AI analysis of a single apical 4-chamber echo view detected mitral regurgitation (AUC 0.883), tricuspid regurgitation (AUC 0.913), and right ventricular dysfunction (AUC 0.942) with high accuracy.
Does a Deep Neural Network analyzing a single apical 4-chamber echocardiographic view accurately assess significant valvular disease and ventricular function compared to standard multi-view echocardiography?
An AI model can accurately detect significant valvular disease and ventricular dysfunction using only a single apical 4-chamber echocardiographic view, potentially streamlining point-of-care cardiac assessments.
Absolute Event Rate: 0% vs 0%
Abstract Background With the rising prevalence and healthcare burden of structural heart disease and heart failure, artificial intelligence (AI) is playing an increasingly prominent role in echocardiography, with promising potential to enhance diagnostic accuracy and efficiency. Purpose We hypothesized that a Deep Neural Network (DNN) could be trained to identify and assess significant cardiac dysfunction using only a single apical 4-chamber echocardiographic view, rather than a comprehensive multi-view standard transthoracic echocardiogram. Methods Echocardiographic reports and corresponding images from 121,767 unique patients, linked to clinical data (2007–2022), were analyzed by a designated DNN. A validation cohort, consisting solely of apical 4-chamber view clips, was used to assess the presence of significant (mild to moderate up to severe) mitral regurgitation (MR), tricuspid regurgitation (TR), right ventricular dysfunction (RVD), and assessment of left ventricular ejection fraction (LVEF). Additionally, a second cohort of 209 point-of-care focused cardiac ultrasound (FoCUS) examinations, performed by non-cardiologists, was analyzed by the DNN. Results For mitral regurgitation, the model achieved an AUC of 0.883, with a sensitivity of 0.744 and specificity of 0.844 (N = 20,313). For tricuspid regurgitation, it yielded an AUC of 0.913, with a sensitivity of 0.766 and specificity of 0.887 (N = 21,742). In assessing right ventricular dysfunction, the DNN reached an AUC of 0.942, with a sensitivity of 0.757 and specificity of 0.939 (N = 6,010). For LVEF assessment, the root mean square error (RMSE) was 4.78, and the mean absolute error (MAE) was 3.34 (N = 23,350). Conclusion AI-driven analysis of a single apical 4-chamber echocardiographic view can provide valid estimates of significant valvular disease, right ventricular dysfunction, and LVEF with high sensitivity and specificity. These findings suggest that AI-based approaches could enable more efficient and widespread cardiac assessment.
Fisher et al. (Sat,) reported a other. AI analysis of a single apical 4-chamber echo view detected mitral regurgitation (AUC 0.883), tricuspid regurgitation (AUC 0.913), and right ventricular dysfunction (AUC 0.942) with high accuracy.