Research Progress of Intelligent Auscultation Technology Based on Deep Learning in Congenital Heart Disease

Congenital heart disease (CHD) is one of the most common congenital birth defects. With the deepening of people’s understanding of CHD disease and the continuous improvement of screening methods, children with CHD have been able to receive diagnosis and treatment at an early stage, thus improving the survival rate and quality of life. The main means of early screening of CHD are heart sound auscultation and percutaneous oxygen saturation detection. At present, there are relatively mature commercial equipment for transcutaneous oximetry, but the heart sound assessment is greatly affected by personal experience and external factors, which is prone to misdiagnosis and missed diagnosis. In recent years, the continuous development of artificial intelligence (AI) makes the digital collection, storage, and analysis of heart sound signals, and then makes the intelligent auscultation-assisted diagnosis technology of cardiovascular diseases possible. At present, it is based on deep learning. DL’s AI algorithm has been extensively studied in CHD cardiac sound auscultation assisted diagnosis, but most of them are still in the algorithm research stage and are implemented based on specific data sets, and have not been verified in clinical Settings. In this paper, the development and research status of AI auscultation technology at the current stage are reviewed, the development of DL based intelligent auscultation technology in the field of CHD in recent years is summarized and the problems to be solved in the clinical application of heart sound auscultation are proposed.