Diagnosing coronary artery disease from coronary CTA scans is labor-intensive, can take hours for specialists, and often yields subjective conclusions, creating a need for faster, more objective functional assessment and earlier detection of clinically significant disease.
Reported impact
Heartflow enables quicker and more precise CAD evaluation, achieves accuracy close to invasive functional assessment, supports triage for intermediate stenosis, helps physicians avoid unnecessary risky interventions, and has scaled to broad adoption across US hospitals and outpatient facilities.
Heartflow built an in-house AI diagnostic platform for coronary artery disease that starts with raw coronary computed tomography angiography (CTA) image sets uploaded from CT scanners. The Heartflow platform processes thousands to tens of thousands of images per case, reconstructs a patient-specific 3D model of the coronary arteries, and applies computational fluid dynamics through its FFR analysis workflow to simulate blood flow and pressure across the coronary tree. The platform then calculates FFRCT values at every point to show whether a narrowing is functionally significant, and returns objective quantitative results to physicians in 5-10 minutes as a color-coded visualization rather than a purely manual read. Heartflow also uses Plaque analysis to quantify coronary plaque for earlier detection and prevention. The article says Heartflow continues to improve its models using a library of 110 million annotated CCTA images, indicating a large training data store feeding ongoing model refinement and clinical deployment.
Coronary CTA image sets from CT scanners are uploaded into Heartflow, which reconstructs a 3D coronary model from thousands of images, runs FFR analysis to simulate flow and pressure, computes FFRCT values throughout the arteries, and serves quantitative visual results to physicians for triage and treatment decisions. Plaque analysis uses the same imaging foundation to quantify plaque burden for preventive care.
"As of October 2025, approximately 1,400 of 2,700 US hospitals and outpatient facilities performing CCTA have already adopted the Heartflow platform."
"Clinical trials and real world data show sensitivity of around 85% to 90% and specificity of around 80%."
"It then applies computational fluid dynamics (CFD) to simulate blood flow and pressure throughout the coronary tree in just minutes."
"Since launch, Heartflow has improved the accuracy of its algorithms, using a vast library of 110 million annotated CCTA images"
"The system calculates a fractional flow reserve (FFRCT) value at every point in the arteries"
"Using raw CTA images generated by computed tomography scanners – often thousands to tens of thousands – Heartflow constructs a detailed 3D model of the coronary arteries."
"automatic AI tools like Heartflow can quantify plaque in just 5-10 minutes after image upload, delivering objective quantitative results powered by artificial intelligence and machine learning."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
The filing states: “As of December 31, 2025, we had 843 full-time employees globally.”
Related
In-house Sample Jul 28, 2026 Novartis Novartis R&D needs to turn large volumes of scientific, clinical, operational, and real-world data into faster, higher-quality decisions across drug discovery and development, reducing cycle times, surfacing safety… less than 10 percent of drug candidates historically reach the market AI models · AI-enhanced analytics · Generative AI In-house Sample Apr 13, 2026 Elevance Health Elevance Health needed to find fraud, waste, and abuse in very large volumes of claims, payment, contract, and medical-record data so it could detect billing errors, suspicious coding patterns, and improper payments… across an annualized volume of nearly 23,000 reviews In-house Sample Feb 24, 2026 Sanofi Sanofi needed a faster, more objective way to decide which R&D programs to advance, accelerate, or stop while weighing costs, clinical trial enrollment timelines, unmet need, competition, and each program's probability… more than one billion data points across Sanofi Aily Labs · Plai 