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.

Automated summary

The study aimed to explore a new algorithm model that leverages deep learning for screening and diagnosing left-to-right shunt congenital heart disease (CHD) in children. With deep learning, screening models were constructed, successfully identifying 884 heart sound recordings from children with this type of CHD. The RCRnet model showed higher accuracy in diagnosing various types of CHD compared to expert auscultation. Additionally, there were weak correlations between heart sounds and LVEF, RVSP, and malformation size.