PARAMOUNT, the First Randomized Trial of AI-Enabled Plaque-Based Care, Meets Primary Endpoint in Late-Breaking Results at AHA 2026

Plaque-guided care improved diagnostic certainty and increased use of preventive therapy compared with usual care in patients with suspected coronary artery disease

DENVER, November 7, 2026 - Cleerly, a leader in advanced cardiovascular imaging analysis, today presented primary results from PARAMOUNT, the first randomized trial of AI-QCT-guided care against usual care, as Late-Breaking Science at the American Heart Association (AHA) Scientific Sessions 2026 in Chicago. Compared with usual care based on stress testing, care guided by AI-based quantitative coronary CT analysis (AI-QCT) improved diagnostic certainty and led to more patients receiving lipid-lowering therapy.

PARAMOUNT is a prospective, multicenter, open-label randomized trial of symptomatic outpatients with suspected coronary artery disease (CAD), elevated LDL-C (≥100 mg/dL), and no prior history of CAD. Between January 2025 and February 2026, 530 participants at 21 sites were randomized to either plaque-based care guided by AI-QCT, including quantitative plaque and plaque-based ischemia assessment, or to usual care guided by functional stress testing. Preliminary results are based on 523 participants with locked data at the time of analysis.

Women made up 57% of participants, a rare majority in cardiovascular research, where women have historically been underrepresented. The median age was 57, and median baseline LDL-C cholesterol was 127 mg/dL.

Key Findings

• PARAMOUNT met its primary endpoint. On the prespecified hierarchical composite endpoint at 180 days, Plaque-based care was favored over usual care with a win ratio of 2.00 (95% CI 1.37 to 2.56, p<0.0001). In unmatched patient comparisons, the plaque-based care patient had the better result 46.7% of the time, compared with 23.4% for usual care.
• Diagnostic certainty and lowering LDL-C drove the result. Improved certainty about whether a patient's chest pain was caused by CAD was the largest contributor to the primary endpoint, with a win difference of 16.6 percentage points.
• Many more patients started lipid-lowering therapy. In the AI-QCT-guided arm, lipid-lowering therapy use rose from 31% at baseline to 75% after testing, compared with 32% to 47% in the usual care arm. Reductions in LDL-C also favored AI-QCT-guided care.
• Fewer invasive angiograms ended without intervention. Among patients who underwent invasive coronary angiography, 38% in the AI-QCT-guided arm did not go on to revascularization with PCI or bypass surgery (CABG), compared with 60% in the usual care arm.
• Women were well represented. Of the 523 participants, 300 were women.

"For decades, we've evaluated patients with chest pain by looking for blockages or reduced blood flow," said Todd C. Villines, MD, FACC, FAHA, MSCCT, co-principal investigator of PARAMOUNT and the Donald C. Barnes Professor of Cardiology in Internal Medicine at the University of Virginia. "PARAMOUNT shows that when we measure plaque directly and use it to guide care, physicians gain clearer answers and patients are far more likely to start preventive therapy. Importantly, plaque-based care resulted in significantly fewer patients without obstructive CAD among those referred to the cath lab and did not increase overall rates of catheterizations or revascularizations. We're also proud that more than half of our participants were women, a group too often underrepresented in cardiovascular trials."

Udo Hoffmann, MD, MPH, Chief Medical, Scientific, and AI Officer at Cleerly, added, "PARAMOUNT has demonstrated for the first time how this novel approach supports clinicians in 'Diagnosing, Staging, and Treating' CAD and unlocks the potential benefits of both medical management and interventional treatment for patients with stable chest pain."

The findings suggest that AI-QCT plaque assessment can give physicians greater certainty when evaluating chest pain, help more patients start preventive treatment early, and support more targeted use of invasive procedures. Full results are expected to be published in early 2027.

Cleerly's science continues this afternoon at 3:15 p.m. CT in Learning Studio 3, where TRANSFORM investigators will discuss diagnosing, staging, and treating CAD. Note that this event is not part of the official Scientific Sessions Conference 2026 as planned by the American Heart Association Committee on Scientific Sessions Programming. Attendees can also see AI-QCT at HIPod 8 in the Health Innovation Pavilion through November 9.

PARAMOUNT results presented at AHA Scientific Sessions 2026 have not yet been peer reviewed and should be considered preliminary until published.

About Cleerly

Cleerly is the company on a mission to eliminate heart attacks by creating a new standard of care for heart disease. Through its FDA-cleared solutions driven by artificial intelligence, Cleerly supports comprehensive phenotyping of coronary artery disease, as determined from advanced noninvasive CT imaging. Cleerly's approach is grounded in science, based on millions of images from over 40,000 patients. Led by a world-class clinical and technical team, Cleerly enhances health literacy for each and every stakeholder in the coronary care pathway. For more information, please visit: cleerly.com.