The mechanism of splitting of the second heart sound in atrial septal defect

Deep learning-based computer-aided heart sound analysis in children with left-to-right shunt congenital heart disease

OBJECTIVE

The purpose of this study was to explore a new algorithm model capable of leverage deep learning to screen and diagnose specific types of left-to-right shunt congenital heart disease (CHD) in children.

METHODS

Using deep learning, screening models were constructed to identify 884 heart sound recordings from children with left-to-right shunt CHD. The most suitable model for each type was summarized and compared with expert auscultation. An exploratory analysis was conducted to assess whether there were correlations between heart sounds and left ventricular ejection fraction (LVEF), pulmonary artery pressure, and malformation size.

RESULTS

The residual convolution recurrent neural network (RCRnet) classification model had higher accuracy than other models with respect to atrial septal defect (ASD), ventricular septum defect (VSD), patent ductus arteriosus (PDA) and combined CHD, and the best auscultation sites were determined to be the 4th, 5th, 2nd and 3rd auscultation areas, respectively. The diagnostic results of this model were better than those derived from expert auscultation, with sensitivity values of 0.932-1.000, specificity values of 0.944-0.997, precision values of 0.888-0.997 and accuracy values of 0.940-0.994. Absolute Pearson correlation coefficient values between heart sounds of the four types of CHD and LVEF, right ventricular systolic pressure (RVSP) and malformation size were all less than 0.3.

CONCLUSIONS

The RCRnet model can preliminarily determine types of left-to-right shunt CHD and improve diagnostic efficiency, which may provide a new choice algorithmic CHD screening in children.

An Intelligent Phonocardiography for Automated Screening of Pediatric Heart Diseases

This paper presents a robust device for automated screening of pediatric heart diseases based on our unique processing method in murmur characterization; the Arash-Band method. The present study modifies the Arash-Band method and employs output of the modified method in conjunction with the two other original techniques to extract indicative feature vectors for the screening. The extracted feature vectors are classified by using the support vector machine method. Results show that the proposed modifications significantly enhances performance of the Arash-Band in terms of the both accuracy and sensitivity as the corresponding effect sizes are sufficiently large. The proposed algorithm has been incorporated into an Android-based tablet to constitute an intelligent phonocardiogram with the automatic screening capability. In order to obtain confidence interval of the accuracy and sensitivity, an inferable statistical test is applied on our database containing the phonocardiogram signals recorded from 263 of the referrals to a hospital. The expected value of the accuracy/sensitivity is estimated to be 87.45 % / 87.29 % with a 95 % confidence interval of (80.19 % - 92.47 %) / (76.01 % - 95.78 %) exhibiting superior performance than a pediatric cardiologist who relies on conventional or even computer-assisted auscultation.

Atrial septal defect: a diagnostic approach

A simple objective screening method for diagnosis of the atrial septal defect (ASD) is needed. Acoustic signals were collected from 61 children with ASD and 60 with a physiological murmur. The second heart sound (S2) and the spectrum of systolic murmur were analysed. A statistical model was designed using stepwise logistic regression analysis. Significant variables distinguishing pathological form normal findings were the interval between the first heart sound and the beginning of systolic murmur or the respiratory variation of S2, and the frequency of the murmur at its maximum intensity. The area under the ROC curve was 0.922; indicating very good fit of the model and the confidence interval was 0.872-0.971. The sensitivity of the model was 91% and the specificity 73%. The analysis of acoustic findings from the heart is a valuable tool in diagnosing ASD. The next step will be automating this process.

Computer-based detection and analysis of heart sound and murmur

To develop a digital algorithm that detects first and second heart sounds, defines the systole and diastole, and characterises the systolic murmur. Heart sounds were recorded in 300 children with a cardiac murmur, using an electronic stethoscope. A Digital algorithm was developed for detection of first and second heart sounds. R-waves and T-waves in the electrocardiography were used as references for detection. The sound signal analysis was carried out using the short-time Fourier transform. The first heart sound detection rate, with reference to the R-wave, was 100% within 0.05-0.2R-R interval. The second heart sound detection rate between the end of the T-wave and the 0.6R-R interval was 97%. The systolic and diastolic phases of the cardiac cycle could be identified. Because of the overlap between heart sounds and murmur a systolic segment between the first and second heart sounds (20-70%) was selected for murmur analysis. The maximum intensity of the systolic murmur, its average frequency, and the mean spectral power were quantified. The frequency at the point with the highest sound intensity in the spectrum and its time from the first heart sound, the highest frequency, and frequency range were also determined. This method will serve as the foundation for computer-based detection of heart sounds and the characterisation of cardiac murmurs.

The forgotten chamber: the importance of the right ventricle

Historically, the right heart was viewed as less important than the left heart in the maintenance of normal overall hemodynamic performance. However, there is now considerable evidence that emphasizes the significance of intact right ventricular (RV) function. The RV's anatomy and physiology are reviewed in order to provide insight into how changes in volume can be accommodated within a low-pressure environment and how this contributes to hemodynamic stability. The interdependent relationship between the right and left ventricles is also explored. The contribution of RV performance to overall hemodynamics is best exemplified when the RV becomes diseased. RV infarction, atrial septal defect, and cor pulmonale are used as examples to illustrate the dramatic sequelae associated with RV dysfunction, as well as to identify the RV's specific adaptive mechanisms.

Assessment of right atrial pressure-volume relations in patients with and without an atrial septal defect

Assessment of the complex relations between pressure and volume in the right atrium has been hampered in the past by difficulties in the measurement of atrial volume. Accordingly, in the present study the dynamics of right atrial pressure-volume relations were examined (with the use of an impedance catheter to measure right atrial volume) in patients with and without an atrial septal defect. Right atrial pressure and impedance volume were measured in 16 patients at the time of cardiac catheterization with the use of a multi-electrode impedance catheter to provide continuous, on-line, pressure-volume data. Eleven patients without evidence of an interatrial shunt were examined during normal respiration and during the Valsalva maneuver and contrasted with five patients with an atrial septal defect documented by oxygen saturation step-up and echocardiographic studies. Right atrial pressure-volume diagrams in patients without an atrial septal defect exhibited the normal figure eight pattern, with an A loop (atrial contraction) and a V loop (passive filling), corresponding to the A wave and V wave of right atrial pressure, respectively. During inspiration, mean right atrial pressure decreased and mean right atrial volume increased, consistent with augmented venous return. With the Valsalva maneuver, right atrial pressure increased and both right atrial stroke volume and mean right atrial volume decreased compared with baseline. Patients with an atrial septal defect demonstrated baseline pressure-volume diagrams similar to those of patients without an interatrial shunt. However, no change in mean right atrial volume occurred with either respiration or the Valsalva maneuver despite changes in right atrial pressure similar to those seen inpatients without an atrial septal defect.(ABSTRACT TRUNCATED AT 250 WORDS)

Right ventricular systolic time intervals: comparison of echocardiographic and Doppler-derived values

Although the clinical utility of right ventricular (RV) systolic time intervals (STI) has been well documented, their use is at times limited by an inability to obtain adequate M-mode echocardiographic images of the pulmonary valve. Therefore the relationship between the pulmonary artery Doppler flow tracing and the timing of pulmonary valve opening and closure was investigated to determine if the more readily available Doppler recording could be utilized for determining RV STIs. We compared RV preejection period (PEP), ejection time (VET), and PEP/VET ratio derived from the pulsed Doppler frequency-time curve recorded in the main pulmonary artery with measurements from a simultaneously recorded M-mode pulmonary valve echocardiogram (Echo). The nadir of the late systolic flow reversal, rather than the point at which the frequency spectrum crosses the zero baseline, correlated best with the point of pulmonary valve closure. By the use of this method for determining end-systole, all three Doppler-derived measurements were highly correlated with the values from the pulmonary valve echocardiogram: PEPEcho = 1.01 PEPDoppler - 3.1 (r = 0.990, S.E.E. PEPEcho = 2.7 msec); VETEcho = 0.98 VETDoppler + 10.2 (r = 0.998, S.E.E. VETEcho = 3.3 msec); (PEP/VET)Echo = 0.95 (PEP/VET)Doppler + 0.007 (r = 0.980, S.E.E. (PEP/VET)Echo = 0.012 msec). The Doppler velocity-time curve provides accurate measurement of RV STIs that can be recorded with relative ease compared with the pulmonary valve echocardiogram. This expanded availability of RV STIs permits an improved ability to investigate the hemodynamic determinants of these indices and their relation to the status of the pulmonary vasculature and right ventricular performance.