Detection Of Heart Sounds Research Articles

Development of explainable machine intelligence models for heart sound abnormality detection

Development of explainable machine intelligence models for heart sound abnormality detection

Heart Sound Abnormality Detection From Multi-Institutional Collaboration: Introducing a Federated Learning Framework.

Early diagnosis of cardiovascular diseases is a crucial task in medical practice. With the application of computer audition in the healthcare field, artificial intelligence (AI) has been applied to clinical non-invasive intelligent auscultation of heart sounds to provide rapid and effective pre-screening. However, AI models generally require large amounts of data which may cause privacy issues. Unfortunately, it is difficult to collect large amounts of healthcare data from a single centre. In this study, we propose federated learning (FL) optimisation strategies for the practical application in multi-centre institutional heart sound databases. The horizontal FL is mainly employed to tackle the privacy problem by aligning the feature spaces of FL participating institutions without information leakage. In addition, techniques based on deep learning have poor interpretability due to their "black-box" property, which limits the feasibility of AI in real medical data. To this end, vertical FL is utilised to address the issues of model interpretability and data scarcity. Experimental results demonstrate that, the proposed FL framework can achieve good performance for heart sound abnormality detection by taking the personal privacy protection into account. Moreover, using the federated feature space is beneficial to balance the interpretability of the vertical FL and the privacy of the data. This work realises the potential of FL from research to clinical practice, and is expected to have extensive application in the federated smart medical system.

Paramps: Convolutional neural networks based on tensor decomposition for heart sound signal analysis and cardiovascular disease diagnosis

Currently, convolutional neural networks have demonstrated outstanding efficiency in heart sound detection and automatic diagnosis of cardiovascular diseases. However, due to the non-stationary nature and complex data patterns caused by environmental noise and stethoscope differences, traditional neural networks are limited in extracting discriminative features. This article proposes a convolutional neural network based on tensor decomposition to address this issue. This model uses a convolutional neural network with four parallel structures to extract audio features of heart sound signals and introduces a tensor network to use tensor decomposition to perform low-rank approximation on the convolutional kernel, compress model parameters, reduce redundancy, and improve performance. When processing feature data, the model divides large areas of features into locally unordered small areas to achieve feature compression and reorganization, ensuring that crucial information is preserved while compressing parameters. The model can accurately capture spatial structural information and critical features by refining the matrix product state layer. Experiments were conducted on the 2016 PhysioNet/CinC Challenge and the Yaseen heart sound public dataset, the experimental results show that the proposed method has an accuracy of 96.4% and 99.2% on two datasets, specificity of 99.1% and 99.8%, demonstrating its excellent generalization ability and diagnostic accuracy.

Fed-MStacking: Heterogeneous Federated Learning With Stacking Misaligned Labels for Abnormal Heart Sound Detection.

Ubiquitous sensing has been widely applied in smart healthcare, providing an opportunity for intelligent heart sound auscultation. However, smart devices contain sensitive information, raising user privacy concerns. To this end, federated learning (FL) has been adopted as an effective solution, enabling decentralised learning without data sharing, thus preserving data privacy in the Internet of Health Things (IoHT). Nevertheless, traditional FL requires the same architectural models to be trained across local clients and global servers, leading to a lack of model heterogeneity and client personalisation. For medical institutions with private data clients, this study proposes Fed-MStacking, a heterogeneous FL framework that incorporates a stacking ensemble learning strategy to support clients in building their own models. The secondary objective of this study is to address scenarios involving local clients with data characterised by inconsistent labelling. Specifically, the local client contains only one case type, and the data cannot be shared within or outside the institution. To train a global multi-class classifier, we aggregate missing class information from all clients at each institution and build meta-data, which then participates in FL training via a meta-learner. We apply the proposed framework to a multi-institutional heart sound database. The experiments utilise random forests (RFs), feedforward neural networks (FNNs), and convolutional neural networks (CNNs) as base classifiers. The results show that the heterogeneous stacking of local models performs better compared to homogeneous stacking.

Multi-Feature Decision Fusion Network for Heart Sound Abnormality Detection and Classification.

The heart sound reflects the movement status of the cardiovascular system and contains the early pathological information of cardiovascular diseases. Automatic heart sound diagnosis plays an essential role in the early detection of cardiovascular diseases. In this study, we aim to develop a novel end-to-end heart sound abnormality detection and classification method, which can be adapted to different heart sound diagnosis tasks. Specifically, we developed a Multi-feature Decision Fusion Network (MDFNet) composed of a Multi-dimensional Feature Extraction (MFE) module and a Multi-dimensional Decision Fusion (MDF) module. The MFE module extracted spatial features, multi-level temporal features and spatial-temporal fusion features to learn heart sound characteristics from multiple perspectives. Through deep supervision and decision fusion, the MDF module made the multi-dimensional features extracted by the MFE module more discriminative, and fused the decision results of multi-dimensional features to integrate complementary information. Furthermore, attention modules were embedded in the MDFNet to emphasize the fundamental heart sounds containing effective feature information. Finally, we proposed an efficient data augmentation method to circumvent the diagnosis performance degradation caused by the lack of cardiac cycle segmentation in other end-to-end methods. The developed method achieved an overall accuracy of 94.44% and a F1-score of 86.90% on the binary classification task and a F1-score of 99.30% on the five-classification task. Our method outperformed other state-of-the-art methods and had good clinical application prospects.

Construction and validation of a method for automated time label segmentation of heart sounds.

Heart sound detection technology plays an important role in the prediction of cardiovascular disease, but the most significant heart sounds are fleeting and may be imperceptible. Hence, obtaining heart sound information in an efficient and accurate manner will be helpful for the prediction and diagnosis of heart disease. To obtain heart sound information, we designed an audio data analysis tool to segment the heart sounds from single heart cycle, and validated the heart rate using a finger oxygen meter. The results from our validated technique could be used to realize heart sound segmentation. Our robust algorithmic platform was able to segment the heart sounds, which could then be compared in terms of their difference from the background. A combination of an electronic stethoscope and artificial intelligence technology was used for the digital collection of heart sounds and the intelligent identification of the first (S1) and second (S2) heart sounds. Our approach can provide an objective basis for the auscultation of heart sounds and visual display of heart sounds and murmurs.

Federated Abnormal Heart Sound Detection with Weak to No Labels.

Cardiovascular diseases are a prominent cause of mortality, emphasizing the need for early prevention and diagnosis. Utilizing artificial intelligence (AI) models, heart sound analysis emerges as a noninvasive and universally applicable approach for assessing cardiovascular health conditions. However, real-world medical data are dispersed across medical institutions, forming "data islands" due to data sharing limitations for security reasons. To this end, federated learning (FL) has been extensively employed in the medical field, which can effectively model across multiple institutions. Additionally, conventional supervised classification methods require fully labeled data classes, e.g., binary classification requires labeling of positive and negative samples. Nevertheless, the process of labeling healthcare data is time-consuming and labor-intensive, leading to the possibility of mislabeling negative samples. In this study, we validate an FL framework with a naive positive-unlabeled (PU) learning strategy. Semisupervised FL model can directly learn from a limited set of positive samples and an extensive pool of unlabeled samples. Our emphasis is on vertical-FL to enhance collaboration across institutions with different medical record feature spaces. Additionally, our contribution extends to feature importance analysis, where we explore 6 methods and provide practical recommendations for detecting abnormal heart sounds. The study demonstrated an impressive accuracy of 84%, comparable to outcomes in supervised learning, thereby advancing the application of FL in abnormal heart sound detection.

Hilbert domain characterizations of wavelet packets for automated heart sound abnormality detection

Heart valve disease (HVD) is a common disease that affects millions of people worldwide. Early detection and treatment are essential for improving the prognosis of patients with HVD. Phonocardiogram (PCG) signals are a non-invasive and inexpensive way to assess the mechanical activity of the heart. In this study, a novel method for HVD detection using Hilbert domain mapping of wavelet packet of PCG signals is proposed. Two standard PCG databases are used to evaluate the proposed method. Packet instantaneous frequency deviation (PIFD) and packet instantaneous energy deviation (PIED) features are extracted from the PCG signals and used for classification. A support vector machine (SVM) and K-nearest neighbour (KNN) based error-correcting output code (ECOC) approach is used to handle multiclass classification and minimize classification error. The proposed method achieves an unweighted average recall (UAR) of 99.8% on database 1 and 99.32% on database 2, which outperforms other baseline methods. The results suggest that the proposed method is a promising approach for HVD detection using PCG signals.

DS-CNN: Dual-Stream Convolutional Neural Networks-Based Heart Sound Classification for Wearable Devices

Cardiovascular diseases (CVDs) is considered a serious public health problem due to the uncertainty of its onset. Consuming wearable devices have increasing popularities for healthcare monitoring, and many of them are capable of continuous monitoring and early detection of CVDs. This paper proposes a framework for heart sound detection that can be considered for deployment on smart wearable devices to screen CVDs conveniently. A dual-stream convolutional neural network (DS-CNN) is developed to detect abnormal ones from short-term heart sound recordings. Preprocessing module is first employed for noise filtering and amplitude normalization. Then short-time Fourier transform and higher-order spectral are introduced for feature extraction, whose products are subsequently fed into the DS-CNN for screening abnormal heart sound signals. Two open accessible datasets are employed for performance evaluation. The results well demonstrate the classification accuracy of the proposed DS-CNN, and also indicate its advantages for adapting to heart sound recordings collected by different equipments.

QDRJL: Quaternion dynamic representation with joint learning neural network for heart sound signal abnormal detection

At present, deep learning based heart sound diagnosis algorithms are mostly complex and large models for high accuracy, which are difficult to deploy on mobile devices due to the high number of parameters and large computational cost. The current mainstream approach for processing heart sound signals involves utilizing their Mel-frequency cepstral coefficients (MFCC) features. However, most existing methods have overlooked the multi-channel characteristics of MFCC. To address this issue, we propose a Quaternion Dynamic Representation with Joint Learning (QDRJL) neural network for learning MFCC multi-channel features. Our proposed approach combines quaternion dynamic convolution with dynamic weighting and the Quaternion Interior Learning Block (QILB). Finally, we present a global and energy joint learning branch for jointly learning MFCC features. The success of the proposed quaternion network depends on its ability to utilize the internal relations between quaternion-valued input features and the definition of the dynamic weight variables in the augmented quaternion domain. We assessed various state-of-the-art classification algorithms for detecting heart sounds and found that our proposed classifier achieved an accuracy of up to 97.2%, outperforming existing models. Our experimental evaluation, using the 2016 PhysioNet/CinC Challenge dataset, revealed that our model could reduce the number of network parameters to 25% due to quaternion properties.

Detection of valvular heart diseases combining orthogonal non-negative matrix factorization and convolutional neural networks in PCG signals

Background and objective:Valvular heart disease (VHD) is associated with elevated mortality rates. Although transthoracic echocardiography (TTE) is the gold standard detection tool, phonocardiography (PCG) could be an alternative as it is a cost-effective and noninvasive method for cardiac auscultation. Many researchers have dedicated their efforts to improving the decision-making process and developing robust and precise approaches to assist physicians in providing reliable diagnoses of VHD. Methods:This research proposes a novel approach for the detection of anomalous valvular heart sounds from PCG signals. The proposed approach combines orthogonal non-negative matrix factorization (ONMF) and convolutional neural network (CNN) architectures in a three-stage cascade. The aim of the proposal is to improve the learning process by identifying the optimal ONMF temporal or spectral patterns for accurate detection. In the first stage, the time–frequency representation of the input PCG signal is computed. Next, band-pass filtering is performed to locate the spectral range that is most relevant for the presence of such cardiac abnormalities. In the second stage, the temporal and spectral cardiac structures are extracted using the ONMF approach. These structures are utilized in the third stage and fed into the CNN architecture to detect abnormal heart sounds. Results:Several state-of-the-art CNN architectures, such as LeNet5, AlexNet, ResNet50, VGG16 and GoogLeNet, have been evaluated to determine the effectiveness of using ONMF temporal features for VHD detection. The results reveal that the integration of ONMF temporal features with a CNN classifier significantly improve VHD detection. Specifically, the proposed approach achieves an accuracy improvement of approximately 45% when ONMF spectral features are used and 35% when time–frequency features from the short-time Fourier transform (STFT) spectrogram are used. Additionally, feeding ONMF temporal features into low-complexity CNN architectures yields competitive results comparable to those obtained with complex architectures. Conclusions:The temporal structure factorized by ONMF plays a critical role in distinguishing between normal heart sounds and abnormal heart sounds since the repeatability of normal heart cycles is disrupted by the presence of cardiac abnormalities. Consequently, the results highlight the importance of appropriate input data representation in the learning process of CNN models in the biomedical field of valvular heart sound detection.

A wearable nanoscale heart sound sensor based on P(VDF-TrFE)/ZnO/GR and its application in cardiac disease detection.

This paper describes a method for preparing flexible composite piezoelectric nanofilms of P(VDF-TrFE)/ZnO/graphene using a high-voltage electrospinning method. Composition and β-phase content of the piezoelectric composite films were analyzed using X-ray diffraction. The morphology of the composite film fibers was observed through scanning electron microscopy. Finally, the P(VDF-TrFE)/ZnO/graphene composite film was encapsulated in a sandwich-structure heart sound sensor, and a visual heart sound acquisition and classification system was designed using LabVIEW. A heart sound classification model was trained based on a fine K-nearest neighbor classification algorithm to predict whether the collected heart sounds are normal or abnormal. The heart sound detection system designed in this paper can collect heart sound signals in real time and predict whether the heart sounds are normal or abnormal, providing a new solution for the diagnosis of heart diseases.

Less is More: A Novel Feature Extraction Method for Heart Sound Classification via Fractal Transformation.

Cardiovascular diseases (CVDs) are the leading cause of death globally. Heart sound signal analysis plays an important role in clinical detection and physical examination of CVDs. In recent years, auxiliary diagnosis technology of CVDs based on the detection of heart sound signals has become a research hotspot. The detection of abnormal heart sounds can provide important clinical information to help doctors diagnose and treat heart disease. We propose a new set of fractal features - fractal dimension (FD) - as the representation for classification and a Support Vector Machine (SVM) as the classification model. The whole process of the method includes cutting heart sounds, feature extraction, and classification of abnormal heart sounds. We compare the classification results of the heart sound waveform (time domain) and the spectrum (frequency domain) based on fractal features. Finally, according to the better classification results, we choose the fractal features that are most conducive for classification to obtain better classification performance. The features we propose outperform the widely used features significantly (p < .05 by one-tailed z-test) with a much lower dimension.Clinical relevance-The heart sound classification model based on fractal provides a new time-frequency analysis method for heart sound signals. A new effective mechanism is proposed to explore the relationship between the heart sound acoustic properties and the pathology of CVDs. As a non-invasive diagnostic method, this work could supply an idea for the preliminary screening of cardiac abnormalities through heart sounds.

Heartbeat Cardiac Sounds Analysis

Phonocardiography provides the clinician with a complementary tool to record the heart sounds heard during auscultation. This paper presents an algorithm for the detection of heart sounds (the first and second sounds, S1 and S2) and heart murmurs. Secondly the heartbeat cardiac sounds represented by the phonocardiogram (PCG) signal once segmented is one of the useful approaches to explore cardiac activity and extract many features to help researchers develop techniques that can be used for the medical treatment of several heart diseases. For people affected by a heart activity problem, it is a serious health problem that requires special care. In this paper, importance is given to heart murmurs and their severity to show their impact on heart rate. Heart murmurs are very widespread pathologies in the world and depending on their severity they could constitute. This paper is concerned to the segmentation of heart sounds by using state of art Hidden Markov Models technology which used to extract a smooth envelogram which enable us to apply the tests necessary for temporal localization of heart sounds and heart murmurs.

Wearable pulmonary monitoring system with integrated functional lung imaging and chest sound recording: a clinical investigation in healthy subjects

Objective. Current wearable respiratory monitoring devices provide a basic assessment of the breathing pattern of the examined subjects. More complex monitoring is needed for healthcare applications in patients with lung diseases. A multi-sensor vest allowing continuous lung imaging by electrical impedance tomography (EIT) and auscultation at six chest locations was developed for such advanced application. The aims of our study were to determine the vest’s capacity to record the intended bio-signals, its safety and the comfort of wearing in a first clinical investigation in healthy adult subjects. Approach. Twenty subjects (age range: 23–65 years) were studied while wearing the vests during a 14-step study protocol comprising phases of quiet and deep breathing, slow and forced full expiration manoeuvres, coughing, breath-holding in seated and three horizontal postures. EIT, chest sound and accelerometer signals were streamed to a tablet using a dedicated application and uploaded to a back-end server. The subjects filled in a questionnaire on the vest properties using a Likert scale. Main results. All subjects completed the full protocol. Good to excellent EIT waveforms and functional EIT images were obtained in 89% of the subjects. Breathing pattern and posture dependent changes in ventilation distribution were properly detected by EIT. Chest sounds were recorded in all subjects. Detection of audible heart sounds was feasible in 44%–67% of the subjects, depending on the sensor location. Accelerometry correctly identified the posture in all subjects. The vests were safe and their properties positively rated, thermal and tactile properties achieved the highest scores. Significance. The functionality and safety of the studied wearable multi-sensor vest and the high level of its acceptance by the study participants were confirmed. Availability of personalized vests might further advance its performance by improving the sensor-skin contact.

HS-Vectors: Heart Sound Embeddings for Abnormal Heart Sound Detection Based on Time-Compressed and Frequency-Expanded TDNN With Dynamic Mask Encoder.

In recent years, auxiliary diagnosis technology for cardiovascular disease based on abnormal heart sound detection has become a research hotspot. Heart sound signals are promising in the preliminary diagnosis of cardiovascular diseases. Previous studies have focused on capturing the local characteristics of heart sounds. In this paper, we investigate a method for mapping heart sound signals with complex patterns to fixed-length feature embedding called HS-Vectors for abnormal heart sound detection. To get the full embedding of the complex heart sound, HS-Vectors are obtained through the Time-Compressed and Frequency-Expanded Time-Delay Neural Network(TCFE-TDNN) and the Dynamic Masked-Attention (DMA) module. HS-Vectors extract and utilize the global and critical heart sound characteristics by masking out irreverent information. Based on the TCFE-TDNN module, the heart sound signal within a certain time is projected into fixed-length embedding. Then, with a learnable mask attention matrix, DMA stats pooling aggregates multi-scale hidden features from different TCFE-TDNN layers and masks out irrelevant frame-level features. Experimental evaluations are performed on a 10-fold cross-validation task using the 2016 PhysioNet/CinC Challenge dataset and the new publicly available pediatric heart sound dataset we collected. Experimental results demonstrate that the proposed method excels the state-of-the-art models in abnormality detection.

Exploring interpretable representations for heart sound abnormality detection

The advantages of non-invasive, real-time and convenient, computer audition-based heart sound abnormality detection methods have increasingly attracted efforts among the community of cardiovascular diseases. Time–frequency analyses are crucial for computer audition-based applications. However, a comprehensive investigation on discovering an optimised way for extracting time–frequency representations from heart sounds is lacking until now. To this end, we propose a comprehensive investigation on time–frequency methods for analysing the heart sound, i.e., short-time Fourier transformation, Log-Mel transformation, Hilbert–Huang transformation, wavelet transformation, Mel transformation, and Stockwell transformation. The time–frequency representations are automatically learnt via pre-trained deep convolutional neural networks. Considering the urgent need of smart stethoscopes for high robust detection algorithms in real environment, the training, verification, and testing sets employed in the extensive evaluation are subject-independent. Finally, to further understand the heart sound-based digital phenotype for cardiovascular diseases, explainable artificial intelligence approaches are used to reveal the reasons for the performance differences of four time–frequency representations in heart sound abnormality detection. Experimental results show that Stockwell transformation can beat other methods by reaching the highest overall score of 65.2%. The interpretable results demonstrate that Stockwell transformation does not only present more information for heart sounds, but also provides a certain noise robustness. Besides, the considered fine-tuned deep model brings an improvement of the mean accuracy over the previous state-of-the-art results by 9.0% in subject-independent testing.

Abnormal heart sound detection from unsegmented phonocardiogram using deep features and shallow classifiers

Abnormal heart sound detection from unsegmented phonocardiogram using deep features and shallow classifiers

Heartbeat sound classification using a hybrid adaptive neuro-fuzzy inferences system (ANFIS) and artificial bee colony.

Cardiovascular disease is one of the main causes of death worldwide which can be easily diagnosed by listening to the murmur sound of heartbeat sounds using a stethoscope. The murmur sound happens at the Lub-Dub, which indicates there are abnormalities in the heart. However, using the stethoscope for listening to the heartbeat sound requires a long time of training then only the physician can detect the murmuring sound. The existing studies show that young physicians face difficulties in this heart sound detection. Use of computerized methods and data analytics for detection and classification of heartbeat sounds will improve the overall quality of sound detection. Many studies have been worked on classifying the heartbeat sound; however, they lack the method with high accuracy. Therefore, this research aims to classify the heartbeat sound using a novel optimized Adaptive Neuro-Fuzzy Inferences System (ANFIS) by artificial bee colony (ABC). The data is cleaned, pre-processed, and MFCC is extracted from the heartbeat sounds. Then the proposed ABC-ANFIS is used to run the pre-processed heartbeat sound, and accuracy is calculated for the model. The results indicate that the proposed ABC-ANFIS model achieved 93% accuracy for the murmur class. The proposed ABC-ANFIS has higher accuracy in compared to ANFIS, PSO ANFIS, SVM, KSTM, KNN, and other existing studies. Thus, this study can assist physicians to classify heartbeat sounds for detecting cardiovascular disease in the early stages.

Le-LWTNet: A Learnable Lifting Wavelet Convolutional Neural Network for Heart Sound Abnormality Detection

Automatic heart sound abnormality detection plays a vital role in the preliminary diagnosis of cardiovascular diseases. Many handcraft-designed or learning-based methods have been proposed in recent years. However, due to the influence of environment, the divergence of different stethoscopes, and data collection protocol, the pattern of heart sound signals are so complex that fixed pattern feature extraction or learning features directly from the signal can not enough lead to final accurate classification. For this issue, a learnable lifting wavelet transform block (Le-LWT), which embeds the trainable convolutional neural network (CNN) into the lifting wavelet transform, is proposed in this paper. Le-LWT can utilize the non-linear learning ability of CNN while maintaining the multi-resolution time-frequency analysis ability of wavelet transform, as well as more interpretation than the deep networks designed as black boxes. Based on Le-LWT module, we propound an end-to-end Le-LWTNet that has stronger non-linear characterization capabilities and few parameters for automatic abnormality detection of the heart sound. Experimental evaluations are performed on a 10-fold cross-validation task using the 2016 PhysioNet/CinC Challenge dataset and the new publicly available pediatric heart sound dataset we collected. Results demonstrate that the proposed method excels the state-of-the-art models both in abnormality detection and parameter consumption. Moreover, the proposed method can give an interpretation of the current classification results, which will help doctors do a second review.