Time-frequency characteristics of the vibrations underlying the first fetal heart sound: a preliminary study.

This work studied, for the first time, the time-frequency characteristics of the vibrations underlying the first fetal heart sound (S1). To this end, the continuous wavelet transform was used to produce time-energy and time-frequency representations of S1 from where five vibrations were studied by their timing, energy, and frequency characteristics in three gestational age groups (early, G1, preterm, G2, and term, G3). Results on a dataset of 1111 S1s (9 phonocardiograms between 33 and 40 weeks) indicate that such representations uncovered a set of five well-defined, non-overlapped, and large-energy vibrations whose features presented interesting behaviors. Thus, for each group, while the timing characteristics of the five vibrations were likely to be statically different, their frequencies were similar. Also, the energies of the vibrations were likely to be different only in G2 and G3. Alternatively, while the frequencies and energies of each vibration were likely to statistically change among groups (excluding the energy of the third vibration), the timings were more likely to change only from G1 to G2 and from G2 to G3. Therefore, this methodology seems suitable to detect and study the generating vibrations of S1. Future work will test the correlation between these vibrations and the valvular events.

CNN-Based Heart Sound Classification with an Imbalance-Compensating Weighted Loss Function.

Heart sound auscultation is an effective method for early-stage diagnosis of heart disease. The application of deep neural networks is gaining increasing attention in automated heart sound classification. This paper proposes deep Convolutional Neural Networks (CNNs) to classify normal/abnormal heart sounds, which takes two-dimensional Mel-scale features as input, including Mel frequency cepstral coefficients (MFCCs) and the Log Mel spectrum. We employ two weighted loss functions during the training to mitigate the class imbalance issue. The model was developed on the public PhysioNet/Computing in Cardiology Challenge (CinC) 2016 heart sound database. On the considered test set, the proposed model with Log Mel spectrum as features achieves an Unweighted Average Recall (UAR) of 89.6%, with sensitivity and specificity being 89.5% and 89.7% respectively. This work proposes a CNN-based model to enable automated heart sound classification, which can provide auxiliary assistance for heart auscultation and has the potential to screen for heart pathologies in clinical applications at a relatively low cost.

Abdominal cardiovascular sound recording and analysis using cardio-microphones.

In view of using abdominal microphones for fetal heart rate (FHR) monitoring, the analysis of the obtained abdominal phonocardiogram (PCG) signals is complex due to many interferential noises including blood flow sounds. In order to improve the understanding of abdominal phonocardiography, a preliminary study was conducted in one healthy volunteer and designed to characterize the PCG signals all over the abdomen. Acquisitions of PCG signals in different abdominal areas were realized, synchronously with one thoracic PCG signal and one electrocardiogram signal. The analysis was carried out based on the temporal behavior, amplitude and mean pattern of each signal. The synchronized rhythmic signature of each signal confirms that the PCG signals obtained on the abdominal area are resulting from heart function. However, the abdominal PCG patterns are totally different from the thoracic PCG one, suggesting the recording of vascular blood flow sounds on the abdomen instead of cardiac valve sounds. Moreover, the abdominal signal magnitude depends on the sensor position and therefore to the size of the underlying vessel. The sounds characterization of abdominal PCG signals could help improving the processing of such signals in the purpose of FHR monitoring.

A comparative study of single-channel signal processing methods in fetal phonocardiography.

Fetal phonocardiography is a non-invasive, completely passive and low-cost method based on sensing acoustic signals from the maternal abdomen. However, different types of interference are sensed along with the desired fetal phonocardiography. This study focuses on the comparison of fetal phonocardiography filtering using eight algorithms: Savitzky-Golay filter, finite impulse response filter, adaptive wavelet transform, maximal overlap discrete wavelet transform, variational mode decomposition, empirical mode decomposition, ensemble empirical mode decomposition, and complete ensemble empirical mode decomposition with adaptive noise. The effectiveness of those methods was tested on four types of interference (maternal sounds, movement artifacts, Gaussian noise, and ambient noise) and eleven combinations of these disturbances. The dataset was created using two synthetic records r01 and r02, where the record r02 was loaded with higher levels of interference than the record r01. The evaluation was performed using the objective parameters such as accuracy of the detection of S1 and S2 sounds, signal-to-noise ratio improvement, and mean error of heart interval measurement. According to all parameters, the best results were achieved using the complete ensemble empirical mode decomposition with adaptive noise method with average values of accuracy = 91.53% in the detection of S1 and accuracy = 68.89% in the detection of S2. The average value of signal-to-noise ratio improvement achieved by complete ensemble empirical mode decomposition with adaptive noise method was 9.75 dB and the average value of the mean error of heart interval measurement was 3.27 ms.

Effective features extraction by analyzing heart sound for identifying cardiovascular diseases related to COVID-19: A diagnostic model.

Incidence and exacerbation of some of the cardiovascular diseases in the presence of the coronavirus will lead to an increase in the mortality rate among patients. Therefore, early diagnosis of such diseases is critical, especially during the COVID-19 pandemic (mild COVID-19 infection). Thus, for diagnosing the heart diseases related to the COVID-19, an automatic, non-invasive, and inexpensive method based on the heart sound processing approach is proposed. In the present study, a set of features related to the nature of heart signals is defined and extracted. The investigated features included morphological and statistical features in the heart sound frequencies. By extracting and selecting a set of effective features related to the mentioned diseases, and avoiding to use different segmentation and filtering techniques, dependence on a limited dataset and specific sampling procedures has been eliminated. Different classifiers with various kernels are applied for diagnosis in data unbalanced and balanced conditions. The results showed 93.15% accuracy and 93.72% F1-score using 60 effective features in data balanced conditions. The identification system using the extracted features from Azad dataset is able to achieve the desired results in a generalized dataset. In this way, in the shortest possible sampling time, the present system provided an effective and generalizable method and a practical model for diagnosing important cardiovascular diseases in the presence of coronavirus in the COVID-19 pandemic.

Deep Time Growing Neural Network vs Convolutional Neural Network for Intelligent Phonocardiography.

This paper explores the capabilities of a sophisticated deep learning method, named Deep Time Growing Neural Network (DTGNN), and compares its possibilities against a generally well-known method, Convolutional Neural network (CNN). The comparison is performed by using time series of the heart sound signal, so-called Phonocardiography (PCG). The classification objective is to discriminate between healthy and patients with cardiac diseases by applying a deep machine learning method to PCGs. This approach which is called intelligent phonocardiography has received interest from the researchers toward the development of a smart stethoscope for decentralized diagnosis of heart disease. It is found that DTGNN associates further flexibility to the approach which enables the classifier to learn subtle contents of PCG, and meanwhile better copes with the complexities intrinsically that exist in the medical applications such as the imbalance training. The structural risk of the two methods is compared using the A-Test method.

Simple Phonocardiography with the Ankle-Brachial Index Measurement System as a Tool for Detecting Fourth Heart Sounds of Hypertrophic Cardiomyopathy.

Conventional phonocardiography is useful for objective assessment of cardiac auscultation, but its availability is limited. More recently, an ankle-brachial index (ABI) measurement system equipped with simple phonocardiography has become widely used for diagnosing peripheral artery disease, however, whether this simple phonocardiography can be an alternative to conventional phonocardiography remains unclear.This retrospective study consisted of 48 patients with hypertrophic cardiomyopathy (HCM) and 107 controls. The presence of the fourth sound (S4) was assessed by conventional phonocardiography, in addition to apexcardiography and auscultation, in all patients with HCM. S4 was also estimated by the ABI measurement system with the phonocardiographic microphone on the sternum (the standard method) or at the apex (the apex method) in HCM patients and controls.S4 on conventional phonocardiography was detected in 42 of 48 patients (88%) with HCM. Auscultation for the detection of S4 had a sensitivity of 0.78, specificity of 0.57, and accuracy of 0.75. These diagnostic values were generally superior to those of the standard method using the ABI measurement system, whereas the apex method using the ABI measurement system had better diagnostic values, with an excellent specificity of 1.0, sensitivity of 0.77, and accuracy of 0.80. No significant differences were observed in low ABI defined as < 0.9.Simple phonocardiography equipped with the ABI measurement system may be an alternative to conventional phonocardiography for the detection of S4 in patients with HCM when the phonocardiographic microphone is moved from the sternum to the apex.

Unsupervised detection and classification of heartbeats using the dissimilarity matrix in PCG signals.

BACKGROUND AND OBJECTIVE: Auscultation is the first technique applied to the early diagnose of any cardiovascular disease (CVD) in rural areas and poor-resources countries because of its low cost and non-invasiveness. However, it highly depends on the physician's expertise to recognize specific heart sounds heard through the stethoscope. The analysis of phonocardiogram (PCG) signals attempts to segment each cardiac cycle into the four cardiac states (S1, systole, S2 and diastole) in order to develop automatic systems applied to an efficient and reliable detection and classification of heartbeats. In this work, we propose an unsupervised approach, based on time-frequency characteristics shown by cardiac sounds, to detect and classify heartbeats S1 and S2. METHODS: The proposed system consists of a two-stage cascade. The first stage performs a rough heartbeat detection while the second stage refines the previous one, improving the temporal localization and also classifying the heartbeats into types S1 and S2. The first contribution is a novel approach that combines the dissimilarity matrix with the frame-level spectral divergence to locate heartbeats using the repetitiveness shown by the heart sounds and the temporal relationships between the intervals defined by the events S1/S2 and non-S1/S2 (systole and diastole). The second contribution is a verification-correction-classification process based on a sliding window that allows the preservation of the temporal structure of the cardiac cycle in order to be applied in the heart sound classification. The proposed method has been assessed using the open access databases PASCAL, CirCor DigiScope Phonocardiogram and an additional sound mixing procedure considering both Additive White Gaussian Noise (AWGN) and different kinds of clinical ambient noises from a commercial database. RESULTS: The proposed method outperforms the detection and classification performance of other recent state-of-the-art methods. Although our proposal achieves the best average accuracy for PCG signals without cardiac abnormalities, 99.4% in heartbeat detection and 97.2% in heartbeat classification, its worst average accuracy is always above 92% for PCG signals with cardiac abnormalities, signifying an improvement in heartbeat detection/classification above 10% compared to the other state-of-the-art methods evaluated. CONCLUSIONS: The proposed method provides the best detection/classification performance in realistic scenarios where the presence of cardiac anomalies as well as different types of clinical environmental noises are active in the PCG signal. Of note, the promising modelling of the temporal structures of the heart provided by the dissimilarity matrix together with the frame-level spectral divergence, as well as the removal of a significant number of spurious heart events and recovery of missing heart events, both corrected by the proposed verification-correction-classification algorithm, suggest that our proposal is a successful tool to be applied in heart segmentation.

Heart rate estimation and validation algorithm for fetal phonocardiography.

Objective.Fetal heart rate (FHR) is an important parameter for assessing fetal well-being and is usually measured by doppler ultrasound. Fetal phonocardiography can provide non-invasive, easy-to-use and passive alternative for fetal monitoring method if reliable FHR measurements can be made even in noisy clinical environments. Therefore, this work presents an automatic algorithm to determine FHR from the fetal heart sound recordings in a noisy clinical environment.Approach.Using an electronic stethoscope fetal heart sounds were recorded from the expecting mother's abdomen, during weeks 30-40 of their pregnancy. Of these, 60 recordings were analyzed manually by two observers to obtain reference heart rate measurement. An algorithm was developed to determine FHR using envelope detection and autocorrelation of the signals. Algorithm performance was improved by implementing peak validation algorithm utilizing knowledge of valid FHR from prior windows and power spectral density function. The improvements in accuracy and reliability of algorithm were measured by mean absolute error (MAE) and positive percent agreement.Main results.By including the validation step, the MAE reduced from 11.50 to 7.54 beats per minute and positive percent agreement improved from 81% to 87%.Significance.We classified the recordings into good, moderate and poor quality to understand how the algorithm works in each of the case. The proposed algorithms provide good accuracy overall but are sensitive to the noises in recording environment that influence the quality of the signals.

Non-invasive fetal monitoring: Fetal Heart Rate multimodal estimation from abdominal electrocardiography and phonocardiography.

BACKGROUND: Fetal cardiac well-being is essential during labor as the delivery is at risk for fetal distress. Continuous monitoring by cardiotocography (CTG) is daily used to record the fetal heart rate (FHR) but this technique has important drawbacks in clinical use. OBJECTIVES: We propose to monitor FHR with a non-invasive technique, using multimodal recordings of the fetus cardiac activity, associating electrocardiographic (ECG) and phonocardiographic (PCG) sensors. The aim of this study is to evaluate the quality of these multimodal FHR estimations by comparison with CTG, based on clinical criteria. METHODS: A clinical protocol was established and a prospective open label study was carried out in the University Hospital of Grenoble. The objective was to record thoracic and abdominal PCG and ECG signals on pregnant women over 37 WG (weeks of gestation), simultaneously with CTG recordings. Adapted signal processing algorithms were then applied on abdominal PCG and ECG signals to extract FHR. Quantitative evaluation was carried out on FHR estimations compared with FHR extracted from CTG. RESULTS: A total of 40 recordings were performed. Due to technical mistakes the analysis was made possible for 38. 35 recordings allowed a FHR follow-up by ECG or PCG, 30 recordings allowed a FHR follow-up by PCG only, 25 recordings allowed a FHR follow-up by ECG only and 20 recordings allowed a FHR follow-up by both ECG and PCG. CONCLUSION: Reliable multimodal recording of FHR associating ECG and PCG sensors is possible during the last month of pregnancy. These positive results encourage the study of multimodal FHR recording during labor and delivery.

A multi-scale and multi-domain heart sound feature-based machine learning model for ACC/AHA heart failure stage classification.

Objective.Heart sounds can reflect detrimental changes in cardiac mechanical activity that are common pathological characteristics of chronic heart failure (CHF). The ACC/AHA heart failure (HF) stage classification is essential for clinical decision-making and the management of CHF. Herein, a machine learning model that makes use of multi-scale and multi-domain heart sound features was proposed to provide an objective aid for ACC/AHA HF stage classification.Approach.A dataset containing phonocardiogram (PCG) signals from 275 subjects was obtained from two medical institutions and used in this study. Complementary ensemble empirical mode decomposition and tunable-Q wavelet transform were used to construct self-adaptive sub-sequences and multi-level sub-band signals for PCG signals. Time-domain, frequency-domain and nonlinear feature extraction were then applied to the original PCG signal, heart sound sub-sequences and sub-band signals to construct multi-scale and multi-domain heart sound features. The features selected via the least absolute shrinkage and selection operator were fed into a machine learning classifier for ACC/AHA HF stage classification. Finally, mainstream machine learning classifiers, including least-squares support vector machine (LS-SVM), deep belief network (DBN) and random forest (RF), were compared to determine the optimal model.Main results. The results showed that the LS-SVM, which utilized a combination of multi-scale and multi-domain features, achieved better classification performance than the DBN and RF using multi-scale or/and multi-domain features alone or together, with average sensitivity, specificity, and accuracy of 0.821, 0.955 and 0.820 on the testing set, respectively.Significance.PCG signal analysis provides efficient measurement information regarding CHF severity and is a promising noninvasive method for ACC/AHA HF stage classification.

Utilizing Conversational Artificial Intelligence, Voice, and Phonocardiography Analytics in Heart Failure Care.

Conversational artificial intelligence involves the ability of computers, voice-enabled devices to interact intelligently with the user through voice. This can be leveraged in heart failure care delivery, benefiting the patients, providers, and payers, by providing timely access to care, filling the gaps in care, optimizing management, improving quality of care, and reducing cost. Introduction of machine learning to phonocardiography has potential to achieve outstanding diagnostic and prognostic performances in heart failure patients. There is ongoing research to use voice as a biomarker in heart failure patients. If successful, this may facilitate the screening, diagnosis, and clinical assessment of heart failure.

Intellicor: Mobile Design for Monitoring Phonographic Signals.

A mobile and web-based prototype was developed to explore utility of heart sound data in the context of patient self-monitoring. There are not many applications available despite measurement equipment that can be purchased. This research aimed at developing an application that could help patients understand and use phonocardiography. The resulting prototype Intellicor enables easy-to-use web and mobile solutions such as registering heart sound, review of previous heart signal recordings, summaries of terms related to patient condition, and medication taken. These functions can be utilized by both patients and physicians to create understanding of heart signals and build communication as a part of treatment. Three development iterations included several expert evaluators who gave positive feedback on the concept of the application. It was appreciated that patients could monitor heart signals and better understand the results. The medical experts would welcome such a system into their work domain if developed correctly and in accordance with the formal expectations, both legal and clinical. The prototype has shown the advantage of gathering data otherwise impossible to obtain. The Intellicor prototype presents the foundation that ought to be further developed in close cooperation of clinical and biomedical experts. The self-monitoring of this kind could benefit patients and the healthcare sector as demonstrated by the Intellicor prototype.

Automatic segmentation for neonatal phonocardiogram.

This work addresses the automatic segmentation of neonatal phonocardiogram (PCG) to be used in the artificial intelligence-assisted diagnosis of abnormal heart sounds. The proposed novel algorithm has a single free parameter - the maximum heart rate. The algorithm is compared with the baseline algorithm, which was developed for adult PCG segmentation. When evaluated on a large clinical dataset of neonatal PCG with a total duration of over 7h, an F1 score of 0.94 is achieved. The main features relevant for the segmentation of neonatal PCG are identified and discussed. The algorithm is able to increase the number of cardiac cycles by a factor of 5 compared to manual segmentation, potentially allowing to improve the performance of heart abnormality detection algorithms.

Can Heart Sound Denoising be Beneficial in Phonocardiogram Classification Tasksƒ.

The purpose of computer-aided diagnosis (CAD) systems is to improve the detection of diseases in a shorter time and with reduced subjectivity. A robust system frequently requires a noise-free input signal. For CADs which use heart sounds, this problem is critical as heart sounds are often low amplitude and affected by some unavoidable sources of noise such as movement artifacts and physiological sounds. Removing noises by using denoising algorithms can be beneficial in improving the diagnostics accuracy of CADs. In this study, four denoising algorithms were investigated. Each algorithm has been carefully adapted to fit the requirements of the phonocardiograph signal. The effect of the denoising algorithms was objectively compared based on the improvement it introduces in the classification performance of the heart sound dataset. According to the findings, using denoising methods directly before classification decreased the algorithm's classification performance because a murmur was also treated as noise and suppressed by the denoising process. However, when denoising using Wiener estimation-based spectral subtraction was used as a preprocessing step to improve the segmentation algorithm, it increased the system's classification performance with a sensitivity of 96.0%, a specificity of 74.0%, and an overall score of 85.0%. As a result, to improve performance, denoising can be added as a preprocessing step into heart sound classifiers that are based on heart sound segmentation.

Unsupervised Heart Sound Decomposition and State Estimation with Generative Oscillation Models.

This paper proposes a new generative probabilistic model for phonocardiograms (PCGs) that can simultaneously capture oscillatory factors and state transitions in cardiac cycles. Conventionally, PCGs have been modeled in two main aspects. One is a state space model that represents recurrent and frequently appearing state transitions. Another is a factor model that expresses the PCG as a non-stationary signal consisting of multiple oscillations. To model these perspectives in a unified framework, we combine an oscillation decomposition with a state space model. The proposed model can decompose the PCG into cardiac state dependent oscillations by reflecting the mechanism of cardiac sounds generation in an unsupervised manner. In the experiments, our model achieved better accuracy in the state estimation task compared to the empirical mode decomposition method. In addition, our model detected S2 onsets more accurately than the supervised segmentation method when distributions among PCG signals were different.

Automated Assessment of the Quality of Phonocardographic Recordings through Signal-to-Noise Ratio for Home Monitoring Applications.

The signal quality limits the applicability of phonocardiography at the patients' domicile. This work proposes the signal-to-noise ratio of the recorded signal as its main quality metrics. Moreover, we define the minimum acceptable values of the signal-to-noise ratio that warrantee an accuracy of the derived parameters acceptable in clinics. We considered 25 original heart sounds recordings, which we corrupted by adding noise to decrease their signal-to-noise ratio. We found that a signal-to-noise ratio equal to or higher than 14 dB warrants an uncertainty of the estimate of the valve closure latencies below 1 ms. This accuracy is higher than that required by most clinical applications. We validated the proposed method against a public database, obtaining results comparable to those obtained on our sample population. In conclusion, we defined (a) the signal-to-noise ratio of the phonocardiographic signal as the preferred metric to evaluate its quality and (b) the minimum values of the signal-to-noise ratio required to obtain an uncertainty of the latency of heart sound components compatible with clinical applications. We believe these results are crucial for the development of home monitoring systems aimed at preventing acute episodes of heart failure and that can be safely operated by naïve users.

Phonocardiogram signal analysis for classification of Coronary Artery Diseases using MFCC and 1D adaptive local ternary patterns.

Coronary Artery Diseases (CADs) are a dominant cause of worldwide fatalities. The development of accurate and timely diagnosis routines is imperative to reduce these risks and mortalities. Coronary angiography, an invasive and expensive technique, is currently used as a diagnostic tool for the detection of CAD but it has some procedural hazards, i.e., it requires arterial puncture, and the subject gets exposed to iodinated radiation. Phonocardiography (PCG), a non-invasive and inexpensive technique, is a modality employing heart sounds to diagnose heart diseases but it requires only trained medical personnel to apprehend cardiac murmurs in clinical environments. Furthermore, there is a strong compulsion to characterize CAD into its types, such as Single vessel coronary artery disease (SVCAD), Double vessel coronary artery disease (DVCAD), and Triple vessel coronary artery disease (TVCAD) to assist the cardiologist in decision making about the treatment procedure followed. This paper presents a computer-aided diagnosis system for the categorization of CAD and its types based on Phonocardiogram (PCG) signal analysis. The raw PCG signals were denoised via empirical mode decomposition (EMD) to remove redundant information and noise. Next, we extract MFCC and proposed 1D-Adaptive Local Ternary Patterns (1D-ALTP) and fused them serially to get a strong feature representation of multiple PCG signal classes. Features were further reduced through Multidimensional Scaling (MDS) and subjected to several classification methods such as support vector machines (SVM), Decision Tree (DT), and K-nearest neighbors (KNN) in a comparative fashion. The best classification performances of 98.3% and 97.2% mean accuracies were obtained through SVM with the cubic kernel for binary and multiclass experiments, respectively. The performance of the proposed system is comprehensively tested through 10-fold cross-validation and hold-out train-test techniques to avoid model overfitting. Comparative analysis with existing approaches advocates the superiority of the proposed approach.

Spectral analysis of heart sounds associated with coronary artery disease.

Objective. The aim of this study was to find spectral differences of diagnostic interest in heart sound recordings of patients with coronary artery disease (CAD) and healthy subjects.Approach. Heart sound recordings from three studies were pooled, and patients with clear diagnostic outcomes (positive: CAD and negative: Non-CAD) were selected for further analysis. Recordings from 1146 patients (191 CAD and 955 Non-CAD) were analyzed for spectral differences between the two groups using Welch's spectral density estimate. Frequency spectra were estimated for systole and diastole segments, and time-frequency spectra were estimated for first (S1) and second (S2) heart sound segments. An ANCOVA model with terms for diagnosis, age, gender, and body mass index was used to evaluate statistical significance of the diagnosis term for each time-frequency component.Main results. Diastole and systole segments of CAD patients showed increased energy at frequencies 20-120 Hz; furthermore, this difference was statistically significant for the diastole. CAD patients showed decreased energy for the mid-S1 and mid-S2 segments and conversely increased energy before and after the valve sounds. Both S1 and S2 segments showed regions of statistically significant difference in the time-frequency spectra.Significance. Results from analysis of the diastole support findings of increased low-frequency energy from previous studies. Time-frequency components of S1 and S2 sounds showed that these two segments likely contain heretofore untapped information for risk assessment of CAD using phonocardiography; this should be considered in future works. Further development of features that build on these findings could lead to improved acoustic detection of CAD.

Digital phonocardiography of cardiac arrhythmias in dogs - Preliminary experiences.

Electronic stethoscopes and digital phonocardiograms (DPCGs) can be applied when diagnosing cardiac murmurs, but their use for cardiac arrhythmias is not described in veterinary medicine. Data of 10 dogs are presented in this preliminary study, demonstrating the applicability of these techniques. Although the number of artefacts and the amount of baseline noise produced by the two digitising systems used did not differ, the Welch Allyn Meditron system or similar ones capable of simultaneous recording of electrocardiograms (ECGs) and DPCGs provide a better option for clinical research and education, whilst the 3M Littmann 3200 system might be more suitable for everyday clinical settings. A combined system with simultaneous phonocardiogram and ECG, especially with wireless transmission, might be a solution in the future.