Automatic Classification of Periodic Heart Sounds Using Convolutional Neural Network

Heart sounds convey important information regarding potential heart diseases. Currently, heart sound classification attracts many researchers from the fields of telemedicine, digital signal processing, and machine learning—among others—mainly to identify cardiac pathology as quickly as possible. This article proposes chaogram as a new transform to convert heart sound signals to colour images. In the proposed approach, the output image is, therefore, the projection of the reconstructed phase space representation of the phonocardiogram (PCG) signal on three coordinate planes. This has two major benefits: (1) it makes possible to apply deep convolutional neural networks to heart sounds and (2) it is also possible to employ a transfer learning scheme by converting a heart sound signal to an image. The performance of the proposed approach was verified on the PhysioNet dataset. Due to the imbalanced data on this dataset, it is common to assess the results quality using the average of sensitivity and specificity, which is known as score, instead of accuracy. In this study, the best results were achieved using the model, which achieved a score of 88.06%.

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.

Analysis of PCG signals using quality assessment and homomorphic filters for localization and classification of heart sounds

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

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.

Heart disease is a major problem in most deaths. To conquer this situation, heartbeat sound analysis is a convenient method for diagnosing heart disease. Heartbeat sound classification remains a challenging problem in heart sound division and feature extraction. A stethoscope is a medical device widely used by physicians to listen to the heartbeat. An acoustic stethoscope operates on the chest piece to the ears of the listener. The main problem is in listening to heart sounds that the low signal level and are difficult to be analyzed. Adding electronic circuitry and software to acoustic stethoscopes will strengthen the heart rate signal and can minimize error analysis of the state of the patient's heart. Machine learning is used to efficiently analyze and classify heart sounds. Convolutional Neural Network (CNN) models and Support Vector Machine (SVM) with feature extractors were effective methods and were used in this research. First, the Phonocardiogram (PCG) files are fragmented into pieces of equivalent length. Then, we convert the PCG files to a spectrogram. The spectrogram images are fed into a convolutional neural network and support vector machine. The best result is using an Inception V3 model with the CNN classifier which has an accuracy of 0.909, with 0.948 sensitivity and 0.869 specificity.

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 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.

In this work, we present a method to separate aortic (A2) and pulmonary (P2) components from second heart sounds (S2). The proposed approach captures the different dynamical behavior of A2 and P2 components via a joint Gaussian mixture model, which is then used to perform separation via a closed-form conditional mean estimator.The proposed approach is tested over synthetic heart sounds and it is shown guarantee a reduction of approximately 25% of the normalized root mean-squared error incurred in signal separation, with respect to a previously presented approach in the literature.

Heart hemodynamic status and detection of a cardiovascular disease can be evaluated by analyzing and visualizing the heart waveform through graphs called the Phonocardiogram (PCG). The normal sounds of the heart generate signals that are in the audible frequency range of the human ear. Due to the significance of cardiac auscultation for recognizing pathological cardiac status, there has been special interest in automating the classification of heart sounds in the past years. The objective of this research is to present an automatic classification algorithm for anomaly (normal vs. abnormal heart status) of PCG recordings. For this purpose, distinctive time and frequency features are extracted out of heart sound signals to build a learning model using random forest. The accuracy of the proposed algorithm is about 12% better than state of the art.

Analyzing the condition and function of the heart is very important because cardiovascular diseases (CVDs) are responsible for high mortality rates worldwide and can lead to strokes and heart attacks; thus, early diagnosis and treatment are important. Phonocardiogram (PCG) signals can be used to analyze heart rate characteristics to detect heart health and detect heart-related diseases. In this paper, we propose a method for designing using wavelet analysis techniques and an ensemble of deep learning models from phonocardiogram (PCG) for heart sound classification. For this purpose, we use wavelet scattering transform (WST) and continuous wavelet transform (CWT) as the wavelet analysis approaches for 1D-convolutional neural network (CNN) and 2D-CNN modeling, respectively. These features are insensitive to translations of the input on an invariance scale and are continuous with respect to deformations. Furthermore, the ensemble model is combined with 1D-CNN and 2D-CNN. The proposed method consists of four stages: a preprocessing stage for dividing signals at regular intervals, a feature extraction stage through wavelet scattering transform (WST) and continuous wavelet transform (CWT), a design stage of individual 1D-CNN and 2D-CNN, and a classification stage of heart sound by the ensemble model. The datasets used for the experiment were the PhysioNet/CinC 2016 challenge dataset and the PASCAL classifying heart sounds challenge dataset. The performance evaluation is performed by precision, recall, F1-score, sensitivity, and specificity. The experimental results revealed that the proposed method showed good performance on two datasets in comparison to the previous methods. The ensemble method of the proposed deep learning model surpasses the performance of recent studies and is suitable for predicting and diagnosing heart-related diseases by classifying heart sounds through phonocardiogram (PCG) signals.

An early detection of heart disease can save lives, caution individuals and also help to determine the type of treatment to be given to the patients. The first test of diagnosing a heart disease is through auscultation - listening to the heart sounds. The interpretation of heart sounds is subjective and requires a professional skill to identify the abnormalities in these sounds. A medical practitioner uses a stethoscope to perform an initial screening by listening for irregular sounds from the patient's chest. Later, echocardiography and electrocardiography tests are taken for further diagnosis. However, these tests are expensive and require specialized technicians to operate. A simple and economical way is vital for monitoring in homecare or rural hospitals and urban clinics. This dissertation is focused on developing a patient-centered device for initial screening of the heart sounds that is both low cost and can be used by the users on themselves, and later share the readings with the healthcare providers. An innovative mobile health service platform is created for analyzing and classifying heart sounds. Certain properties of heart sounds have to be evaluated to identify the irregularities such as the number of heart beats and gallops, intensity, frequency, and duration. Since heart sounds are generated in low frequencies, human ears tend to miss certain sounds as the high frequency sounds mask the lower ones. Therefore, this dissertation provides a solution to process the heart sounds using several signal processing techniques, identifies the features in the heart sounds and finally classifies them. This dissertation enables remote patient monitoring through the integration of advanced wireless communications and a customized low-cost stethoscope. It also permits remote management of patients' cardiac status while maximizing patient mobility. The smartphone application facilities recording, processing, visualizing, listening, and classifying heart sounds. The application also generates an electronic medical record, which is encrypted using the efficient elliptic curve cryptography and sent to the cloud, facilitating access to physicians for further analysis. Thus, this dissertation results in a patient-centered device that is essential for initial screening of the heart sounds, and could be shared for further diagnosis with the medical care practitioners.

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.

In this study, classification of Normal and Extra systolic heart sounds (HS) have been carried out using in PASCAL Heart Sounds (HS) data base. The extrasystole is the HS that is produced by performing an extra beat in each heart cycle, unlike the heartbeat normal cycle. It can be felt by people as palpitations. Occurrence of these sounds in certain age groups may be the indication of tachycardia. In this study, firstly HS have been normalized at first. Then an elliptic filter has used for noise reduction. HS features have been obtained using Mel-Frequency Cepstrum Coefficients. These features have classified using Artificial Neural Network. In this study, 45 extra systoles heart sounds have used. 30 of them have been used as training data for classification while remaining 15 ones have been used for the test. Certainty, sensitivity, accuracy values have been calculated using confusion matrix. Classification success has been calculated as 90%.

Background: The merging of machine learning and deep learning approaches offers a viable route for improving breast cancer prediction in this era of advanced technology and data-driven healthcare. This study focused on the use of supervised machine learning and deep learning algorithms for breast cancer prediction using Wisconsin breast cancer dataset. Methods: The features from this dataset were computed from a digitized image of a fine needle aspirate (FNA) of a breast mass. Supervised machine learning algorithms, such as logistic regression, random forests, and support vector machines were compared with deep learning algorithms like convolutional and recurrent neural networks (RNN and CNN) for the prediction of breast cancer. The techniques combine clinical, genomic, and image-based data, that both aid in early diagnosis and individualized treatment suggestions. Results: The results of model comparison were very promising, with models obtaining excellent accuracy, sensitivity, and specificity in breast cancer diagnosis. The study used a pair plot and different classifiers with their accuracy scores on test dataset to determine which machine learning model was most suitable based on the relationship of variables represented in the plot. Support vector machine (SVM) has the highest accuracy of 98.8% and Artificial Neural Network (ANN) has lowest accuracy of 95.80% using confusion matrix and the accuracy metric. Conclusion: The study revealed that Support Vector Machine (SVM) has the highest prediction capability for Breast Cancer using Supervised Machine Learning and Deep Leaning. The new classifier performed better than the existing breast cancer prediction models in the literature.