HeartFlow FFRCT may spare heart patients invasive tests, NICE finds

NICE found that HeartFlow FFRCT is safe and accurate. In one study, planned invasive angiography was canceled for 61% of patients, and NICE estimated savings of £391 per patient in 2021.

  • 2 for a person

    In the PLATFORM study, 12% of patients with planned angiography in the FFRCT arm had no obstructive disease at angiography, against 73% with functional imaging.

  • Not rated an organization

    The savings of £391 per patient come from NICE's cost model, and NICE reports no measured spending.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

An independent assessment report supports the benefit.

Compared with

Usual care with functional imaging, in patients with planned invasive angiography (PLATFORM study). Measured.

Without the system
137 patients (73%) with no obstructive coronary artery disease at angiography
With it
24 patients (12%) in the CCTA/FFRCT arm
The system’s part
The NXT trial compared CT angiography with and without FFRCT against invasive measurement, and PLATFORM compared an FFRCT-guided strategy with usual care. NICE describes FFRCT as coronary physiology simulation software run by company analysts and does not show that it learns from data. In May 2026, SHTG wrote that HeartFlow used computational fluid dynamics in 2021 and that its makers have since integrated AI.
Later
Challenged, 1 May 2026. SHTG relays a study of 27 NHS England hospitals that adopted HeartFlow. Patients scanned after its arrival had fewer invasive angiograms but more heart attacks and PCIs, with no difference in deaths at two years.
Not yet checked
LimitsCosts and harmsLearns from data

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
HeartFlow FFRCT
Made by
HeartFlow, Inc.
Used by
NHS services in England that offer coronary CT angiography, with the NXT and PLATFORM study sites in NICE's evidence
Where
England, United Kingdom (guidance), with studies in several countries
Stage
In routine use
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Estimating the Quantifiable Characteristics of Products, Events, or Information, Analyzing Data or Information
Collections
Scrutiny and findings, Cross-border records
Last revised
1 November 2026

Sources

  1. Assessment report, by authors with no tie to the system.

    National Institute for Health and Care Excellence. HeartFlow FFRCT for estimating fractional flow reserve from coronary CT angiography. HealthTech guidance HTG429 (formerly medical technologies guidance MTG32), published 13 February 2017, last updated 19 May 2021. Recommendations 1.1 to 1.3.

    The case for adopting HeartFlow FFR CT for estimating fractional flow reserve from coronary CT angiography (CCTA) is supported by the evidence. The technology is non-invasive and safe, and has a high level of diagnostic accuracy.

Details

AI system

Reported configuration

Version 1.7 at the 2017 guidance, with version 1.4 in the NXT trial

Workflow

Hospitals sent anonymized CT angiography data to HeartFlow's processing center in the US, where company analysts built 3D models of the coronary arteries. Clinicians received a report with estimated FFR values within 48 hours.

Money

Kind of value

Base-case cost saving per patient against the current pathway with functional imaging tests, in the 2021 cost update

Amount

Estimate: £391 per patient

Recipients and payers

The NHS in England

Follow-up

Conditions for replication

Sites have access to 64-slice or better CT angiography. Patients have stable, recent-onset chest pain, and the test is not used after acute coronary syndrome, stenting, bypass surgery or a recent heart attack.

Entry details

Sector

Healthcare.

Purpose

HeartFlow built HeartFlow FFRCT to calculate fractional flow reserve from coronary CT angiography, so that clinicians can judge which narrowed arteries limit blood flow without an invasive test.

36 more questions not yet checked

model, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, currency and prices, period and unit, realization, gross or net, included costs, comparison, method, return and payback, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). HeartFlow FFRCT may spare heart patients invasive tests, NICE finds (AIBD-1122). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1122.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions