Cleerly's AI plaque analysis beats usual chest-pain care in first randomised trial

Cleerly said care guided by its AI-based analysis of coronary plaque beat usual care in PARAMOUNT, the first randomised trial of the approach, according to a company release. The results were presented as Late-Breaking Science at the American Heart Association Scientific Sessions 2026 in Chicago.

The trial randomised 530 symptomatic outpatients with suspected coronary artery disease and elevated LDL cholesterol at 21 sites between January 2025 and February 2026, comparing plaque-based care guided by Cleerly's AI quantitative CT analysis with usual care based on stress testing. On the hierarchical composite endpoint at 180 days, plaque-based care was favoured with a win ratio of 2.00. Women made up 57% of participants.

Greater certainty about whether chest pain was caused by coronary disease was the largest contributor to the result. In the AI-guided arm, use of lipid-lowering therapy rose from 31% to 75% after testing, against 32% to 47% with usual care. Among patients who had invasive angiography, 38% in the AI-guided arm did not go on to stenting or bypass surgery, compared with 60% in the usual care arm.

The results have not yet been peer reviewed and should be considered preliminary, the company said; full results are expected to be published in early 2027.