Keya Medical's DeepVessel FFR Receives FDA Clearance, Ending HeartFlow's Seven-Year Monopoly in the U.S. CT-FFR Market

On April 1, 2022, DEEPVESSEL FFR, a product independently developed by the medical AI company Keya Medical, received FDA 510(k) clearance from the U.S. Food and Drug Administration (FDA) and was officially launched in the U.S. market.

Since HeartFlow, the pioneer of CT-FFR, obtained FDA de novo 510(k) clearance in 2014, the company has successively entered markets in the United States, Canada, Japan, and other countries, gradually establishing a monopolistic position.

With the FDA approval of DeepVessel FFR (DVFFR), the significance extends beyond mere medical device certification; it breaks HeartFlow’s seven-year monopoly on FFRCT products in the U.S. market and is poised to reshape CT-FFR pricing globally.

For Keya Medical, holding the world’s first CT-FFR product with triple certifications from China’s NMPA (January 2020), the EU CE (August 2018), and the US FDA positions the company to expand its previously regionalized commercial development to most parts of the globe.

The DeepVessel FFR (DVFFR), recently approved by the FDA, holds core value in digitally transforming Fractional Flow Reserve (FFR).

FFR is a functional index for evaluating coronary hemodynamics. It facilitates the functional assessment of coronary stenosis, assists physicians in diagnosing coronary artery disease, accurately evaluates coronary blood flow function, reduces unnecessary coronary angiography, and helps physicians better plan coronary treatment strategies.

The core technology adopted by DeepVessel Fractional Flow Reserve (DVFFR) is CT-FFR, one of the various FFR measurement methods. It leverages CTA imaging and its proprietary artificial intelligence to provide non-invasive FFR analysis for patients, serving as an alternative to invasive catheter-based FFR.

Furthermore, this technology can guide PCI treatment, reduce the number of unnecessary diagnostic coronary angiographies and stent implantations, and effectively avoid complications such as coronary artery spasm and perforation caused by invasive FFR.

Professor Hou Jiangtao of the Faculty of Medicine at The Chinese University of Hong Kong has stated that image-based FFR requires neither vasodilator drugs nor pressure wires and associated equipment. More importantly, it can be performed non-invasively or minimally invasively, significantly reducing procedural pain for patients and effectively alleviating their anxiety. Consequently, non-invasive FFR, led by CT-FFR, is gradually replacing wire-based invasive FFR in percutaneous coronary intervention (PCI) procedures and capturing a larger market share.

To ensure algorithmic efficacy, the DeepVessel FFR (DVFFR) model not only fully accounts for the vascular tree structure and performs global optimization but also incorporates training on complex lesions. It calculates fractional flow reserve (FFR) values at various points along the vascular tree, enabling precise FFR assessment and demonstrating strong concordance with wire-based FFR measurements.

From a temporal perspective, CT-FFR technology is not new. As early as 2013–2016, cardiology societies in the United States, Europe, China, and other countries successively affirmed in their guidelines the value of FFR in revascularization and in the diagnostic evaluation of certain types of coronary artery disease. During this period, guidelines in the United States and China stated: “The level of evidence supporting the use of FFR in stable coronary artery disease is Class I, Level A.” However, in practice, the adoption of CT-FFR has not been widespread.

Two factors constrain the application of CT-FFR: first, the high pricing under HeartFlow’s patent protection; second, the insufficient supply of medical resources due to model reconstruction taking several hours.

For the latter, the integration of medical artificial intelligence can delegate time-consuming and highly repetitive image post-processing tasks to intelligent algorithms, reducing processing time to just a few minutes and enabling more precise and efficient FFR calculations. Consequently, when Keya Medical’s FFR product received the first Class III medical device certification for medical AI from the National Medical Products Administration (NMPA) in 2020, the agency characterized the product with the nine-character phrase “significant economic benefits.”

Revisiting HeartFlow’s High-Pricing Strategy Under Patent Protection: The Underlying Support Lies in the Technical Barriers of CT-FFR. With its DeepVessel FFR (DVFFR) gaining FDA clearance, Keya Medical has not only validated its R&D capabilities but also broken HeartFlow’s long-standing monopoly. Amidst robust competition, patients will benefit from more accessible pricing.

The so-called “significant economic benefits” extend beyond merely reducing patients’ out-of-pocket expenses for cardiovascular disease treatment. Against the macro backdrop of DRG-based cost containment and the advancement of precision diagnosis and therapy, if DeepVessel FFR can be fully implemented in hospitals to optimize existing clinical workflows, streamline diagnostic steps, and reduce the number of clinical decisions required by physicians, multiple stakeholders—including patients, hospitals, physicians, and medical insurance payers—will benefit.

Traditional coronary angiography and functional assessments are invasive procedures with numerous limitations, often leading to significant patient resistance. In contrast, CT-FFR is a non-invasive modality that shortens examination time, minimizes impact on patient health, and is therefore more readily accepted by patients. Additionally, it eliminates the costs associated with surgical procedures and catheter-based consumables; the relatively lower cost of a single CT-FFR test makes it affordable for the vast majority of patients.

When the revenue for a single disease type is positive, patients previously required 1–3 days to obtain results from CTA examinations. However, with AI-enabled CT-FFR, patients can receive their results in just half a day. This means that the hospital stay for each patient will be shortened by two days, allowing hospitals to admit more patients within the same time frame.

There are numerous causes of myocardial ischemia, which may be triggered by stenosis of large epicardial arteries or result from microcirculatory dysfunction. In addition, functional abnormalities of the arteries exist; both large and small vessels can cause myocardial ischemia due to vasospasm. If myocardial ischemia is caused by stenotic lesions, leading to angina symptoms, percutaneous coronary intervention (PCI) with stent implantation can alleviate symptoms, improve quality of life, and reduce the incidence of long-term cardiac events. However, if the stenotic lesions do not induce myocardial ischemia, premature revascularization will not only fail to treat ischemia or improve symptoms and prognosis but may also expose patients to new risks.

Under the traditional model, due to a lack of effective data acquisition methods, physicians often rely solely on imaging-based diagnostic assessments to evaluate patients' vascular conditions, making it difficult to accurately determine the severity of myocardial ischemia. In such cases, physicians may still recommend coronary angiography even when it is unnecessary or poses risks. Over time, this approach imposes a significant burden on physicians, patients, and healthcare expenditures.

To address the aforementioned issues, DeepVessel FFR integrates imaging and functional assessments, enabling vessel-level detection with accuracy, sensitivity, and specificity all exceeding 90%, thereby delivering highly accurate diagnostic results even in the "gray zone."

This means that new technologies can avoid ineffective PCI procedures, reduce the use of high-value consumables such as catheters and stents, help physicians improve treatment precision, and decrease patient readmissions, thereby reducing healthcare insurance expenditures through FFR.

Currently, Keya Medical has not yet publicly disclosed detailed clinical data to substantiate the clinical value of its DeepVessel FFR. However, data from the "Health Economic Evaluation Report on Functional Diagnosis of Coronary Artery Disease in China" indicates that, under ideal conditions, DeepVessel FFR (DVFFR) could save at least RMB 6 billion annually in the overall health and economic burden of CAD in China.

According to Frost & Sullivan data, the number of CTA examinations performed in China increased from 3.6 million in 2015 to 6.2 million in 2020, representing a compound annual growth rate (CAGR) of 11.7%. The figure is estimated to further rise to 22.2 million by 2023, corresponding to a CAGR of 13.6% from 2020 to 2023.

Driven by factors such as data availability, favorable policies, increasing market acceptance of deep learning-based medical devices, and an unprecedented demand in China for non-invasive diagnostic tools for coronary artery disease, the market for deep learning-based CT-FFR products in China is expected to grow exponentially. At a 30% penetration rate, the annual market size for CT-FFR is projected to reach approximately RMB 4 billion by 2030.

Keya Medical is clearly not the only player following this high-potential market. To date, nearly ten companies in China have been conducting R&D based on fractional flow reserve (FFR) technology. Both Northcore Life Science and Bodong Medical have filed their prospectuses with the Hong Kong Stock Exchange, joining Keya Medical in the IPO pipeline.

As FFR products from various companies successively obtain regulatory review and approval, the accuracy of AI-supported FFR calculations, while important, cannot become a significant competitive advantage. At this stage, companies need to build their brands by focusing on commercialization, service processes, and other aspects.

In the competitive landscape, Keya Medical has secured two core elements essential to capturing the CT-FFR market.

The first is the first-mover advantage. Throughout Keya Medical’s development, since obtaining NMPA certification in January 2020, it has rapidly expanded into provincial and municipal price catalogs. It has now entered the pricing approval stage in 11 provinces and municipalities across China, enabling direct billing to patients. Following the commercialization pathway for medical AI—“registration approval → pricing approval → insurance reimbursement approval”—Keya Medical is nearly one year ahead of its competitors.

The second strategy is a comprehensive product line layout. For Keya Medical, the combined market size for CT-FFR in China, the European Union, and the United States is substantial; however, relying on a single product line exposes the company to numerous risks, such as displacement by new technologies, commercialization progress falling short of expectations, and failure to capture market share. As the economic adage goes, “Don’t put all your eggs in one basket.” The second key initiative undertaken by Keya Medical is to continuously enrich its product portfolio.

Keya Medical has now established two major product lines—Intelligent Diagnosis and Intelligent Treatment—with its portfolio encompassing cardiovascular and cerebrovascular diagnosis, pulmonary diagnosis, and even products such as balloons.

From the “Deep Pulse Shockwave Balloon,” we can gain some insight into Keya Medical’s logic.

When physicians assess vascular plaques using CT, DSA angiography, or intravascular ultrasound, Keya Medical’s DeepVessel Analytics series can assist in identifying calcified plaques and calculating calcium scores, thereby guiding clinical intervention. For patients with calcified plaques requiring urgent treatment, Keya Medical’s “DeepVessel Shockwave Balloon” can precisely fracture the calcified lesions. This enables successful vessel recanalization and improved vascular compliance with minimal damage to the intima, facilitating better stent apposition or enhanced drug release from drug-coated balloons, ultimately leading to improved patient prognosis.

Thus, it is evident that Keya Medical’s ultimate objective extends beyond merely innovating a single key technology to achieve metrics of high accuracy and sensitivity. Healthcare is a complex process, and Keya Medical’s strategy is increasingly penetrating the intricate details of diagnosis and treatment, helping physicians circumvent practical challenges encountered in clinical practice and optimizing specific therapeutic workflows.

To address these challenges, can we rely solely on precise FFR data? Only when technology is truly integrated into every detail and provides solutions to specific problems encountered by physicians can it be considered technology that genuinely benefits healthcare—this is the underlying logic behind Keya Medical’s current strategic layout.

Reviewing Keya Medical’s development over the years, it achieved several milestones: the first Class III medical device to receive NMPA certification, the first price catalog entry for AI-supported CT-FFR, and the world’s first medical AI device to simultaneously obtain authoritative certifications from China, the United States, and Europe. Setting aside the technological aspects, each of its steps has consistently placed it at the forefront of key inflection points in the development of medical artificial intelligence.

Medical AI technology remains in its growth and cognitive phases, with an uncertain outlook, making it difficult to fairly evaluate a company based solely on marketing data. However, Keya Medical’s clear strategic logic offers valuable insights for navigating the industry’s key trends.

After all, healthcare is a sector characterized by stringent policy regulation and strong cyclical trends. As smart healthcare becomes central to hospital development, those who are prepared earliest will gain a first-mover advantage in the large-scale expansion of medical AI.