Discrimination of Aortic and Pulmonary Components from the Second Heart Sound Using Respiratory Modulation and Measurement of Respiratory Split

Abstract

Featured Application: This work proposes a method to measure the respiratory split in a quantitative way. Based on the assumption model, the aortic component can be extracted by average and the pulmonary component can be estimated by subtracting. The calculation of the split is performed by timing difference of the two components. The method can track the respiratory split and has applications in monitoring heart response to respiration. Abstract:The second heart sound consists of aortic and pulmonary components. Analysis on the changes of the second heart sound waveform in respiration shows that the aortic component has little variation and the delay of the pulmonary component is modulated by respiration. This paper proposes a novel model to discriminate the aortic and pulmonary components using respiratory modulation. It is found that the aortic component could be simply extracted by averaging the second heart sounds over respiratory phase, and the pulmonary component could be extracted by subtraction. Hence, the split is measured by the timing difference of the two components. To validate the measurement, the method is applied to simulated second heart sounds with known varying splits. The simulation results show that the aortic and pulmonary components can be successfully extracted and the measured splits are close to the predefined splits. The method is further evaluated by data collected from 12 healthy subjects. Experimental results show that the respiratory split can be accurately measured. The minimum split generally occurs at the end of expiration and the split value is about 20 ms. Meanwhile, the maximum split is about 50 ms at the end of inspiration. Both the trend of split varying with respect to respiratory phase and the numerical range of split varying are comparable to the results disclosed by previous physiologists. The proposed method is compared to the two previous well known methods. The most attractive advantage of the proposed method is much less complexity. This method has potential applications in monitoring heart hemodynamic response to respiration.

Source Separation of the Second Heart Sound Using Gaussian Mixture Models

“…1, when the split is distributed uniformly between 10 ms and values ranging from 20 ms to 90 ms. As expected, source separation is less reliable when the split is lower, due to the increased time-domain overlap between the A2 and P2 components. On the other hand, the proposed approach is shown to outperform significantly the method described in [6] for all splits considered.…”

“…The performance of the proposed method in separating A2 and P2 components is compared with that provided by the method in [6]. Performance is evaluated in terms of the normalized root mean-squared error (NRMSE) achieved in the reconstruction of A2 and P2 components.…”

“…From this data, a joint GMM with K = 20 Gaussian components is inferred, which models the vectors x = [a T , p T ] T containing samples from the A2 and P2 components. Then, the proposed separation algorithm and the algorithm described in [6] are applied to further 400 heart sounds, each containing 16 heartbeats, which are generated independently from the training data.…”

“…A different approach has recently emerged which refrains from adopting a predetermined waveform model and instead uses the different dynamical behavior of A2 and P2 components in different S2 sounds to perform separation. In particular, Tang et al [6] leverage the fact that A2 components usually occupy the same position in different S2 sounds, whereas P2 components experience a shift according to the respiration phase of each recorded S2 sound (i.e., P2 components experience a more significant delay from A2 components during inspiration phases than during expiration phases). Therefore, assuming that A2 and P2 components keep approximately the same form (apart from time shifts) in successive S2 sounds, the A2 components are estimated by averaging over the collected S2 sounds and the P2 components are obtained by subtraction.…”

Smart Healthcare

“…In [21], Tang, Chen, and Li presented their research on differentiating aortic and pulmonary components from the second heart sound using respiratory modulation and measurement of respiratory split. The key idea is that the aortic component does not change much in the second heart sound waveform in respiration, while the delay of the pulmonary component is modulated by respiration.…”