A deep learning model detected rheumatic heart disease on pediatric echocardiograms with an area under the receiver operating characteristics curve of 0.84, precision of 0.78, and recall of 0.98.
Observational (n=511)
Does an artificial intelligence deep learning model accurately detect rheumatic heart disease and analyze mitral regurgitation on echocardiograms in children compared to expert cardiologists?
Artificial intelligence and deep learning models can accurately detect rheumatic heart disease and analyze mitral regurgitation on pediatric echocardiograms, offering a promising approach to scale screening efforts.
Effect estimate: AUC 0.84
Background Identification of children with latent rheumatic heart disease (RHD) by echocardiography, before onset of symptoms, provides an opportunity to initiate secondary prophylaxis and prevent disease progression. There have been limited artificial intelligence studies published assessing the potential of machine learning to detect and analyze mitral regurgitation or to detect the presence of RHD on standard portable echocardiograms. Methods and Results We used 511 echocardiograms in children, focusing on color Doppler images of the mitral valve. Echocardiograms were independently reviewed by an expert adjudication panel. Among 511 cases, 229 were normal, and 282 had RHD. Our automated method included harmonization of echocardiograms to localize the left atrium during systole using convolutional neural networks and RHD detection using mitral regurgitation jet analysis and deep learning models with an attention mechanism. We identified the correct view with an average accuracy of 0.99 and the correct systolic frame with an average accuracy of 0.94 (apical) and 0.93 (parasternal long axis). It localized the left atrium with an average Dice coefficient of 0.88 (apical) and 0.9 (parasternal long axis). Maximum mitral regurgitation jet measurements were similar to expert manual measurements ( P value=0.83) and a 9‐feature mitral regurgitation analysis showed an area under the receiver operating characteristics curve of 0.93, precision of 0.83, recall of 0.92, and F1 score of 0.87. Our deep learning model showed an area under the receiver operating characteristics curve of 0.84, precision of 0.78, recall of 0.98, and F1 score of 0.87. Conclusions Artificial intelligence has the potential to detect RHD as accurately as expert cardiologists and to improve with more data. These innovative approaches hold promise to scale echocardiography screening for RHD.
Brown et al. (Tue,) conducted a observational in Rheumatic heart disease (n=511). Deep learning model for RHD detection vs. Expert adjudication was evaluated on Detection of rheumatic heart disease (AUC 0.84). A deep learning model detected rheumatic heart disease on pediatric echocardiograms with an area under the receiver operating characteristics curve of 0.84, precision of 0.78, and recall of 0.98.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: