A novel methodology for evaluation of S2 wide split via estimated parameters

Background and objective: Aimed at the shortcomings of using time interval (T-A2 -> P2) between the sounds produced by the aortic valve closure (A(2)) and the pulmonary valve closure (P-2) to detect the wide splitting of the second heart sound (S-2), which are the T-A2 -> P2 easily influenced by the heartbeat and not easily distinguished from the fixed splitting of S-2 without considering the entire respiratory phase, and from the third heart sound (S-3), this study proposes a novel methodology to detect the wide splitting of S-2 using an estimated split coefficient of S-2 (S-2split) combined with an adaptive number (N-Ada) of S-2.Methodology: The methodology is orderly summarized as follows: 1 Stage 1 describes the segmentation-based S-2 automatic location and extraction. 2 A Gaussian mixture model (GMM)-based regression model for S-2 is proposed to estimate the positions of A(2) and P-2, then an overlapping rate (OLR)-based S(2split )and the T-A2 -> P2 are estimated, and finally, a N-Ada-S-2 is automatically determined to calculate the statistics of S-2split and T-A2 -> P2. 3 In stage 3, based on the combination of estimated features, the detection of wide splitting of S-2 is determined.Results: The performance is evaluated using a total of 3350-period heart sounds from 72 patients, with an overall accuracy of 100%, F-1=1 and a Cohen's kappa value (kappa) of 1.Discussion: The significant contributions are highlighted: 1 A novel GMM-based efficient methodology is proposed for estimating the characteristics of A(2) and P-2. 2 A novel OLR-based S-2split is defined to replace the current state-of-the-art criterion for evaluating the split degree of S-2. 3 Considering respiration phases combined with CR are proposed for the high-precision diagnosis of S-2 wide split.

Automated summary

This study proposes a novel methodology to detect the wide splitting of the second heart sound using an estimated split coefficient of S-2 combined with an adaptive number of S-2. The overall accuracy of this method is 100%, indicating its high precision in diagnosing the wide split of S-2.