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

Abstract

A robust multistage decision-based heart sound delineation (MDHSD) method is presented for automatically determining the boundaries and peaks of heart sounds (S1, S2, S3, and S4), systolic, and diastolic murmurs (early, mid, and late) and high-pitched sounds (HPSs) of the phonocardiogram (PCG) signal. The proposed MDHSD method consists of the Gaussian kernels based signal decomposition (GSDs) and multistage decision-based delineation (MDBD). The GSD algorithm first removes the low-frequency (LF) artefacts and then decomposes the filtered signal into two subsignals: the LF sound part (S1, S2, S3, and S4) and the high-frequency sound part (murmurs and HPSs). The MDBD algorithm consists of absolute envelope extraction, adaptive thresholding, and fiducial point determination. The accuracy and robustness of the proposed method is evaluated using various types of normal and pathological PCG signals. Results show that the method achieves an average sensitivity of 98.22%, positive predictivity of 97.46%, and overall accuracy of 95.78%. The method yields maximum average delineation errors of 4.52 and 4.14 ms for determining the start-point and end-point of sounds. The proposed multistage delineation algorithm is capable of improving the delineation accuracy under time-varying amplitudes of heart sounds and various types of murmurs. The proposed method has significant potential applications in heart sounds and murmurs classification systems.1. 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]. 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 ...

Clinical decision support system using a machine learning model to assist simultaneous cardiopulmonary auscultation: Open-label randomized controlled trial

“…To effectively differentiate between overlapping cardiac and pulmonary sounds, we implemented an envelope-based method. 28 , 29 This method is particularly useful for distinguishing between two different rhythms, characteristic of both cardiac and lung sounds, by isolating the temporal patterns that differentiate heartbeats from breathing cycles. The distinct rhythmic patterns of heartbeats compared to the more variable patterns of breath sounds allow for the effective segmentation of our audio data, ensuring that our ML models process and classify cardiac and pulmonary sounds accurately.…”