Heart sound classification from unsegmented phonocardiograms

Langley, Philip; Murray, Alan

doi:10.1088/1361-6579/aa724c

Cited by 67 publications

(34 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, identification of S 2 (SHSD) at the event level, was reported in [25], [29], [45], [47], [52], [57], [64], [87]- [89], [92], [94], [96], [100], and [104], achieving a mean accuracy of 93.96 ± 5.01%; while the mean classification accuracy reported in [90], [106], and [111] was 90.82 ± 6.58%. Pathological heart sounds detection (PHSD) at the event level reported in [29], [64], [65], [67], and [112], achieved mean accuracy of 88.50 ± 5.93%, while pathological heart sounds classification (PHSC) reported in [64], [69], [75], [78], [95], [105], [110], [140], [142], [145], [146], [155], [157], [158], [162]- [164], [167], [170], [183], [185], and [191], achieved mean classification accuracy of 90.28 ± 7.82%. The mean accuracy in the identification of S 1 at the event level was found to be the highest.…”

Section: Synthesis Of Resultsmentioning

confidence: 99%

Algorithms for Automatic Analysis and Classification of Heart Sounds–A Systematic Review

2019

View full text Add to dashboard Cite

Cardiovascular diseases currently pose the highest threat to human health around the world. Proper investigation of the abnormalities in heart sounds is known to provide vital clinical information that can assist in the diagnosis and management of cardiac conditions. However, despite significant advances in the development of algorithms for automated classification and analysis of heart sounds, the validity of different approaches has not been systematically reviewed. This paper provides an in-depth systematic review and critical analysis of all the existing approaches for automatic identification and classification of the heart sounds. All statements on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2009 Checklist were followed and addressed thoroughly to maintain the quality of the accounted systematic review. Out of 1347 research articles available in the academic databases from 1963 to 2018, 117 peerreviewed articles were found to fall under the search and selection criteria of this paper. Amongst them: 53 articles are focused on segmentation, 72 of the studies are related to the feature extraction approaches and 88 to classification, and 56 reported on the databases and heart sounds acquisition. From this review, it is clear that, although a lot of research has been done in the field of automated analysis, there is still some work to be done to develop robust methods for identification and classification of various events in the cardiac cycle so that this could be effectively used to improve the diagnosis and management of cardiovascular diseases in combination with the wearable mobile technologies.

show abstract

Section: Synthesis Of Resultsmentioning

confidence: 99%

Algorithms for Automatic Analysis and Classification of Heart Sounds–A Systematic Review

2019

View full text Add to dashboard Cite

show abstract

“…The variation of normal (9857) and abnormal samples (3158) results in degrading the performance of the model [34]. Author Sensitivity% Specificity% Accuracy% Tang et al [19] 88.00 87.00 88.00 Dominguez et al [12] 93.20 95.12 97.00 Bradley et al [11] 90.07 88.45 89.26 Mostafa et al [13] 76.96 88.31 82.63 Masun et al [14] 79.60 80.60 80.10 Plesinger et al [17] 89.00 81.60 85.00 Vykintas et al [20] 80.63 87.66 84.15 Wei et al [21] 98.33 84.67 91.50 Philip et al [24] 77.00 80.00 79.00 Singh et al [33] 93.00 90.00 90.00 This study 94.08 91.95 92.47…”

Section: Discussionmentioning

confidence: 99%

“…Classification of a heart using unsegmented PCG signals was performed in limited papers [22][23][24][25]. Hamidi et al [23] extracted the features from unsegmented PCG based on curve fitting and fractal dimension, which were then further classified using the K-nearest neighbors (KNN) classifier.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Short unsegmented PCG classification based on ensemble classifier

Singh¹,

Majumder²

2020

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Diseases associated with the heart are one of the main reasons of death worldwide. Hence, early examination of the heart is important. For analysis of cardiac disorders, a study of heart sounds is a crucial and beneficial approach.Still, automated classification of heart sounds is a challenging task that mainly depends on segmentation of heart sounds and derivation of features using segmented samples. In the literature available for PCG classification provided by PhysioNet/CinC Challenge 2016, most of the research has focused on enhancing the accuracy of the classification model based on complicated segmentation processes and has failed to improve the sensitivity. In this paper, we present an automated heart sound classification by eliminating the segmentation steps using multidomain features, which results in enhanced sensitivity. The study is based on homomorphic envelogram, mel frequency cepstral coefficient (MFCC), power spectral density (PSD), and multidomain feature extraction. The extracted features are trained using the 5-fold cross-validation method based on an ensemble boosting algorithm over 100 independent iterations. Our proposed design is evaluated using public datasets published in PhysioNet/Computers in Cardiology Challenge 2016. Accuracy of 92.47% with improved sensitivity of 94.08% and specificity of 91.95% is achieved using our model. The output performance proves that our proposed model offers superior performance results.

show abstract

“…In order to ensure the resilience of the reconstructed signal, should be as consistent as possible with the original multichannel synchronously collected HS signal. We use the similarity coefficient [11] index and peak signal-to-noise ratio (PSNR) index to evaluate the reconstruction effect.…”

Section: B the Principle Of Optimal Reconstructionmentioning

confidence: 99%

Research on Parallel Compressive Sensing and Application of Multi-Channel Synchronous Acquisition of Heart Sound Signals

Cheng

Shan

et al. 2019

IEEE Access

View full text Add to dashboard Cite

The rapid development of wearable biosensors based on the Internet of Things provides a new solution for heart disease analysis and prediction of sudden death from heart failure. However, how to deal with a large amount of data generated by heart sound signals is an urgent problem to be solved. Based on the characteristics of heart sound signals, we propose a parallel compressive sensing model for the multichannel synchronous acquisition of heart sound signals. Furthermore, we provide a series of experiments to assess the performance of the model. The experimental results demonstrate that the reconstruction speed of the proposed model is 9-10 times faster than that of the block sparse Bayesian learning algorithm and the orthogonal matching pursuit algorithm, and the reconstruction effect is better. Meanwhile, the proposed model can effectively reconstruct the normal heart sound signal and abnormal heart sound signal of fourchannel synchronous acquisition. Therefore, the proposed model is feasibility. INDEX TERMS Heart sound signals, compressive sensing, parallel signals, monitoring, L 1 norm, block sparse Bayesian learning. I. INTRODUCTION

show abstract

Heart sound classification from unsegmented phonocardiograms

Abstract: The feasibility of accurate classification without segmentation of the characteristic heart sounds has been demonstrated. Classification accuracy is comparable to other algorithms but achieved without the complexity of segmentation.

Cited by 67 publications

References 12 publications

Algorithms for Automatic Analysis and Classification of Heart Sounds–A Systematic Review

Algorithms for Automatic Analysis and Classification of Heart Sounds–A Systematic Review

Short unsegmented PCG classification based on ensemble classifier

Research on Parallel Compressive Sensing and Application of Multi-Channel Synchronous Acquisition of Heart Sound Signals

Contact Info

Product

Resources

About