Heartflow, Inc.

HeartFlow has pioneered the application of software and artificial intelligence (AI) to provide a more accurate and clinically effective non-invasive solution for diagnosing and managing coronary artery disease (CAD), a leading global cause of death.

As of March 31, 2025, the HeartFlow Platform has been used to assess CAD in over 400,000 patients, including 132,000 patients in 2024 alone. HeartFlow is believed to offer the most widely adopted AI-powered diagnostic test for CAD. The company’s innovative platform utilizes AI and advanced computational fluid dynamics to generate a personalized 3D model of a patient’s heart from a single coronary computed tomography angiography (CCTA), a specialized scan that captures detailed images of the heart’s arteries.

CAD is characterized by the accumulation of plaque—comprising cholesterol, fat, calcium, and other substances—on the walls of the coronary arteries. This buildup restricts blood flow and increases the risk of heart attacks and strokes, contributing to half of all cardiovascular-related deaths globally. In the United States, the Centers for Disease Control and Prevention (CDC) estimates that approximately 805,000 individuals suffer a heart attack annually. Despite progress in therapeutic and interventional approaches, CAD remains a leading cause of mortality due to the lack of scalable methods within healthcare systems for the efficient and personalized detection, diagnosis, and quantification of the disease.

Using Clarivate’s ProcedureFinder data repository, HeartFlow estimates that approximately 9.5 million non-invasive tests (NITs) were conducted in the United States in 2023 for patients presenting with stable or acute chest pain, referred to as symptomatic CAD patients. These NITs primarily consist of stress tests—including single-photon emission computed tomography (SPECT), echocardiography, and positron emission tomography (PET)—which assess blood flow to the heart but do not directly measure the presence of coronary disease. As a result, these conventional tests have demonstrated inconsistent and unreliable performance in detecting CAD.