High Accuracy Rate Found With HeartFlow’s Plaque Analysis Tech

Data from HeartFlow Inc.’s REVEALPLAQUE study shows a high accuracy rate for its Plaque Analysis tool. 

REVEALPLAQUE evaluated HeartFlow’s non-invasive plaque technology, an automated, deep learning-based method for identifying, characterizing, and segmenting coronary artery plaque. Understanding plaque’s volume and composition enables physicians to ensure appropriate medical treatment, which could be life-changing for patients.

Key Results: HeartFlow Plaque Analysis is highly accurate in determining total plaque volume and plaque volume by type vs. invasive imaging (IVUS).¹

• Total plaque volume vs. invasive imaging (IVUS): 95% agreement
• Calcified plaque volume vs. IVUS: 95% agreement
• Non-calcified plaque volume vs. IVUS: 93% agreement

HeartFlow claims its Plaque Analysis solution is the only U.S. Food and Drug Administration-cleared, artificial intelligence (AI)-enabled plaque quantification tool validated in a prospective, international trial against the IVUS gold standard using blinded core lab adjudication.¹

Heart disease is the leading cause of death for both men and women.² Four out of five of deaths may be preventable with nutrition, lifestyle, and medication therapy changes for patients identified early.³ With HeartFlow Plaque Analysis, physicians can measure confidently and accurately, the volume by type. Ultimately, this supports patients in a technology forward way that hasn’t previously been possible.

“I’m thrilled to see such an overwhelming result showcasing that CT angiography, coupled with automated AI-driven Plaque Analysis is an effective way to assess plaque burden,” said Jagat Narula, M.D., Ph.D., co-principal investigator and and K. Lance Gould Distinguished University Chair of Coronary Pathophysiology at UTHealth Houston. “This is a futuristic step forward for patients and clinicians to have an accurate, non-invasive test that gives insights into their total plaque volume, and is every bit as good as the invasive reference standard. It will allow clinicians to feel more informed to deliver the best treatment recommendations possible for each patient.”

The REVEALPLAQUE trial was a large, global prospective study that enrolled 258 patients across 15 sites in the United States and Japan. This was an independent, blinded, core lab adjudicated study to determine HeartFlow’s AI Plaque Analysis’ accuracy compared head-to-head with IVUS.

“HeartFlow continues to be the market leader in developing clinically useful AI-powered tools for non-invasive diagnostic testing for coronary artery disease. What’s more, we continue to support clinicians by providing an overwhelming body of clinical evidence attesting to their utility and accuracy,” HeartFlow Chief Medical Officer Campbell Rogers, M.D., stated. “With the addition of the REVEALPLAQUE data, we’re pleased to highlight that we are the only platform that has conducted and published a head to head comparison vs. IVUS using the most rigorous approach possible. Our plaque assessment technology is highly accurate, giving clinicians confidence in the product to support their clinical decision making.”

The HeartFlow Plaque Analysis technology is an automated method that analyzes coronary computed tomography (CT) scans and enables clinicians to visualize, characterize, and quantify plaque. The plaque technology is based on HeartFlow’s proprietary deep learning-enabled algorithms, which have been trained on more than 15 million coronary CT images. This information is delivered seamlessly to physicians in the HeartFlow platform, and when paired alongside anatomy and physiology of the patient, enhances decision-making for the clinician. HeartFlow has been adopted by more than 1,000 institutions globally. 

HeartFlow is aiming to transform precision coronary care with the only AI-powered non-invasive integrated heart care solution across the CCTA pathway. As the pioneer of FFR_CT, which is now supported by the ACC/AHA Chest Pain Guideline, HeartFlow continues to advance the diagnosis and management of CAD. HeartFlow’s suite of non-invasive technologies includes its FFR_CT Analysis, RoadMapAnalysis, and Plaque Analysis. To date, more than 500 peer-reviewed publications have validated the company’s approach and its technologies have helped clinicians diagnose and manage over 250,000 patients. 

References
¹ Narula et al. Prospective Deep Learning-based Quantitative Assessment of Coronary Plaque by CT Angiography Compared with Intravascular Ultrasound EHJ 2024.
² CDC.org
³ Wang et al. JAHA 2020