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

Abstract

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.

Gated recurrent unit-based heart sound analysis for heart failure screening

“…S2 is produced at the end of systole, following the closure of semilunar valves about aortic and pulmonary [27,38]. S2 has a higher-pitch than S1, with its frequency range between 20 and 250 Hz [39]. Since the original sampling frequency may cause high computational cost, all recordings are down-sampled at 600 Hz in accordance with Nyquist Sampling Theorem.…”

Classification of the Third and Fourth Heart Sounds using Intrinsic Time-Scale Decomposition and Support Vector Machine Technique

“…The S1 frequency ranges from 10-200Hz and lasts for 120-150ms, for S2 the frequenct ranges from 20-250 Hz and lasts for 80-120ms. The third sound (S3) pronounces in the early diastolic cycle for which the frequency ranges from 25-70Hz with a typical duration of 40ms and S4 presents in the late diastolic cycle with frequency ranges 15-70Hz and lasts upto 40ms [3]. A low frequency noise which presents below 30Hz easily masks the S4 signal.…”

An Approach for Automatic Identification of Fundamental and Additional Sounds from Cardiac Sounds Recordings

“…Clinically, the splitting of S1 sounds into its subcomponents, because of reasons other than the respiratory cycle, may be evidence of atrial spectral defects (ASD) or right bundle branch block (RBBB). Similarly, the splitting of S2 sounds may be an indicator of left bundle branch block (LBBB), atrial spectral defects (ASD), right bundle branch blocks (RBBBs), left ventricular ectopic beats and pulmonary stenosis [3]- [5]. During cardiac abnormalities, apart from the split sounds, additional cardiac lub/dub sounds may be observed in the phonocardiogram, which can provide vital information about cardiac conditions and assist in the early stage detection of various cardiovascular diseases (CVDs) [5].…”

“…Similarly, the splitting of S2 sounds may be an indicator of left bundle branch block (LBBB), atrial spectral defects (ASD), right bundle branch blocks (RBBBs), left ventricular ectopic beats and pulmonary stenosis [3]- [5]. During cardiac abnormalities, apart from the split sounds, additional cardiac lub/dub sounds may be observed in the phonocardiogram, which can provide vital information about cardiac conditions and assist in the early stage detection of various cardiovascular diseases (CVDs) [5]. Consequently, the automatic detection of fundamental and additional heart sounds has been a topic of great interest among researchers [5].…”

“…During cardiac abnormalities, apart from the split sounds, additional cardiac lub/dub sounds may be observed in the phonocardiogram, which can provide vital information about cardiac conditions and assist in the early stage detection of various cardiovascular diseases (CVDs) [5]. Consequently, the automatic detection of fundamental and additional heart sounds has been a topic of great interest among researchers [5]. However, as heart sounds are often overlapped with high-frequency acoustic signals unrelated to the operation of the heart, such as noise and artifacts, their correct interpretation is challenging.…”