New data highlight how Heartflow's AI software drives major shifts in heart care
Heartflow has unveiled final results from its landmark DECIDE Registry, highlighting how its artificial intelligence (AI)-powered Heartflow Plaque Analysis software can significantly influence treatment decisions for patients with suspected coronary artery disease (CAD).
The data, presented at the Society of Cardiovascular Computed Tomography (SCCT) 2025 Annual Scientific Meeting, show that Plaque Analysis prompted changes in medical management for more than half of patients, providing improved care compared to what would have occured if clinicians only had access to coronary computed tomography angiography (CCTA) alone.
The AI DErived Plaque Quantification: CCTA and AI-QCPA for Determining Effective CAD Management (DECIDE) Registry is the largest prospective study of its kind, enrolling approximately 20,000 patients at more than 30 clinical sites across the United States. A key presentation of the findings comes from a cohort of 972 patients across 15 sites, shared by Sarah Rinehart, MD, medical director of cardiovascular imaging at Charleston Area Medical Center in Charleston, West Virginia, and a co-lead principal investigator of the registry.
One of the registry's most significant findings was that patients whose care was guided by Heartflow Plaque Analysis, including the company’s new Plaque Staging tool, saw their LDL cholesterol drop by an average of 18.7 mg/dL. This translated to an estimated 15% reduction in cardiac event risk. Notably, drops were seen even among patients with no calcified plaque, where 30% experienced a change in management.
“These data confirm what we’re seeing in clinical practice, Heartflow Plaque Analysis provides individualized insights that go beyond what a traditional analysis of a patient’s risk factors or CCTA alone can show,” Rinehart said in a statement. “By quantifying plaque burden and characterizing higher-risk non-calcified plaque types, Heartflow’s technology empowers physicians to personalize care and intervene earlier, which can change the trajectory of a patient’s coronary health.”
The registry’s primary endpoint focused on changes in clinical management. Secondary endpoints assessed clinical outcomes, biomarkers and safety measures such as major adverse cardiovascular events (MACE), including heart attacks and urgent revascularization procedures.
AI-driven plaque evaluations offer personalized risk scores
The conventional risk factors of age, smoking, hypertension and family history are useful at the population level, but often fall short when predicting risk for individuals. While CCTA effectively detects calcified plaque, it can miss or underrepresent soft, low-attenuation plaque, leading to underdiagnosis. Heartflow’s Plaque Analysis fills that gap by quantifying all plaque types using AI, giving clinicians a more accurate picture of patient-specific risk.
Central to the DECIDE Registry is Heartflow’s newly introduced Plaque Staging system, which stratifies patients into one of four risk levels (mild, moderate, severe, or extensive) based on AI-assessed plaque volume and composition. Developed through expert consensus and validated with outcomes data from the FISH&CHIPS Study, the staging system provides actionable insight to help tailor patient care.
Using data from more than 2,800 patients, the Plaque Staging tool is now a leading method for coronary risk stratification based on AI plaque quantification. The FISH&CHIPS Study, presented at the British Society of Cardiovascular Imaging in April 2025, showed that patients with higher plaque stages faced up to a fivefold increase in cardiovascular event risk over a median follow-up of 3.3 years.
A possible turning point for coronary artery disease care
“The results from the DECIDE Registry clearly show how Heartflow Plaque Analysis can meaningfully change CAD care, with more than half of patients seeing their treatment plans altered after Heartflow Plaque Analysis,” Campbell Rogers, MD, chief medical officer of Heartflow, said in a statement. “We expect that tools like Plaque Staging will enhance the impact Heartflow Plaque Analysis is already making by providing a clearer framework for personalized patient care.”
Many CCTA and preventive cardiology experts say AI-based soft plaque analysis could become a paradigm shift in how patients are assessed though CCTA screening to obtain baseline images, and then tracking the patient over time. This would allow very early disease detection and a way to monitor in preventive drug therapies are effective, or if more aggressive therapies are needed years before a patient becomes symptomatic or presents with an acute coronary syndrome.
Dave Fornell has covered healthcare for more than 17 years, with a focus in cardiology and radiology. Fornell is a 5-time winner of a Jesse H. Neal Award, the most prestigious editorial honors in the field of specialized journalism. The wins included best technical content, best use of social media and best COVID-19 coverage. Fornell was also a three-time Neal finalist for best range of work by a single author. He produces more than 100 editorial videos each year, most of them interviews with key opinion leaders in medicine. He also writes technical articles, covers key trends, conducts video hospital site visits, and is very involved with social media. E-mail: [email protected]