Detection of systolic ejection click using time growing neural network

Development and validation of an integrated residual-recurrent neural network model for automated heart murmur detection in pediatric populations

Congenital heart disease affects approximately 1% of children worldwide, with a number of cases in resource-limited settings remaining undiagnosed through school age. While cardiac auscultation is a key screening method, its effectiveness varies widely, depending on practitioner expertise. This study introduces an innovative artificial intelligence (AI) approach combining conventional machine learning and deep learning techniques to improve heart murmur detection in pediatric populations. By developing an integrated Residual-Recurrent Neural Networks model and analyzing heart sound recordings from 500 pediatric participants, we achieved remarkable diagnostic performance in real-world pediatric clinical settings. At the single recording-level, the model achieved an accuracy of 88.5%, sensitivity of 85.5%, and specificity of 90.7%. Performance improved at the participant-level, with an accuracy of 90.0%, sensitivity of 88.8%, and specificity of 91.2%. The model showed particularly strong results when tested against the PhysioNet database (accuracy 95.2%, sensitivity 91.6%, and specificity 99.1%). This research provides a compelling proof-of-concept for AI-assisted cardiac screening, potentially revolutionizing early detection strategies in pediatric cardiac diseases.

A review on deep learning methods for heart sound signal analysis

Introduction

Application of Deep Learning (DL) methods is being increasingly appreciated by researchers from the biomedical engineering domain in which heart sound analysis is an important topic of study. Diversity in methodology, results, and complexity causes uncertainties in obtaining a realistic picture of the methodological performance from the reported methods.

Methods

This survey paper provides the results of a broad retrospective study on the recent advances in heart sound analysis using DL methods. Representation of the results is performed according to both methodological and applicative taxonomies. The study method covers a wide span of related keywords using well-known search engines. Implementation of the observed methods along with the related results is pervasively represented and compared.

Results and discussion

It is observed that convolutional neural networks and recurrent neural networks are the most commonly used ones for discriminating abnormal heart sounds and localization of heart sounds with 67.97% and 33.33% of the related papers, respectively. The convolutional neural network and the autoencoder network show a perfect accuracy of 100% in the case studies on the classification of abnormal from normal heart sounds. Nevertheless, this superiority against other methods with lower accuracy is not conclusive due to the inconsistency in evaluation.

Deep Learning in Heart Sound Analysis: From Techniques to Clinical Applications

Importance: Heart sound auscultation is a routinely used physical examination in clinical practice to identify potential cardiac abnormalities. However, accurate interpretation of heart sounds requires specialized training and experience, which limits its generalizability. Deep learning, a subset of machine learning, involves training artificial neural networks to learn from large datasets and perform complex tasks with intricate patterns. Over the past decade, deep learning has been successfully applied to heart sound analysis, achieving remarkable results and accumulating substantial heart sound data for model training. Although several reviews have summarized deep learning algorithms for heart sound analysis, there is a lack of comprehensive summaries regarding the available heart sound data and the clinical applications. Highlights: This review will compile the commonly used heart sound datasets, introduce the fundamentals and state-of-the-art techniques in heart sound analysis and deep learning, and summarize the current applications of deep learning for heart sound analysis, along with their limitations and areas for future improvement. Conclusions: The integration of deep learning into heart sound analysis represents a significant advancement in clinical practice. The growing availability of heart sound datasets and the continuous development of deep learning techniques contribute to the improvement and broader clinical adoption of these models. However, ongoing research is needed to address existing challenges and refine these technologies for broader clinical use.

Wavelet based event detection in the phonocardiogram of prolapsed mitral valve

Mitral valve prolapse (MVP) is one of the cardiovascular valve abnormalities that occurs due to the stretching of mitral valve leaflets, which develops in around 2 percent of the population. MVP is usually detected via auscultation and diagnosed with an echocardiogram, which is an expensive procedure. The characteristic auscultatory finding in MVP is a mid-to-late systolic click which is usually followed by a high-pitched systolic murmur. These can be easily detected on a phonocardiogram which is a graphical representation of the auscultatory signal. In this paper, we have proposed a method to automatically identify patterns in the PCG that can help in diagnosing MVP as well as monitor its progression into Mitral Regurgitation. In the proposed methodology the systolic part, which is the region of interest here, is isolated by preprocessing and thresholded Teager-Kaiser energy envelope of the signal. Scalogram images of the systole part are obtained by applying continuous wavelet transform. These scalograms are used to train the convolutional neural network (CNN). A two-layer CNN could identify the event patterns with nearly 100% accuracy on the test dataset with varying sizes (20% - 40% of the entire data). The proposed method shows potential in the quick screening of MVP patients.

Gated temporal convolutional neural network and expert features for diagnosing and explaining physiological time series: A case study on heart rates

BACKGROUND AND OBJECTIVE

Physiological time series are common data sources in many health applications. Mining data from physiological time series is crucial for promoting healthy living and reducing governmental medical expenditure. Recently, research and applications of deep learning methods on physiological time series have developed rapidly because such data can be continuously recorded by smart wristbands or smartwatches. However, existing deep learning methods suffer from excessive model complexity and a lack of explanation. This paper aims to handle these issues.

METHODS

We propose TEG-net, which is a novel deep learning method for accurately diagnosing and explaining physiological time series. TEG-net constructs T-net (a multi-scale bi-directional temporal convolutional neural network) to model physiological time series directly, E-net (personalized linear model) to model expert features extracted from physiological time series, and G-net (gating neural network) to combine T-net and E-net for diagnosis. The combination of T-net and E-net through G-net improves diagnosis accuracy and E-net can be utilized for explanation.

RESULTS

Experimental results demonstrate that TEG-net outperforms the second-best baseline by 13.68% in terms of area under the receiver operating characteristic curve and 11.49% in terms of area under the precision-recall curve. Additionally, intuitive justifications can be provided to explain model predictions.

CONCLUSIONS

This paper develops an ensemble method to combine expert features and deep learning method for modeling physiological time series. Improvements in diagnostic accuracy and explanation make TEG-net applicable to many real-world health applications.

A Deep Machine Learning Method for Classifying Cyclic Time Series of Biological Signals Using Time-Growing Neural Network

This paper presents a novel method for learning the cyclic contents of stochastic time series: the deep time-growing neural network (DTGNN). The DTGNN combines supervised and unsupervised methods in different levels of learning for an enhanced performance. It is employed by a multiscale learning structure to classify cyclic time series (CTS), in which the dynamic contents of the time series are preserved in an efficient manner. This paper suggests a systematic procedure for finding the design parameter of the classification method for a one-versus-multiple class application. A novel validation method is also suggested for evaluating the structural risk, both in a quantitative and a qualitative manner. The effect of the DTGNN on the performance of the classifier is statistically validated through the repeated random subsampling using different sets of CTS, from different medical applications. The validation involves four medical databases, comprised of 108 recordings of the electroencephalogram signal, 90 recordings of the electromyogram signal, 130 recordings of the heart sound signal, and 50 recordings of the respiratory sound signal. Results of the statistical validations show that the DTGNN significantly improves the performance of the classification and also exhibits an optimal structural risk.

Paediatric heart sound signal analysis towards classification using multifractal spectra

Healthy versus unhealthy heart sound computer-aided classification tools are very popular for supporting clinical decisions. In this paper a new method is proposed for the classification of heart sound recordings from a statistical standpoint without detection and localization of fundamental heart sounds (S1, S2). This study analyzes the possibility of detecting healthy heart sound signal from a large set of measurements, corresponding to different pathologies, such as aortic regurgitation, mitral regurgitation, aortic stenosis and ventricular septal defects. The proposed method employs singularity spectra analysis and long-term dependency of irregular structures. Healthy signals are firstly separated from the rest of the recordings. In the second step, the signals with a click syndrome, used here as a reference, are detected in the unhealthy group. Innocent murmurs have not been considered in this paper. Each auscultatory recording is classified into one of the following classes: healthy; click syndrome; and other heart dysfunctions. The results of the proposed method provided high recall and precision values for each of the three classes. Since the presence of additive noise may affect the classification, we also analyzed the possibility of classifying signals in such circumstances. The method was tested, verified and showed high accuracy.

An Intelligent Phonocardiography for Automated Screening of Pediatric Heart Diseases

This paper presents a robust device for automated screening of pediatric heart diseases based on our unique processing method in murmur characterization; the Arash-Band method. The present study modifies the Arash-Band method and employs output of the modified method in conjunction with the two other original techniques to extract indicative feature vectors for the screening. The extracted feature vectors are classified by using the support vector machine method. Results show that the proposed modifications significantly enhances performance of the Arash-Band in terms of the both accuracy and sensitivity as the corresponding effect sizes are sufficiently large. The proposed algorithm has been incorporated into an Android-based tablet to constitute an intelligent phonocardiogram with the automatic screening capability. In order to obtain confidence interval of the accuracy and sensitivity, an inferable statistical test is applied on our database containing the phonocardiogram signals recorded from 263 of the referrals to a hospital. The expected value of the accuracy/sensitivity is estimated to be 87.45 % / 87.29 % with a 95 % confidence interval of (80.19 % - 92.47 %) / (76.01 % - 95.78 %) exhibiting superior performance than a pediatric cardiologist who relies on conventional or even computer-assisted auscultation.

A Novel Method for Screening Children with Isolated Bicuspid Aortic Valve

This paper presents a novel processing method for heart sound signal: the statistical time growing neural network (STGNN). The STGNN performs a robust classification by merging supervised and unsupervised statistical methods to overcome non-stationary behavior of the signal. By combining available preprocessing and segmentation techniques and the STGNN classifier, we build an automatic tool for screening children with isolated BAV, the congenital heart malformation which can lead to serious cardiovascular lesions. Children with BAV (22 individuals) and healthy condition (28 individuals) are subjected to the study. The performance of the STGNN is compared to that of a time growing neural network (CTGNN) and a conventional support vector (CSVM) machine, using balanced repeated random sub sampling. The average of the accuracy/sensitivity is estimated to be 87.4/86.5 for the STGNN, 81.8/83.4 for the CTGNN, and 72.9/66.8 for the CSVM. Results show that the STGNN offers better performance and provides more immunity to the background noise as compared to the CTGNN and CSVM. The method is implementable in a computer system to be employed in primary healthcare centers to improve the screening accuracy.