Congenital Heart Disease Classification Using Phonocardiograms: A Scalable Screening Tool for Diverse Environments
This research addresses the need for scalable and cost-effective screening tools for CHD in resource-limited global health settings, offering a potential AI-driven solution to enhance clinical decision support.
The study tackled the problem of early detection of congenital heart disease (CHD) using phonocardiogram signals, achieving high accuracy of 94.1% on a primary dataset and demonstrating robust performance across diverse datasets and conditions, including low-quality recordings.
Congenital heart disease (CHD) is a critical condition that demands early detection, particularly in infancy and childhood. This study presents a deep learning model designed to detect CHD using phonocardiogram (PCG) signals, with a focus on its application in global health. We evaluated our model on several datasets, including the primary dataset from Bangladesh, achieving a high accuracy of 94.1%, sensitivity of 92.7%, specificity of 96.3%. The model also demonstrated robust performance on the public PhysioNet Challenge 2022 and 2016 datasets, underscoring its generalizability to diverse populations and data sources. We assessed the performance of the algorithm for single and multiple auscultation sites on the chest, demonstrating that the model maintains over 85% accuracy even when using a single location. Furthermore, our algorithm was able to achieve an accuracy of 80% on low-quality recordings, which cardiologists deemed non-diagnostic. This research suggests that an AI- driven digital stethoscope could serve as a cost-effective screening tool for CHD in resource-limited settings, enhancing clinical decision support and ultimately improving patient outcomes.