Deep learning model diagnosed moderate-severe mitral regurgitation with 91% accuracy (AUC 0.98) and tricuspid regurgitation with 84% accuracy (AUC 0.96).
Does a deep learning artificial intelligence algorithm accurately diagnose the severity of mitral and tricuspid regurgitation from echocardiograms compared to ground truth evaluations?
A deep learning algorithm demonstrated high diagnostic accuracy for identifying clinically significant mitral and tricuspid regurgitation from echocardiograms, highlighting its potential to complement expert evaluations.
Absolute Event Rate: 0% vs 0%
Abstract Background Mitral regurgitation (MR) and tricuspid regurgitation (TR) are prevalent valvular heart diseases associated with significant morbidity and mortality. Traditional echocardiography faces limitations in availability, cost, consistency, and reliability, leading to misdiagnosis and undertreatment. The application of artificial intelligence (AI) to echocardiographic scans has the potential to address these challenges. Methods This study evaluates the performance of an AI algorithm on an external population. The algorithm utilizes deep learning networks to analyze echocardiographic exams for diagnosing atrioventricular valve disorders. We tested the algorithm on transthoracic echocardiography data collected from a single center between 2013 and 2023. The model's performance was compared to ground truth values using two classification schemes: distinguishing between normal-mild and moderate-severe regurgitation, and categorizing results into four groups: normal, mild, moderate, and severe. Results The MR cohort included 280 patients, while the TR cohort comprised 298 patients. The model demonstrated a robust ability to identify clinically significant (moderate and above) atrioventricular valve regurgitation. The MR model achieved an area under the curve (AUC) of 0.98 (95% CI: 0.97–0.99), with 91% accuracy, 95% sensitivity, and 89% specificity. In comparison, the TR model exhibited an AUC of 0.96 (95% CI: 0.94–0.98), with 84% accuracy, 91% sensitivity, and 80% specificity. Conclusion The model demonstrated high diagnostic accuracy and reliability in assessing atrioventricular valve regurgitation severity, highlighting its potential as a valuable clinical tool. The findings underscore the role of AI in complementing expert evaluations and improving access to effective diagnostics, with future applications potentially including point-of-care diagnosis and monitoring of disease progression.
Cohen et al. (Sat,) reported a other. Deep learning model diagnosed moderate-severe mitral regurgitation with 91% accuracy (AUC 0.98) and tricuspid regurgitation with 84% accuracy (AUC 0.96).