Feature extraction and recognition methods based on phonocardiogram

Most of the causes of death are related to cardiovascular disease. Heart sound classification plays a key role in the early detection of cardiovascular disease. The distinction between normal and abnormal heart sounds is not obvious, making heart sound classification a challenging task. This paper proposes a method based on statistical analysis and feature engineering to analyze the features extracted from heart sound signals. The discriminative features are selected and input into the classifier to classify the heart sound. While ensuring accuracy, the method reduces the scale of the input data and computational time for classification. The selected distinguishable features achieved an accuracy of 96.5 % for the classification of abnormal and normal heart sounds. The experimental results show that the selected features can achieve a high accuracy rate in the classification of heart sound, which is suitable for real-time applications.

Heart sounds classification plays an important role in cardiovascular disease detection. Currently, deep learning methods for heart sound classification with heavy parameters consumption cannot be deployed in environments with limited memory and computational budgets. Besides, de-noising of heart sound signals (HSSs) can affect accuracy of heart sound classification, because erroneous removal of meaningful components may lead to heart sound distortion. In this paper, an automated heart sound classification method using adaptive wavelet threshold and 1D LDCNN (One-dimensional Lightweight Deep Convolutional Neural Network) is proposed. In this method, we exploit WT (Wavelet Transform) with an adaptive threshold to de-noise heart sound signals (HSSs). Furthermore, we utilize 1D LDCNN to realize automatic feature extraction and classification for de-noised heart sounds. Experiments on PhysioNet/CinC 2016 show that our proposed method achieves the superior classification results and excels in consumption of parameter comparing to state-of-the-art methods.

The heart sound signal is one of the signals that reflect the health of the heart. Research on the heart sound signal contributes to the early diagnosis and prevention of cardiovascular diseases. As a commonly used deep learning network, convolutional neural network (CNN) has been widely used in images. In this paper, the method of analyzing heart sound through using CNN has been studied. Firstly, the original data set was preprocessed, and then the heart sounds were segmented on U-net, based on the deep CNN. Finally, the classification of heart sounds was completed through CNN. The data from 2016 PhysioNet/CinC Challenge was utilized for algorithm validation, and the following results were obtained. When the heart sound segmented, the overall accuracy rate was 0.991, the accuracy of the first heart sound was 0.991, the accuracy of the systolic period was 0.996, the accuracy of the second heart sound was 0.996, and the accuracy of the diastolic period was 0.997, and the average accuracy rate was 0.995; While in classification, the accuracy was 0.964, the sensitivity was 0.781, and the specificity was 0.873. These results show that deep learning based on CNN shows good performance in the segmentation and classification of the heart sound signal.

This study focuses on the evaluation of cardiotoxicity during radiotherapy for breast cancer. The background of the study is that radiotherapy is widely used in the treatment of breast cancer but may cause cardiotoxicity, especially radiation myocarditis, which poses a threat to the long-term quality of life of patients. The subject of this study is the monitoring of heart health using a flexible patch heart sound sensor. The research methods include selecting radiotherapy patients as research objects, collecting heart sound signals and using Matlab software for feature extraction, and exploring the relationship between heart sound signals and heart function through statistical analysis. The results show that the heart sound signals of patients undergo important changes during radiotherapy, and indicators such as heart rate, heart sound intensity, and heart sound interval can be used to evaluate heart function. Moreover, the heart sound classification model based on the KNN classification algorithm can accurately identify abnormal heart sounds, providing an effective guarantee for predicting radiation myocarditis. The flexible patch heart sound sensor has an important value in the evaluation of cardiotoxicity in breast cancer radiotherapy, which can effectively predict the risk of heart injury and provide an important reference for clinical decision-making.

Biometric recognition refers to the automatic recognition of individuals based on their physiological or behavioral characteristics. This paper presents a new biometric identification technique based on heart sounds. It is a signal of benefits recognition by analyzing the basic characteristics of heart sound. For first heart sound signal s1, secondly heart sound signal s2, their characteristic parameters are extracted by the independent sub-function and wavelet transform. And the heart sound cycle-power-frequency drawing (CPFD) is used to achieve identity recognition of single channel heart sound signal. The data of multi-feature extraction was processed based on the data layer fusion and improved D-S information fusion method. The results of practical experiments show the effectiveness of the heart sound identification technology which has a promising future.

CardioPHON: Quality assessment and self-supervised pretraining for screening of cardiac function based on phonocardiogram recordings

We purpose a novel method that combines modified frequency slice wavelet transform (MFSWT) and convolutional neural network (CNN) for classifying normal and abnormal heart sounds. A hidden Markov model is used to find the position of each cardiac cycle in the heart sound signal and determine the exact position of the four periods of S1, S2, systole, and diastole. Then the one-dimensional cardiac cycle signal was converted into a two-dimensional time-frequency picture using the MFSWT. Finally, two CNN models are trained using the aforementioned pictures. We combine two CNN models using sample entropy (SampEn) to determine which model is used to classify the heart sound signal. We evaluated our model on the heart sound public dataset provided by the PhysioNet Computing in Cardiology Challenge 2016. Experimental classification performance from a 10-fold cross-validation indicated that sensitivity (Se), specificity (Sp) and mean accuracy (MAcc) were 0.95, 0.93, and 0.94, respectively. The results showed the proposed method can classify normal and abnormal heart sounds with efficiency and high accuracy. Graphical abstract Block diagram of heart sound classification.

Heart sound is a kind of non-stationary and nonlinear signal with typical chaotic characteristics. As everyone knows, exercise and age can influence heart function, will they also influence the chaotic characteristics of heart sound? This problem is studied based on the correlation dimension and Kolmogorov entropy. Firstly, discuss calculation methods of correlation dimension and K entropy of heart sound signal. Secondly, introduce the experimental methods, and use a self-made wireless heart sound acquisition device to collect heart sound signals in different move status and at different ages. The effects of exercise on correlation dimension and K entropy were discussed in three status of rest, in and after exercise. Then carry out phase plane analysis of heart sound signals, and analyze change rules of correlation dimension of heart sound signals with aging. Finally, the prediction model of heart sound is proposed according to the relationship between age and correlation dimension. The results show that: (1) There were significant differences in correlation dimension and K entropy of heart sound signals under different move status. (2) Affected by cardiac inefficiency and pathological murmurs, correlation dimensions of heart sound decrease with the increases of age. Therefore, senescence is a process in which the chaotic characteristics of heart sounds gradually change to zero. (3) According to the prediction model of heart sounds, we can try to obtain heart sounds for many years to come, which can be used to assist in predicting the risk of human-related diseases in a certain sense.

Heart sounds are critical for early detection of cardiovascular diseases, yet existing studies mostly focus on traditional signal segmentation, feature extraction, and shallow classifiers, which often fail to sufficiently capture the dynamic and nonlinear characteristics of heart sounds, limit recognition of complex heart sound patterns, and are sensitive to data imbalance, resulting in poor classification performance. To address these limitations, this study proposes a novel heart sound classification method that integrates improved Mel-frequency cepstral coefficients (MFCC) for feature extraction with a convolutional neural network (CNN) and a deep Transformer model. In the preprocessing stage, a Butterworth filter is applied for denoising, and continuous heart sound signals are directly processed without segmenting the cardiac cycles, allowing the improved MFCC features to better capture dynamic characteristics. These features are then fed into a CNN for feature learning, followed by global average pooling (GAP) to reduce model complexity and mitigate overfitting. Lastly, a deep Transformer module is employed to further extract and fuse features, completing the heart sound classification. To handle data imbalance, the model uses focal loss as the objective function. Experiments on two public datasets demonstrate that the proposed method performs effectively in both binary and multi-class classification tasks. This approach enables efficient classification of continuous heart sound signals, provides a reference methodology for future heart sound research for disease classification, and supports the development of wearable devices and home monitoring systems.

Analysis of heart sound signals for automatic segmentation and classification has revealed in recent decades that it has the potential to detect pathology accurately in clinical applications. Various audio signal processing techniques have been used to reduce the subjectivity of heart sound analysis. This study aims to classify normal and abnormal heart sound signals. The feature extraction process was optimized by EMD and calculated using five first-order statistical parameters: mean, variance, kurtosis, skewness, and entropy. The classification system is optimized with a mutual information algorithm to select traits that can significantly improve system performance. In addition, the selection of the optimal system configuration also includes the k-fold cross-validation and kNN methods with k values ​​and the proper distance type. Based on the test results, the highest accuracy of 98.2% was obtained when the value of k = 1 and the type of cosine distance on kNN with a five-fold cross-validation system evaluation model.

IntroductionHeart sound signal is an important physiological signal of human body, and the identification and research of heart sound signal is of great significance.MethodsFor abnormal heart sound signal recognition, an abnormal heart sound recognition system, combining hidden semi-Markov models (HSMM) with deep neural networks, is proposed. Firstly, HSMM is used to build a heart sound segmentation model to accurately segment the heart sound signal, and then the segmented heart sound signal is subjected to feature extraction. Finally, the trained deep neural network model is used for recognition.ResultsCompared with other methods, this method has a relatively small amount of input feature data and high accuracy, fast recognition speed.DiscussionHSMM combined with deep neural network is expected to be deployed on smart mobile devices for telemedicine detection.

Heart sounds are the most significant parameter that can be used to represent the heart condition. However, the original heart sounds signal such as PCG still contained some unwanted information while the recording process happens that becomes a noise or extra sounds that will influence inside of the signal. This paper present signal processing technique and data analysis to suppress any noise in the recorded signal and classified it into two groups which are normal heart sounds and pathological heart sounds that contain Ventricular Septal Defect (VSD) inside. There are some steps in signal processing, first the signal will be processed through preprocessing technique which consists of the filter and smoothing by using IIR high pass filter in LabVIEW, secondly segmentation and feature extraction that is used to recognize the different parameter on each signal, and finally we use Support Vector Machine (SVM) to classify the heart sound signals. The result of the method capable to separate and classify the normal and pathological heart sound signals.

The main objective is to develop a novel method for the heart sound analysis for the detection of cardiovascular diseases. It can be considered as one of the important phases in the automated analysis of PCG signals. Heart sounds carry information about mechanical activity of the cardiovascular system. This information includes specific physiological state of the subject and the short term variability related to the respiratory cycle. The interpretation of sounds and extraction of changes in the physiological state while maintaining the short term variability are still an open problem and is subject of this paper. The system deals with the process of de-noising of the heart sound signal(PCG) and the signal is decomposed into several sub-bands and the de-noised heart sound signal is segmented into the basic heart sounds S1 and S2, along with the systolic and diastolic interval.. Also, the ECG signal is de-noised. Meanwhile, the R-peaks are identified from the ECG signal and RR interval is obtained. Extraction of features are done from both the heart sound signal and the ECG signal. From the features, the R-peaks are identified from the ECG signal and RR interval is obtained. The attribute selection is to find the best attribute values that can be used for the classification process. Finally, using classification technique, cardiac diseases are detected. This work is implemented by using MATLAB software.

The majority of deaths today are due to heart diseases. Early diagnosis of heart diseases will lead to early initiation of the treatment process. Therefore, computer-aided systems are of great importance. In this study, heart sounds were used for the early diagnosis and treatment of heart diseases. Diagnosing heart sounds provides important information about heart diseases. Therefore, a hybrid model was developed in the study. In the developed model, first of all, spectrograms were obtained from audio signals with the Mel-spectrogram method. Then, the interpolation method was used to train the developed model more accurately and with more data. Unlike other data augmentation methods, the interpolation method produces new data. The feature maps of the data were obtained using the Darknet53 architecture. In order for the developed model to work faster and more effectively, the feature map obtained using the Darknet53 architecture has been optimized using the Relief feature selection method. Finally, the obtained feature map was classified in different classifiers. While the accuracy value of the developed model in the first dataset was 99.63%, the accuracy rate in the second dataset was 97.19%. These values show that the developed model can be used to classify heart sounds.

The paper is focused on analyzing 20 heart sound samples, including patients with coronary disease and healthy persons. Short Time Flourier Transform (STFT) is adopted for the analysis, since Flourier Transform (FT) has its limitations as a tool in analyzing heart sound signals which as biological signals are weak and nonstable. The study demonstrates that the heart sounds of patients with coronary disease, including those with atrial septal defects, exhibit markedly different characteristics from those of healthy persons. Specifically, the first heart sound (SI) is closely followed by a systolic murmur of high frequency; a persistent splitting of the second heart sound (S2) is observed, which is accompanied by a diastolic murmur. It is therefore concluded that the frequency changes and structure of cardiac sounds are mainly related to the health of the heart and basically free from the influences of individual differences.