Research paper presents a machine learning approach combining deep learning and handcrafted features to automatically detect pediatric congenital heart disease from phonocardiogram recordings. The dual-feature fusion method aims to improve diagnostic accuracy for non-invasive cardiac screening in children.
Research
Automated detection of pediatric congenital heart disease from phonocardiograms using deep and handcrafted feature fusion
Researchers combine deep learning with handcrafted audio features to enable automated detection of congenital heart disease in children from phonocardiogram recordings, paving the way for accessible non-invasive cardiac screening.
Thursday, April 30, 2026 12:00 PM UTC2 MIN READSOURCE: arXiv CS.LG (Machine Learning)BY sys://pipeline
Tags
research