AI-based tool predicts future cardiovascular events in patients with angina
Reduced coronary blood flow, measured with an artificial intelligence-based imaging tool, predicted future cardiovascular events in patients with suspected stable coronary artery disease.These findings were presented at EACVI 2025, the flagship congress of the European Association of Cardiovascular Imaging (EACVI), a branch of the European Society of Cardiology (ESC).
Stable coronary artery disease (CAD) refers to the common syndrome of recurrent, transient episodes of chest symptoms, often manifesting as angina. Coronary computed tomography angiography (CCTA) is a non-invasive heart scan that is used as the first-line investigation for patients with suspected stable CAD. While CCTA clearly shows blockages in coronary arteries, it is limited in its ability to estimate reduced blood flow, which is necessary to diagnose angina. An artificial intelligence-based tool has been developed that analyses CCTA images and provides an estimate of blood flow, termed CT-derived fractional flow reserve (FFR-CT). The FISH&CHIPS observational study has shown that including FFR-CT as a decision-making tool in the diagnosis of stable CAD reduces the number of subsequent invasive and non-invasive tests performed.2
“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,” explained study presenter, Doctor Jack Bell from the Liverpool Heart and Chest Hospital, UK. “Previous studies have had small patient numbers, short follow-up and investigated combined cardiovascular outcomes. 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.”
Data from all patients receiving FFR-CT analysis (HeartFlow) for stable CAD at 27 English sites in the FISH&CHIPS observational cohort study were included in the presented analysis. FFR-CT measurements were related to the individual outcomes of myocardial infarction (MI), cardiovascular mortality, all-cause mortality and whether the patient underwent subsequent revascularisation (coronary artery bypass grafting or stenting). FFR-CT measurements were divided into subgroups: normal (FFR-CT >0.8), borderline (0.71–0.8), reduced (0.51–0.7) and severely reduced (≤0.5).
Of 90,553 patients receiving CCTA, 7,836 patients underwent FFR-CT. They had a median age of 63 years and 37.4% were female. At a median follow up of 3.1 years, there were 191 MIs (2.4%), 1,573 revascularisations (20.1%), 74 cardiovascular deaths (0.9%) and 261 all-cause deaths (3.3%).
When FFR-CT was measured close to the stenosis (blockage) site, lower values were associated with higher cardiovascular event rates: FFR-CT categories incrementally stratified risk of MI (p<0.001), revascularisation (p<0.001), cardiovascular mortality (p<0.001) and all-cause mortality (p=0.002) over time. As an example, MI occurred in 1.0% of patients with normal FFR-CT, 2.0% of patients with borderline FFR-CT, 3.9% of those with reduced FFR-CT and 5.2% of those with severely reduced FFR-CT. Patients with the lowest FFR-CT values had a four-fold increased risk of a heart attack and a three-fold increased risk of dying from a heart attack.
FFR-CT less than normal was associated with an increased risk for future MI and revascularisation, with severely reduced FFR-CT also associated with cardiovascular death and death. This was independent of traditional cardiovascular risk factors such as age, sex, hypertension, diabetes and dyslipidaemia.
Senior author, Professor Timothy Fairbairn, also from the Liverpool Heart and Chest Hospital, concluded: “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. 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 personalised risk assessment, allowing us to provide more intensive bespoke treatment to those at high risk.”
Results of an analysis investigating the cost-effectiveness of using FFR-CT in the diagnosis of stable CAD will also be presented at EACVI 2025.
