An artificial intelligence (AI)–based imaging tool that analyzes coronary CT scans can predict future cardiovascular events and death in patients with suspected stable coronary artery disease (CAD), according to new data presented at EACVI 2025, the flagship congress of the European Association of Cardiovascular Imaging (EACVI).
The findings suggest that AI-derived measurements of coronary blood flow could help identify high-risk patients earlier and support more personalized treatment strategies.
Moving beyond anatomy to functional risk
Stable CAD is a common condition characterized by recurrent episodes of chest pain, often presenting as angina. Coronary computed tomography angiography (CCTA) is widely used as a first-line, noninvasive test for patients with suspected disease, as it provides detailed images of coronary artery blockages. However, CCTA alone has limited ability to determine whether those blockages significantly reduce blood flow – an essential factor in diagnosing angina and assessing future risk.
To address this limitation, an AI-based tool has been developed to analyze CCTA images and estimate coronary blood flow, known as CT-derived fractional flow reserve (FFR-CT). While FFR-CT is already used to guide diagnostic decision-making, its prognostic value has remained less well defined.
“We already know that FFR-CT is valuable for the diagnosis of stable CAD, but whether FFR-CT could also be used prognostically, to predict future major cardiovascular events, is not fully understood,” said study presenter Doctor Jack Bell from the Liverpool Heart and Chest Hospital, UK.
Large national cohort with long-term follow-up
The analysis drew on data from the nationwide FISH&CHIPS observational study, which included all patients who underwent FFR-CT analysis across 27 sites in England. Unlike earlier studies, the large cohort and extended follow-up allowed researchers to evaluate whether FFR-CT adds predictive value beyond traditional cardiovascular risk factors.
“Previous studies have had small patient numbers, short follow-up and investigated combined cardiovascular outcomes,” Doctor Bell explained. “We performed an analysis from a national FISH&CHIPS population, which was large enough to determine whether FFR-CT adds incremental value to traditional cardiovascular risk factors in predicting cardiovascular outcomes and death.”
Of more than 90,000 patients who underwent CCTA, 7,836 received FFR-CT analysis. The median age was 63 years, and 37.4% were female. Patients were followed for a median of 3.1 years.
Lower coronary blood flow linked to worse outcomes
During follow-up, researchers recorded 191 myocardial infarctions, 1,573 revascularization procedures, 74 cardiovascular deaths, and 261 deaths from any cause.
FFR-CT values were categorized as normal, borderline, reduced, or severely reduced. When measured near the site of coronary narrowing, lower FFR-CT values were consistently associated with higher event rates. Risk increased stepwise across all categories for myocardial infarction, revascularization, cardiovascular mortality, and all-cause mortality.
For example, myocardial infarction occurred in 1.0% of patients with normal FFR-CT, compared with 5.2% of those with severely reduced values. Patients in the lowest FFR-CT category had a fourfold higher risk of heart attack and a threefold higher risk of cardiovascular death.
These associations remained significant after adjustment for established risk factors, including age, sex, hypertension, diabetes, and dyslipidemia.
Implications for personalized patient care
Senior author Professor Timothy Fairbairn, also from the Liverpool Heart and Chest Hospital, emphasized the clinical significance of the findings. “Adding to its diagnostic abilities, this study is the first to provide conclusive evidence of FFR-CT’s prognostic power, independent of other risk factors,” he said. “We observed that even so-called ‘borderline’ FFR-CT was associated with worse outcomes compared with normal values, but the individuals with the lowest values have the highest risk. FFR-CT could be used to inform personalized risk assessment, allowing us to provide more intensive bespoke treatment to those at high risk.”
Additional results from the FISH&CHIPS program, including an analysis of the cost-effectiveness of FFR-CT–guided care, will also be presented at EACVI 2025.
