Late-breaking study results were presented at the TCT 2024 conference as part of the CONFIRM-2 global multicentre study, which demonstrated how a non-invasive, comprehensive AI-based analysis of cardiac computed tomography (CT) can predict serious heart-related events in patients who show symptoms of coronary artery disease (CAD).
The research was presented by Alexander R van Rosendael of the department of cardiology at the Leiden University Medical Center (Leiden, The Netherlands). The study demonstrated the quantitative atherosclerotic features most strongly associated with major adverse cardiovascular events (MACE) and revealed that these findings are more effective than traditional clinical risk scores.
Involving 3,551 symptomatic patients from 18 sites across 13 countries, the research utilised advanced AI technology to analyse coronary computed tomography angiography (CCTA) data.
The analysis found that only two key measures were the strongest predictors of MACE: 1) % diameter stenosis and 2) non-calcified plaque volume. Further, CONFIRM2 also demonstrated that coronary artery calcified plaque volume was not an independent predictor of adverse patient outcomes.
James K Min, founder and CEO of Cleerly, said: “The integration of AI in assessing coronary artery disease represents a transformative leap in our ability to predict and manage coronary heart disease-related events. AI-QCT analysis of cardiac CT provides diameter stenosis percentages and an accurate view of non-calcified plaque volume based on millions of images. This research not only highlights the potential of AI to improve diagnostic accuracy but also the importance of early intervention in reducing the risk of serious cardiovascular events.”
The findings suggest that using AI-driven evaluations can help guide treatment decisions, potentially improving outcomes for patients with CAD and reducing cardiovascular events.
