A System for Heart Sounds Classification

Abstract

The future of quick and efficient disease diagnosis lays in the development of reliable non-invasive methods. As for the cardiac diseases – one of the major causes of death around the globe – a concept of an electronic stethoscope equipped with an automatic heart tone identification system appears to be the best solution. Thanks to the advancement in technology, the quality of phonocardiography signals is no longer an issue. However, appropriate algorithms for auto-diagnosis systems of heart diseases that could be capable of distinguishing most of known pathological states have not been yet developed. The main issue is non-stationary character of phonocardiography signals as well as a wide range of distinguishable pathological heart sounds. In this paper a new heart sound classification technique, which might find use in medical diagnostic systems, is presented. It is shown that by combining Linear Predictive Coding coefficients, used for future extraction, with a classifier built upon combining Support Vector Machine and Modified Cuckoo Search algorithm, an improvement in performance of the diagnostic system, in terms of accuracy, complexity and range of distinguishable heart sounds, can be made. The developed system achieved accuracy above 93% for all considered cases including simultaneous identification of twelve different heart sound classes. The respective system is compared with four different major classification methods, proving its reliability.

Localization and classification of heart beats in phonocardiography signals —a comprehensive review

“…Authors in [35], for instance, use support vector machine with a modified cuckoo search (MCS) optimizer using features extracted from linear predictive coding (LPC) for classification. Similarly, Chen et al [36] investigated deep neural networks for recognition of heart sounds S1 and S2.…”

“…From the view point of heart sounds, S1 and S2 are considered in [30,31,36,37] while [35] and [16], in addition to S1 and S2, also consider split S1, split S2, S3, S4, murmurs, clicks, and snaps. The work in [34] is focused on discrimination between normal heart sounds and murmurs.…”

A benchmark of heart sound classification systems based on sparse decompositions

“…Instead of representing the temporal waveform, LPC tries to fit the spectrum of the signal. A number of works have used the LPC parameters 7,21 as features for PCG's classification. Let h k be the set of LPC coefficients.…”

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

“…The presence of noise and some artifacts can mask the PCG plot, however, this doesn't provide transparency for clinical diagnosis. This situation can be overwhelmed by considering the frequency and time characteristic analysis [2]. Precise diagnosis can be achieved by signal processing methods which give the characteristics of heart signal.…”