HeartFlow is a medical technology company transforming the diagnosis and treatment of heart disease. We’re uniquely positioned at the intersection of healthcare and technology, leveraging cutting-edge technology to improve our product. Artificial intelligence, deep learning, cloud computing and computational fluid dynamics aren’t buzzwords to us – they’re foundational to our company and the engine driving the continuous evolution of our products.
The HeartFlow Analysis starts when a patient undergoes a standard coronary Computed Tomography (CT) scan at a hospital or imaging center. The CT images are securely uploaded to our cloud. Next, we use advanced algorithms incorporating artificial intelligence to build a personalized, digital model of that patient’s coronary arteries. Our team of highly trained analysts then inspects this model, making any needed edits. Once this patient-specific model is completed, the HeartFlow process applies physiologic principles and computational fluid dynamics to compute the blood flow and FFRCT values at every point in the model. Throughout the process, we follow rigorous and well-established protocols to ensure consistent processing for every patient – no matter which site the data comes from.
The completed HeartFlow Analysis is a color-coded, digital 3D-model of the
heart, reflecting the impact that blockages have on blood flow. This model
can be viewed both on web browser and on mobile. The entire process for
receiving a HeartFlow Analysis is conducted non-invasively, fits in with
your current workflow and leverages the convenience of cloud computing for
easy, and secure, data exchange.
At HeartFlow, we apply the latest in artificial intelligence (AI). One of the most exciting areas in the field of artificial intelligence is image analysis, with major advances in recent years in areas such as facial recognition and image searching. HeartFlow uses this same technology – an advanced form of AI called deep learning – to analyze CT images and help create a personalized digital model for each patient.
What makes deep learning so powerful is the fact that as the algorithms are trained on more data, the performance of future product improves. Today, our deep learning algorithms have been trained using tens of thousands of CT images, and our data set is growing rapidly. We also use the input of our expert analysts, as well as data obtained from invasive methods, to further train the algorithms. This leads to powerful population-based insights. And with an intelligent system doing the legwork, physicians have more time to focus on providing optimal care for each patient.
Our technology arms clinicians with actionable, highly-accurate information to aid in ensuring that each patient gets the treatment that is right for them.
Benefits of HeartFlow’s technology include:
More than 50% of analyses are completed and returned within 5 hours or less*, which allows the HeartFlow Analysis to fit into existing clinical pathways.
Our standardized processes maintain the same level of quality for each and every patient.
Data shows 86% accuracy vs. the gold standard of invasive FFR1.
Having a software-based product allows for rapid development cycles to respond to customer feedback regarding feature requests and defects.
Machines won’t replace physicians, but they absolutely can help. We think it’s time to take the best of technology and apply it to saving lives.
*As of 31 March 2018. Subject to change.
1 Nørgaard BL, et al. Diagnostic performance of non-invasive
fractional flow reserve derived from coronary CT angiography in suspected
coronary artery disease: The NXT Trial (Analysis of Coronary Blood Flow
Using CT Angiography: Next Steps). J Am Coll Cardiol2014;63(12):1145-55.