Detection of the third and fourth heart sounds using Hilbert-Huang transform

Abstract

BackgroundThe third and fourth heart sound (S3 and S4) are two abnormal heart sound components which are proved to be indicators of heart failure during diastolic period. The combination of using diastolic heart sounds with the standard ECG as a measurement of ventricular dysfunction may improve the noninvasive diagnosis and early detection of myocardial ischemia.MethodsIn this paper, an adaptive method based on time-frequency analysis is proposed to detect the presence of S3 and S4. Heart sound signals during diastolic periods were analyzed with Hilbert-Huang Transform (HHT). A discrete plot of maximal instantaneous frequency and its amplitude was generated and clustered. S3 and S4 were recognized by the clustered points, and performance of the method was further enhanced by period definition and iteration tracking.ResultsUsing the proposed method, S3 and S4 could be detected adaptively in a same method. 90.3% of heart sound cycles with S3 were detected using our method, 9.6% were missed, and 9.6% were false positive. 94% of S4 were detected using our method, 5.5% were missed, and 16% were false positive.ConclusionsThe proposed method is adaptive for detecting low-amplitude and low-frequency S3 and S4 simultaneously compared with previous detection methods, which would be practical in primary care.

Multistage decision‐based heart sound delineation method for automated analysis of heart sounds and murmurs

“…Introduction: Phonocardiography provides vital information for diagnosis of various cardiovascular diseases [1][2][3][4][5][6][7][8]. The normal PCG signal consists of the first heart sound (S1), the systolic pause after the sound S1, the second heart sound (S2), and the diastolic pause after the sound S2 [3][4][5]. The other normal and abnormal heart sounds (S3 and S4), high-pitched clicks, and different types of heart murmurs may occur in the systolic and diastolic pause intervals [5].…”

“…The normal PCG signal consists of the first heart sound (S1), the systolic pause after the sound S1, the second heart sound (S2), and the diastolic pause after the sound S2 [3][4][5]. The other normal and abnormal heart sounds (S3 and S4), high-pitched clicks, and different types of heart murmurs may occur in the systolic and diastolic pause intervals [5]. Heart murmurs are often characterised by the timing (early, mid, or late), intensity, duration, pitch (low, medium, or high), quality (blowing, rumbling, or musical), and configurations of crescendo, decrescendo, crescendo-decrescendo [1][2][3][4][5][6][7][8].…”

“…The other normal and abnormal heart sounds (S3 and S4), high-pitched clicks, and different types of heart murmurs may occur in the systolic and diastolic pause intervals [5]. Heart murmurs are often characterised by the timing (early, mid, or late), intensity, duration, pitch (low, medium, or high), quality (blowing, rumbling, or musical), and configurations of crescendo, decrescendo, crescendo-decrescendo [1][2][3][4][5][6][7][8]. Thus, an automated delineation method for accurate measurements of sound parameters including amplitude, frequency content, duration, systolic, and diastolic intervals, timing, and configuration of murmurs is most important for effective diagnosis of cardiovascular diseases.…”

“…Heart murmurs are often characterised by the timing (early, mid, or late), intensity, duration, pitch (low, medium, or high), quality (blowing, rumbling, or musical), and configurations of crescendo, decrescendo, crescendo-decrescendo [1][2][3][4][5][6][7][8]. Thus, an automated delineation method for accurate measurements of sound parameters including amplitude, frequency content, duration, systolic, and diastolic intervals, timing, and configuration of murmurs is most important for effective diagnosis of cardiovascular diseases.Many heart sound segmentation (HSS) methods were reported based on the reference electrocardiogram (ECG) and/or carotid pulse (CP) signals [3], empirical mode decomposition (EMD) [4,5], hidden Markov models [7], wavelet transform (WT), and wavelet packet transform [8][9][10], temporal-spectral features [11][12][13][14], homomorphic envelogram, and self-organising probabilistic model [15], Hilbert transform [16,17], support vector machine [18], and artificial neural network [19]. On the basis of the feature extraction approaches, the HSS methods can be categorised into four major groups: (i) ECG and/or CP waveform-based methods, (ii) temporal-spectral feature-based methods, (iii) envelope-based methods, and (iv) hybrid methods.…”

“…Many heart sound segmentation (HSS) methods were reported based on the reference electrocardiogram (ECG) and/or carotid pulse (CP) signals [3], empirical mode decomposition (EMD) [4,5], hidden Markov models [7], wavelet transform (WT), and wavelet packet transform [8][9][10], temporal-spectral features [11][12][13][14], homomorphic envelogram, and self-organising probabilistic model [15], Hilbert transform [16,17], support vector machine [18], and artificial neural network [19]. On the basis of the feature extraction approaches, the HSS methods can be categorised into four major groups: (i) ECG and/or CP waveform-based methods, (ii) temporal-spectral feature-based methods, (iii) envelope-based methods, and (iv) hybrid methods.…”