AI software may replace invasive heart tests — a validation study puts it to the test
NCT ID NCT07763769
First seen Aug 13, 2026 · Last updated Aug 14, 2026 · Updated 1 time
Summary
This study tests whether a software tool called AutocathFFR can accurately measure the severity of coronary artery blockages from standard 2D angiogram images, compared to the gold-standard invasive FFR measurement. The software uses machine learning to analyze images taken during cardiac catheterization, potentially avoiding the need for a pressure wire. Researchers will evaluate its sensitivity and specificity in adults with stable or unstable angina or NSTEMI who underwent both procedures. If the software proves accurate, it could offer a less invasive way to guide treatment decisions.
What this could mean
Our plain-language read of the trial. This is informational only, not medical advice or a prediction.
- Active substance
- MedHub AutocathFFR, a software device that analyzes standard 2D coronary angiogram images using machine learning to estimate fractional flow reserve (FFR)
- What this could lead to
- If validated, this software could let doctors assess coronary artery disease severity without invasive pressure-wire measurements, making diagnosis faster and less risky.
- What could go wrong
- This is an observational validation study, not a treatment trial. The software's accuracy may not meet the performance goals, and results may not generalize beyond the studied population.
This is an AI summary of the original study and may miss details. Read our disclaimer.
Study facts
What this study's own registry entry says, in plain language.
- Participants
-
277 people
The number who actually took part.
- Started
-
Nov 2025
- Finished
-
Jun 2026
- Lead sponsor
-
A company
The lead sponsor is a pharmaceutical, biotech, or medical-device company.
Who can take part
This study's own entry requirements. Only the study team can say for certain whether you qualify.
Who is studied
Angiograms from adult subjects with stable angina, unstable angina or NSTEMI who underwent a clinically indicated invasive coronary angiography and on whom invasive FFR has been measured to assess the hemodynamic significance of suspected coronary lesions.
- Ages
-
23 years and older
- Sex
-
Anyone
- Healthy volunteers
-
Not accepted
This study is not open to healthy volunteers. The entry requirements below say who it is open to.
Show the full entry requirements Hide the full entry requirements
Copied word for word from the study's registry entry, so the wording is the study team's rather than ours.
Inclusion Criteria: * Age \> 22 years * Subjects with stable angina pectoris, unstable angina pectoris, or NSTEMI and in whom invasive FFR was performed to assess a non-culprit stenosis in at least one coronary artery * Subject underwent a clinically indicated Invasive Coronary Angiogram (ICA) * Subject underwent invasive FFR with intravenous (IV) or intracoronary adenosine, or adenosine triphosphate (ATP), as hyperemic stimulus Exclusion Criteria: * Angiogram not obtained on a United States Food and Drug Administration (FDA)-cleared C-arm angiography system * Invasive FFR not obtained on an FDA-cleared FFR catheter tip pressure transducer (also known as a pressure wire) * Vessel size less than 2 mm * Subject presents with an ST-elevation myocardial infarction (STEMI) * Chronic total occlusion (CTO) in target vessel * Prior coronary artery bypass graft (CABG) surgery, heart transplant or valve surgery, prior transcatheter aortic valve implantation/replacement (TAVI/TAVR), or severe left-sided valvular disease * Known left ventricular ejection fraction (LVEF) ≤ 30% * Arteries supplying akinetic or severe hypokinetic territories on target lesion, if already known based on prior imaging * Thrombolysis in Myocardial Infarction (TIMI) flow grade equal to or lower than 2 at baseline * Target lesion involves Left Main (stenosis \>50%) * Percutaneous coronary intervention (PCI) with stent in target vessel in past 12 months, or target vessel involves in-stent restenosis * Target coronary vessel provides collaterals to a chronically occluded vessel * Coronary angiography was not performed per standard of care at a cine frame rate of at least 7 frames per second * Presence of aortic damping * Distortion of the waveform * Less than two different angiographic views for each lesion of interest in the Left Circumflex Artery (LCX), Left Anterior Descending Artery (LAD), or Right Coronary Artery (RCA) * Lesion is not clearly visible
Get updates
Get notified about this study
Sign up to get updates when this study changes or when new studies for Coronary artery disease are added.
Genom att skicka in godkänner du våra Användarvillkor
Conditions
The condition(s) this trial relates to.
As listed by the trial registrant
The condition terms exactly as the trial's registrant entered them.
Contacts and locations
Locations
-
Emory University Hospital
Atlanta, Georgia, 30322, United States
-
MedStar Washington Hospital Center
Washington D.C., District of Columbia, 20010, United States
-
Northeast Georgia Medical Center
Gainesville, Georgia, 30501, United States
-
University of Virginia Health System
Charlottesville, Virginia, 22908, United States
More trials for these conditions
Other studies related to the condition(s) this trial covers.
- Heart bypass surgeons test which vein layout keeps grafts open
- A soft patch that watches your heart beat in real time
- Zapping the ear: a new way to stop Post-Surgery heart rhythm problems?
- Squeeze a ball, lower your blood pressure? heart trial puts handgrip exercise to the test
- New heart scan aims to spot hidden plaque before it strikes
- Can a kidney ultrasound scan warn of kidney damage after heart bypass surgery?