Accurate left ventricular ejectionfraction (LVEF) assessment is crucial in acute coronary syndrome (ACS)management but traditional methods like echocardiography (TTE) andventriculography have limitations such as risks, contrast exposure, andlogistical delays.

The CathEF study introduced adeep-learning algorithm integrated with the PACS-AI (www.pacsai.co) platform,providing real-time LVEF estimates directly from routine coronary angiographyvideos, without extra catheterization or contrast.

Conductedprospectively at two Canadian tertiary care institutions—the Montreal HeartInstitute and the University of Ottawa Heart Institute—the CathEF studyenrolled 207 patients presenting with ACS undergoing coronary angiography. ThePACS-AI platform enabled the instant analysis of angiographic videos acquiredduring routine coronary procedures, allowing clinicians to receive rapidfeedback on left ventricular function status at the point of care. CathEFpredictions were validated against conventional TTE measurements performedwithin seven days following angiography.

• CathEF achieved high accuracy:
  • AUROC 0.84 for detecting LVEF ≤50%
  • o    AUROC 0.90 for detecting LVEF ≤40%
• Comparable accuracy to ventriculography (AUROC 0.90).
• Performance improved by averaging multiple angiographic views.
• Reduced accuracy observed:
  • STEMI patients (AUROC 0.76 for LVEF ≤50%)
  • ACS culprit lesion in RCA (AUROC 0.73 for LVEF ≤50%)
  • TTE delayed >2 days post-angiography (AUROC 0.58 for LVEF ≤50%, 0.65for ≤40%) perhaps due to LVEF recovery.

The integration of CathEF with the PACS-AI (www.pacsai.co) platform presents significant clinical implications. By enabling real-time detection of left ventricular dysfunction during coronary angiography, CathEF supports rapid clinical decision-making, potentially expediting subsequent diagnostic testing or interventions. Furthermore, it may reduce the need for unnecessary inpatient echocardiography in patients identified as having normal LVEF, streamlining patient management, and reducing healthcare costs. Decision curve analyses further underscored these clinical benefits, demonstrating a clear net benefit of using CathEF for screening, especially in settings where comprehensive echocardiographic evaluations may not be readily accessible.

‍

In summary, the CathEF algorithm, powered by PACS-AI, represents a meaningful advancement in cardiovascular imaging, combining sophisticated artificial intelligence with routine clinical workflows to improve patient care in acute cardiac settings.

Published in NEJM AI, 2025. Funded by the Canadian Institute for Advanced Research Solution Network on Integrated AI for Health Imaging, Institute for Data Valorisation (IVADO) and collaborators.

‍