Prospective evaluation of an AI algorithm for real-time LVEF assessment in acute coronary syndrome using left coronary angiograms: the CathEF multicenter study

Abstract Background Acute assessment of Left Ventricular Ejection Fraction (LVEF) is critical at time of percutaneous coronary intervention to optimize clinical management. The CathEF artificial intelligence algorithm offers a novel approach for real-time, intra-procedural LVEF assessment using routinely obtained left coronary artery angiograms without additional dye use[1]. Our objective was to evaluate the real-time application of the CathEF algorithm for LVEF measurement during coronary angiogram procedures in patients with acute coronary syndrome (ACS) and to compare its performance with transthoracic echocardiography (TTE) and left ventriculography. Methods The CathEF study is a prospective multi-center study that recruited ACS patients undergoing coronary angiography at two institutions from July 2022 to July 2023. Using the CathEF algorithm and the PACS-AI software, we analyzed 2 to 4 left coronary angiogram videos per procedure for LVEF assessment to compare to ventriculography (if indicated) and echocardiography performed during the same hospitalization. Operators were blinded to the CathEF AI-generated results. The primary measure was the algorithm's area under the receiving-operating characteristic curve (AUC) in identifying LVEF