Deep Learning Prediction of Left Ventricular Dimensions and Screening for Cardiac Amyloidosis and Hypertrophic Cardiomyopathy

In 3 independent cohorts of representative patients seen at academic medical centers, a deep learning algorithm was able to accurately assess left ventricular dimensions, including cavity size and left ventricular wall thickness. Among patients with increased left ventricular wall thickness, the deep learning algorithm was able to subsequently identify patients with cardiac amyloidosis and hypertrophic cardiomyopathy who would benefit from referral to specialty clinics.

This video illustrates how the prediction of the deep learning algorithm in assessing left ventricular dimensions. Key points along the septal wall and left ventricular posterior wall are identified, with a heatmap showing potential areas for annotation and subsequent measurements from the deep learning algorithm. Because the model can systematically measure each frame of the video, beat-by-beat assessment of left ventricular dimensions is made possible, enabling higher accuracy and precision.

Click the Related Article link for full details.