, the system improves the traditional stethoscope, and a composite probe equipped with a MEMS microphone sensor is designed. The MEMS microphone sensor converts the sound pressure signal into a voltage signal, and then amplifies, converts with Sigma Delta, extracts and filters the collected signal. After the heart sound signal is uploaded to the PC, the Empirical Mode Decomposition (EMD) is carried out to reconstruct the signal, and then the Independent Component Analysis (ICA) method is used for blind source separation and finally the heart rate is calculated by autocorrelation analysis. At the end of the paper, a preliminary comparative analysis of the performance of the system was carried out, and the accuracy of the heart sound signal was verified.

Design and Implementation of a New Heart Sound Detecting Device / 中国医疗器械杂志

This article describes how to develop a practical new type of digital heart sound signal detection device that can achieve quantitative and accurate capture of human heart sounds and records. According to the mechanism and characteristics of the heart sound signal, the goal of this system design is to set the platform. The system uses a contact-type piezoelectric film microphone, which can effectively pick up the effective frequency band of the heart sound, then amplify and filter the collected original signal, and perform preliminary verification on the system to obtain the desired heart sound signal.

Recognition of heart sound based on distribution of Choi-Williams

IntroductionTo realize noninvasive diagnosis and early diagnosis of coronary heart disease, the study proposes a new time-frequency method for analyzing heart sound signals. This method is based on Choi-Williams Distribution (CWD).MethodsCWD distribution is developed and modified from Wigner Ville distribution (WVD). To solve the problem of cross-term interference existing in WVD there is an improved version of WVD, called Choi-Williams Distribution (CWD), which introduces the smoothing window as the kernel function and deals with the time-frequency analysis of heart sound signal.ResultsThe improved method has good performance and can be implemented simply without much increase of operation complexity.ConclusionIn this paper, 21 cases of heart sound signals are acquired from the outpatients and hospitalized patients with coronary heart diseases. The research results of 21 cases show that the CWD method can be used to analyze heart sounds. It accurately identifies the 9 cases of heart sounds of health people and 12 cases of heart sounds of patients with coronary heart disease. Besides, the CWD displays obvious differences between heart sounds of healthy people and abnormal heart sounds. The contour line of heart sounds from healthy people shows the following characteristics: concise, columnar and non-divergence; while the contour line of abnormal heart sounds is divergent and has many columnar links. These research shows that CWD method can effectively distinguish heart sounds between healthy people and patients with coronary heart disease.

Assessment of training in cardiac auscultation using a simulator / 医学教育

The use of simulators for skills training has become widespread. However, no quantitative analysis has been performed to determine whether simulation-based medical education is useful for improving the acquisition of clinical skills. The educational effect must be evaluated to further develop stimulation-based education. A seminar for cardiac auscultation was held, with the skills laboratory taking the initiative; the effectiveness was verified, and various problems were identified.1)The skills laboratory held a series of training seminars to examine the effectiveness of simulation-based education.2) Sixteen medical students participated in the seminars. One seminar lasted 120 minutes, including 60 minutes of lectures and 60 minutes of skills training. All students attended the three seminars. A questionnaire survey, a written examination, and a skills test were administered to all students three times (before, immediately after, and 5 months after the seminars).3) The students were extremely satisfied with the seminars. The students believed their cardiac auscultation skills had improved and that this improvement was still present 5 months later. After the seminars, the heart sound simulators were used more frequently than before the seminar.4) The results of skills testing after the seminars were better than those before the seminars and remained better 5 months later. However, results of a written examination 5 months after the seminars were similar to those before the seminars.5) The seminars in the skills laboratory were effective for improving students' auscultation skills and increased the effective use of mannequins in the skills laboratory.

A Novel Method for Extraction of Heart Sounds Envelope Based on Interpolation of Local Peak and Valley Points / 航天医学与医学工程

Objective To extract envelope of heart sounds exactly,for the purpose of the further analysis of its characteristics.Methods The way that envelope extraction of heart sounds based on key-points was given.The points of local peak and valley were calculated firstly,and then heart sound envelope was gotten by the interpolation of these points.Results Compared with the envelope extracted by Hilbert-transform and mathematical morphology,respectively,the outline of heart sounds was extracted more accurately,and its time-domain characters were acquired by this method.Conclusion The envelope of heart sound is extracted correctly by this method,which is useful for the further analysis.

Envelope Extraction of Heart Sounds Based on Hilbert-Huang Transform / 航天医学与医学工程

Objective Based on the analysis of time domain of heart sound with envelop to extract the envelope character of heart sounds.Methods The envelope extraction of heart sounds based on Hilbert-Huang Transform was given.Firstly,the original heart sounds signal was preprocessed by Huang Transform.Secondly,the envelope of heart sounds was got with Hilbert Transform.Results The first heart sound and the second heart sound were extracted,and all kinds of characters in time domain of heart sound were acquired more accurately.Conclusion The envelope of heart sound is extracted correctly.The foundation for further analysis of heart sounds is established.

Effect of Attractor Construction Methods to Fractal Dimension for Heart Sound Analysis / 대한의료정보학회지

Strange attractor can be constructed from time series data such as heart sound. In the areas of the recognition and diagnosis of abnormal heart sounds, signal presentation method is very useful because good features can be detected from good presentation. This paper examines efficiency in diagnosing abnormal heart sounds of the two different methods for constructing attractor. Nine different heart sounds from typical clinical conditions were used for this study. The first method was constructing attractors using original heart sounds, and the second was modifying the original sounds by autocorrelation and they were then applied to the orignal sounds as to cross correlation checks. Attractors could be constructed using signals generated by these methods, and values of fractal dimensions would then be calculated which has been a well known method to measure characteristics of attractors. The results showed that the second method appeared to provide more efficient way to correctly classify abnormal heart sounds.

Implementation of serial communication between personal computer and C8051F000 in sampling of heart sound / 医疗卫生装备

This paper analyses the requirements of serial data communication interface between upper and lower hosts in a heart sound sampling system, and then introduces the system design scheme, schematic of hardware interface and source codes of upper and lower hosts. C8051F000 and personal computer adopted as the lower host and upper host respectively, C++ Builder and Windows API functions are also used to implement the applications.

Wireless Ausculate Educational System / 대한의료정보학회지

This research is about embodiment of system to support auscultation education more effectively. Cardiac sound data that is stored to PC made many learner deliver by wireless system. For this system we developed a special radio transmitter receiver and a program to manage and remake data. Because of selecting radio system, there is no limitation of establishment and education place. also through web server database and update of data are available. For this reason we can add cardiac sound data newly in education. In case of utilizing existent electron stethoscope in auscultation education, the biggest demerit is that do not deliver sense of sound of actuality stethoscope properly. But radio receiving apparatus that we developed is no difference with sense of sound of cardiac through actuality stethoscope and did so that heighten effect of auscultation education.

Wireless Ausculate Educational System / 대한의료정보학회지

This research is about embodiment of system to support auscultation education more effectively. Cardiac sound data that is stored to PC made many learner deliver by wireless system. For this system we developed a special radio transmitter receiver and a program to manage and remake data. Because of selecting radio system, there is no limitation of establishment and education place. also through web server database and update of data are available. For this reason we can add cardiac sound data newly in education. In case of utilizing existent electron stethoscope in auscultation education, the biggest demerit is that do not deliver sense of sound of actuality stethoscope properly. But radio receiving apparatus that we developed is no difference with sense of sound of cardiac through actuality stethoscope and did so that heighten effect of auscultation education.

Design of Pure Capacitance Phonocardiogram Sensor Based on Phantom Power Supply / 医疗卫生装备

Objective To research a pure capacitance sensor for acquisition of cardiac phonocardiogram. Methods Under the phantom power supply (48V), the faint vibration signal of the heart was processed into electric signal by larger pre - treatment circuit module, shielded cable and the sensor pre-amplifier of circuit module. Results With some experiments, it can be proved that the sensor won't have affect on the sound field which frequency band under 1 000Hz and can detect the level of sound field like 20dB:30dB and 150dB or higher. Conclusion So with the sensor, the precise signal which can exactly reflect the status of patients' hearts can be detected, and it suits to work in complex condition for its high sensitivity, wide frequency band and low distortion.

Design of heart sound processing analog circuit based on the electret capacitor microphone / 医疗卫生装备

This paper designs a heart sound processing analog circuit, in which the amplification circuit, the filter circuit and the lifting of electrical level circuit are involved. It also gives a safety design problem analysis using an electret capacitor microphone to pick-up the heart sound signals. It is proved that the circuit is reliable and effective.