Wavelet packet entropy for heart murmurs classification

External evaluation of a commercial artificial intelligence-augmented digital auscultation platform in valvular heart disease detection using echocardiography as reference standard

OBJECTIVE

There are few studies evaluating the accuracy of commercially available AI-powered digital auscultation platforms in detecting valvular heart disease (VHD). Therefore, the utility of these systems for diagnosing clinically significant VHD remains unclear. We conducted a comprehensive external evaluation of the Eko murmur analysis software (EMAS) and report its accuracy in detecting murmurs associated with VHD using echocardiography (ECHO) as the reference standard.

METHODS

We analyzed phonocardiogram (PCG) and ECHO data from 1,029 individuals (461 females, mean (SD) age: 61 (29) years, BMI: 29 (9)) at a single academic medical center. PCGs were recorded using the EkoDUO and EkoCORE stethoscopes from the four standard auscultation positions immediately before transthoracic ECHO (TTE) testing. TTE diagnostics were used as reference to calculate the EMAS sensitivity and specificity in detecting murmurs associated with VHD. The 95% confidence intervals are reported.

RESULTS

Of the 4,081 PCGs, 79% were of sufficient quality for murmur analysis. The sensitivity and specificity of the EMAS in detecting VHD were 39.3% (95% CI: 37.2-41.3) and 82.3% (95% CI: 80.0-84.5), respectively. EMAS sensitivity in detecting murmurs associated with common VHD types was 62.5%, 75.0%, 88.9%, and 63.3% for moderate-severe and severe cases of mitral stenosis, aortic regurgitation, aortic stenosis, and mitral regurgitation, respectively.

CONCLUSION

The EMAS algorithm exhibits limited overall sensitivity in detecting VHD. The sensitivity of the algorithm varies across VHD types. These findings suggest that EMAS can be used for diagnosis of specific lesions, but not all VHD types, which limits its clinical applicability as a screening tool.

Machine Learning Algorithms for Processing and Classifying Unsegmented Phonocardiographic Signals: An Efficient Edge Computing Solution Suitable for Wearable Devices

The phonocardiogram (PCG) can be used as an affordable way to monitor heart conditions. This study proposes the training and testing of several classifiers based on SVMs (support vector machines), k-NN (k-Nearest Neighbor), and NNs (neural networks) to perform binary ("Normal"/"Pathologic") and multiclass ("Normal", "CAD" (coronary artery disease), "MVP" (mitral valve prolapse), and "Benign" (benign murmurs)) classification of PCG signals, without heart sound segmentation algorithms. Two datasets of 482 and 826 PCG signals from the Physionet/CinC 2016 dataset are used to train the binary and multiclass classifiers, respectively. Each PCG signal is pre-processed, with spike removal, denoising, filtering, and normalization; afterward, it is divided into 5 s frames with a 1 s shift. Subsequently, a feature set is extracted from each frame to train and test the binary and multiclass classifiers. Concerning the binary classification, the trained classifiers yielded accuracies ranging from 92.4 to 98.7% on the test set, with memory occupations from 92.7 kB to 11.1 MB. Regarding the multiclass classification, the trained classifiers achieved accuracies spanning from 95.3 to 98.6% on the test set, occupying a memory portion from 233 kB to 14.1 MB. The NNs trained and tested in this work offer the best trade-off between performance and memory occupation, whereas the trained k-NN models obtained the best performance at the cost of large memory occupation (up to 14.1 MB). The classifiers' performance slightly depends on the signal quality, since a denoising step is performed during pre-processing. To this end, the signal-to-noise ratio (SNR) was acquired before and after the denoising, indicating an improvement between 15 and 30 dB. The trained and tested models occupy relatively little memory, enabling their implementation in resource-limited systems.

[Research on bark-frequency spectral coefficients heart sound classification algorithm based on multiple window time-frequency reassignment]

The multi-window time-frequency reassignment helps to improve the time-frequency resolution of bark-frequency spectral coefficient (BFSC) analysis of heart sounds. For this purpose, a new heart sound classification algorithm combining feature extraction based on multi-window time-frequency reassignment BFSC with deep learning was proposed in this paper. Firstly, the randomly intercepted heart sound segments are preprocessed with amplitude normalization, the heart sounds were framed and time-frequency rearrangement based on short-time Fourier transforms were computed using multiple orthogonal windows. A smooth spectrum estimate is calculated by arithmetic averaging each of the obtained independent spectra. Finally, the BFSC of reassignment spectrum is extracted as a feature by the Bark filter bank. In this paper, convolutional network and recurrent neural network are used as classifiers for model comparison and performance evaluation of the extracted features. Eventually, the multi-window time-frequency rearrangement improved BFSC method extracts more discriminative features, with a binary classification accuracy of 0.936, a sensitivity of 0.946, and a specificity of 0.922. These results present that the algorithm proposed in this paper does not need to segment the heart sounds and randomly intercepts the heart sound segments, which greatly simplifies the computational process and is expected to be used for screening of congenital heart disease.

A new approach to phonocardiogram severity analysis

Phonocardiogram signal (PCG) has been the subject of several signal processing studies, where researchers applied various analysis techniques and extracted numerous features for different purposes, like cardiac pathologies identification, healthy/pathologic case discrimination, and severity assessment. When talking about cardiac severity, many think directly about the intensity or energy of the signal as the most reliable parameter. However, cardiac severity is not always reflected by the intensity or energy of the signal but includes other variables as well. In this paper, we will discuss the probability of having a Discrete Wavelet Transform (DWT) parameter that discriminates, identifies, and assesses the pathological cardiac severity levels, a parameter that takes into consideration other variables and elements for the severity study. For this purpose, we studied six PCGs signals that contain reduced murmurs (clicks) and eight murmur signals with four different cardiac severity levels. We extracted the Entropy of Approximation Coefficients (EAC) from the Discrete Wavelet Transform (DWT) sub-bands as the feature to study in this novel approach. The Energetic Ratio (ER) served as a reference parameter to evaluate the EAC evolution, due to its proven efficiency in cardiac severity tracking. While the DWT-EAC algorithm results revealed that the EAC provides better results for the paper purposes, the One versus All Support Vector Machine (OVA-SVM) classifier affirmed the efficiency of the Entropy of Approximation Coefficients (EAC) for cardiac severity assessment and proved the accuracy of this novel approach.

Cardiovascular Disease Recognition Based on Heartbeat Segmentation and Selection Process

Assessment of heart sounds which are generated by the beating heart and the resultant blood flow through it provides a valuable tool for cardiovascular disease (CVD) diagnostics. The cardiac auscultation using the classical stethoscope phonological cardiogram is known as the most famous exam method to detect heart anomalies. This exam requires a qualified cardiologist, who relies on the cardiac cycle vibration sound (heart muscle contractions and valves closure) to detect abnormalities in the heart during the pumping action. Phonocardiogram (PCG) signal represents the recording of sounds and murmurs resulting from the heart auscultation, typically with a stethoscope, as a part of medical diagnosis. For the sake of helping physicians in a clinical environment, a range of artificial intelligence methods was proposed to automatically analyze PCG signal to help in the preliminary diagnosis of different heart diseases. The aim of this research paper is providing an accurate CVD recognition model based on unsupervised and supervised machine learning methods relayed on convolutional neural network (CNN). The proposed approach is evaluated on heart sound signals from the well-known, publicly available PASCAL and PhysioNet datasets. Experimental results show that the heart cycle segmentation and segment selection processes have a direct impact on the validation accuracy, sensitivity (TPR), precision (PPV), and specificity (TNR). Based on PASCAL dataset, we obtained encouraging classification results with overall accuracy 0.87, overall precision 0.81, and overall sensitivity 0.83. Concerning Micro classification results, we obtained Micro accuracy 0.91, Micro sensitivity 0.83, Micro precision 0.84, and Micro specificity 0.92. Using PhysioNet dataset, we achieved very good results: 0.97 accuracy, 0.946 sensitivity, 0.944 precision, and 0.946 specificity.

Automated Diagnosis of Heart Sounds Using Rule-Based Classification Tree

In order to assist the diagnosis procedure of heart sound signals, this paper presents a new automated method for classifying the heart status using a rule-based classification tree into normal and three abnormal cases; namely the aortic valve stenosis, aortic insufficient, and ventricular septum defect. The developed method includes three main steps as follows. First, one cycle of the heart sound signals is automatically detected and segmented based on time properties of the heart signals. Second, the segmented cycle is preprocessed with the discrete wavelet transform and then largest Lyapunov exponents are calculated to generate the dynamical features of heart sound time series. Finally, a rule-based classification tree is fed by these Lyapunov exponents to give the final decision of the heart health status. The developed method has been tested successfully on twenty-two datasets of normal heart sounds and murmurs with success rate of 95.5%. The resulting error can be easily corrected by modifying the classification rules; consequently, the accuracy of automated heart sounds diagnosis is further improved.

The electronic stethoscope

Most heart diseases are associated with and reflected by the sounds that the heart produces. Heart auscultation, defined as listening to the heart sound, has been a very important method for the early diagnosis of cardiac dysfunction. Traditional auscultation requires substantial clinical experience and good listening skills. The emergence of the electronic stethoscope has paved the way for a new field of computer-aided auscultation. This article provides an in-depth study of (1) the electronic stethoscope technology, and (2) the methodology for diagnosis of cardiac disorders based on computer-aided auscultation. The paper is based on a comprehensive review of (1) literature articles, (2) market (state-of-the-art) products, and (3) smartphone stethoscope apps. It covers in depth every key component of the computer-aided system with electronic stethoscope, from sensor design, front-end circuitry, denoising algorithm, heart sound segmentation, to the final machine learning techniques. Our intent is to provide an informative and illustrative presentation of the electronic stethoscope, which is valuable and beneficial to academics, researchers and engineers in the technical field, as well as to medical professionals to facilitate its use clinically. The paper provides the technological and medical basis for the development and commercialization of a real-time integrated heart sound detection, acquisition and quantification system.

Assessment and in vitro experiment of artificial anal sphincter system based on rebuilding the rectal sensation function

In this paper, a novel artificial anal sphincter (AAS) system based on rebuilding the rectal sensation function is proposed to treat human fecal incontinence. The executive mechanism of the traditional AAS system was redesigned and integrated for a simpler structure and better durability. The novel executive mechanism uses a sandwich structure to simulate the basic function of the natural human anal sphincter. To rebuild the lost rectal sensation function caused by fecal incontinence, we propose a novel method for rebuilding the rectal sensation function based on an Optimal Wavelet Packet Basis (OWPB) using the Davies-Bouldin (DB) index and a support vector machine (SVM). OWPB using a DB index is used for feature vector extraction, while a SVM is adopted for pattern recognition.Furthermore, an in vitro experiment with the AAS system based on rectal sensation function rebuilding was carried out. Experimental results indicate that the novel executive mechanism can simulate the basic function of the natural human anal sphincter, and the proposed method is quite effective for rebuilding rectal sensation in patients.