AI Detection of Cardiac Amyloidosis

AI Detection of Cardiac Amyloidosis   Guest: Patricia Pellikka, M.D. Host: Malcolm Bell, M.D.   Dr. Patricia Pellikka dives into the AI model she helped build. Working with an AI echo company, Ultromics Ltd., her team built an AI echo model to detect cardiac amyloidosis. The model works from an apical 4 chamber videoclip and was approved by the FDA via the breakthrough pathway. They have validated it internationally in a population with 22% prevalence of cardiac amyloidosis and it had a sensitivity of 85%, specificity 93%, PPV 78%, NPV 96%, and AUC 0.93.  The performance of the model was consistent across cardiac amyloid types; among AL, wild type ATTR, and hereditary ATTR, the sensitivity was 84%, 85%, and 86%, respectively.  The performance of the model was also superior to previously validated scores which use clinical and echocardiographic variables for detecting cardiac amyloidosis. The results of the study were published online in the European Heart Journal in July.   Topics Discussed: You have built an AI echo model to detect cardiac amyloidosis.  How did you get into this? Tell us about the model that you built. How did you validate it? How does the model compare with other screening methods for detecting cardiac amyloidosis? What are the next steps for your research?   Connect with Mayo Clinic's Cardiovascular Continuing Medical Education online at https://cveducation.mayo.edu or on Twitter @MayoClinicCV and @MayoCVservices. LinkedIn: Mayo Clinic Cardiovascular Services Cardiovascular Education App: The Mayo Clinic Cardiovascular CME App is an innovative educational platform that features cardiology-focused continuing medical education wherever and whenever you need it. Use this app to access other free content and browse upcoming courses. Download it for free in Apple or Google stores today! No CME credit offered for this episode.   Podcast episode transcript found here.