Skip to content

DEEPVESSEL FFR judged better than CT angiography in China's review

China's CMDE judged that DEEPVESSEL FFR can diagnose functional myocardial ischemia better than coronary CT angiography alone. The report gives no figures from the maker's trials.

  • Not rated an organization

    CMDE judged that diagnosis improves over CT angiography, and the report gives no figures from the maker's trials.

  • Not rated a person

    CMDE judged that patients can be spared unnecessary invasive angiography and coronary intervention, and the report gives no count of procedures avoided.

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

Status
Intended benefit.
Evidence

found, the grade of this recordstudiedreportedclaimed

An independent regulatory document supports the benefit.

Compared with

Coronary CT angiography alone, in CMDE's statement of the main clinical benefit, which gives no figures. Assumed without a measurement.

The system’s part
Not isolated. The trials measured the software's FFR against FFR measured during invasive angiography. The report gives no figures and shows no comparison of diagnosis or care with and without the software. Both trials were the maker's own. The report says that the software segments the vessels and computes FFR with deep learning.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome
Benefit type
Improved Task Accuracy
System
DEEPVESSEL FFR (冠脉血流储备分数计算软件)
Made by
Keya Medical, with 北京昆仑医云科技有限公司 (Beijing Kunlun Medical Cloud Technology Co., Ltd.) as the applicant in China
Used by
北京昆仑医云科技有限公司 (Beijing Kunlun Medical Cloud Technology Co., Ltd.), the applicant (prospective trial at three institutions and retrospective trial at six)
Where
Trial institutions in China that the report does not name, three in the prospective trial and six in the retrospective trial
Stage
In a pilot
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Estimating the Quantifiable Characteristics of Products, Events, or Information, Identifying Objects, Actions, and Events
Collections
Scrutiny and findings
Last revised
1 November 2026

Sources

  1. Regulatory document, by authors with no tie to the system.

    Center for Medical Device Evaluation (CMDE), National Medical Products Administration, China. 医疗器械产品注册技术审评报告:冠脉血流储备分数计算软件 (technical review report for the registration of coronary fractional flow reserve computation software), acceptance no. CQZ1900346, applicant 北京昆仑医云科技有限公司. 6 January 2020. Section 五、临床受益风险评估 (clinical benefit-risk assessment).

    可以提高功能性心肌缺血的诊断性能,减少不必要的冠脉血管造影检查(ICA)和冠脉介入手术(PCI)
    基于当前认知水平,认为该产品临床使用受益大于风险,注册申报资料符合现行技术审评要求,建议予以注册。
    该产品用于冠心病诊断时诊断价值较高,严重不良事件及与器械相关不良事件发生率低,具有可接受的安全性,可满足临床需求,适用于临床。

Details

AI system

Reported configuration

Release 1.0 (full version 1.0.1)

Workflow

The software segmented and reconstructed the coronary vessels on CT angiography with deep learning and extracted their centerlines. It then computed FFR with deep learning. FFR measured during invasive coronary angiography served as the reference standard.

Follow-up

Conditions for replication

Patients have stable coronary artery disease, with stenosis between 30% and 90% on CT angiography. Patients with acute coronary syndrome or other acute chest pain are excluded. Doctors weigh the result with the patient's history, symptoms and other findings.

Entry details

Sector

Healthcare.

Purpose

Keya Medical built DEEPVESSEL FFR to compute fractional flow reserve from coronary CT angiography and help trained staff assess functional myocardial ischemia in patients with stable coronary artery disease before invasive angiography.

30 more questions not yet checked

model, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, 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). DEEPVESSEL FFR judged better than CT angiography in China's review (AIBD-1082). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1082.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions