AUTHOR=Zhang Anqi , Wang Jiaming , Qu Fei , He Zhaoming 

TITLE=Classification of Children's Heart Sounds With Noise Reduction Based on Variational Modal Decomposition

JOURNAL=Frontiers in Medical Technology

VOLUME=Volume 4 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/medical-technology/articles/10.3389/fmedt.2022.854382

DOI=10.3389/fmedt.2022.854382

ISSN=2673-3129

ABSTRACT=Purpose: Children's heart sound was denoised to improve the performance of the intelligent diagnosis system. Method: A combined noise reduction method based on variational modal decomposition (VMD) and wavelet soft threshold algorithm (WST) was proposed, and used to denoise 103 phonocardiogram samples. Features were extracted after denoising and used for an intelligent diagnosis model to verify the effect of the denoising method. Results: The children's heart sound noises, especially crying noise, were suppressed. The signal-to-noise ratio obtained by the method for normal heart sounds was 14.69 dB at 5 dB Gaussian noise, which was higher than that obtained by using WST only. Intelligent classification showed that the accuracy, sensitivity and specificity of the classification system for congenital heart disease were 92.23%, 92.42%, and 91.89%, respectively, and better than those with WST only. Conclusion: The proposed noise reduction method effectively removes children's heart sound noise and improves the performance of intelligent screening for the children with congenital heart disease.