Machine leArning Based CT angiograpHy derIved FFR: a Multi-ceNtEr, Registry
Machine
1 other identifier
observational
352
1 country
1
Brief Summary
Demonstrate in a large multicenter population the diagnostic performance of a pre-commercial on-site, local, CT angiography derived FFR algorithm in comparison to invasive FFR.
Trial Health
Trial Health Score
Automated assessment based on enrollment pace, timeline, and geographic reach
participants targeted
Target at P75+ for all trials
Started Apr 2016
Shorter than P25 for all trials
1 active site
Health score is calculated from publicly available data and should be used for screening purposes only.
Trial Relationships
Click on a node to explore related trials.
Study Timeline
Key milestones and dates
Study Start
First participant enrolled
April 1, 2016
CompletedFirst Submitted
Initial submission to the registry
June 15, 2016
CompletedFirst Posted
Study publicly available on registry
June 20, 2016
CompletedPrimary Completion
Last participant's last visit for primary outcome
January 1, 2017
CompletedStudy Completion
Last participant's last visit for all outcomes
January 1, 2017
CompletedJanuary 4, 2017
January 1, 2017
9 months
June 15, 2016
January 3, 2017
Conditions
Outcome Measures
Primary Outcomes (1)
Diagnostic accuracy of local reduced order CFD and machine learning based CT angiography derived FFR, both validated against invasive FFR. Measured at both vessel and patient level.
6 months
Secondary Outcomes (5)
Influence of calcium on diagnostic accuracy of CT angiography derived FFR.
6 months
Confidence intervals of CT angiography derived FFR
6 months
Direct vessel based comparison between CT angiography derived FFR and QCT stenosis measurements
6 months
Analysis of anatomically mild stenosis (<50% lumen diameter reduction) but functionally significant (invasive FFR ≤ 0.80)
6 months
Long term clinical outcome of CT angiography derived FFR
12 months
Study Arms (1)
Subject
Patients with know or suspected coronary artery disease, who underwent both CT angiography and invasive coronary angiography including invasive FFR measurements.
Eligibility Criteria
In general, each center used its own specific inclusion and exclusion criteria. Here the investigators describe the general criteria, please see the respected publications for a detailed description.1-4
You may qualify if:
- Know or suspect coronary artery disease followed within 6 months by an invasive FFR measurement.
You may not qualify if:
- Cardiac event between coronary CT angiography and the invasive FFR procedure, noninterpretable coronary CT angiography image quality, or incomplete coronary CT angiography coverage.
Contact the study team to confirm eligibility.
Sponsors & Collaborators
- Erasmus Medical Centerlead
- Asan Medical Centercollaborator
- University Hospital, Linkoepingcollaborator
- National Institute of Cardiology, Warsaw, Polandcollaborator
- Medical University of South Carolinacollaborator
- Siemens Healthcare Diagnostics Inccollaborator
Study Sites (1)
ErasmusMC
Rotterdam, South Holland, 3015CE, Netherlands
Related Publications (6)
De Geer J, Sandstedt M, Bjorkholm A, Alfredsson J, Janzon M, Engvall J, Persson A. Software-based on-site estimation of fractional flow reserve using standard coronary CT angiography data. Acta Radiol. 2016 Oct;57(10):1186-92. doi: 10.1177/0284185115622075. Epub 2015 Dec 20.
PMID: 26691914BACKGROUNDKruk M, Wardziak L, Demkow M, Pleban W, Pregowski J, Dzielinska Z, Witulski M, Witkowski A, Ruzyllo W, Kepka C. Workstation-Based Calculation of CTA-Based FFR for Intermediate Stenosis. JACC Cardiovasc Imaging. 2016 Jun;9(6):690-9. doi: 10.1016/j.jcmg.2015.09.019. Epub 2016 Feb 17.
PMID: 26897667BACKGROUNDBaumann S, Wang R, Schoepf UJ, Steinberg DH, Spearman JV, Bayer RR 2nd, Hamm CW, Renker M. Coronary CT angiography-derived fractional flow reserve correlated with invasive fractional flow reserve measurements--initial experience with a novel physician-driven algorithm. Eur Radiol. 2015 Apr;25(4):1201-7. doi: 10.1007/s00330-014-3482-5. Epub 2014 Nov 18.
PMID: 25403173BACKGROUNDCoenen A, Lubbers MM, Kurata A, Kono A, Dedic A, Chelu RG, Dijkshoorn ML, Gijsen FJ, Ouhlous M, van Geuns RJ, Nieman K. Fractional flow reserve computed from noninvasive CT angiography data: diagnostic performance of an on-site clinician-operated computational fluid dynamics algorithm. Radiology. 2015 Mar;274(3):674-83. doi: 10.1148/radiol.14140992. Epub 2014 Oct 13.
PMID: 25322342BACKGROUNDYang DH, Kim YH, Roh JH, Kang JW, Ahn JM, Kweon J, Lee JB, Choi SH, Shin ES, Park DW, Kang SJ, Lee SW, Lee CW, Park SW, Park SJ, Lim TH. Diagnostic performance of on-site CT-derived fractional flow reserve versus CT perfusion. Eur Heart J Cardiovasc Imaging. 2017 Apr 1;18(4):432-440. doi: 10.1093/ehjci/jew094.
PMID: 27354345BACKGROUNDTesche C, Otani K, De Cecco CN, Coenen A, De Geer J, Kruk M, Kim YH, Albrecht MH, Baumann S, Renker M, Bayer RR, Duguay TM, Litwin SE, Varga-Szemes A, Steinberg DH, Yang DH, Kepka C, Persson A, Nieman K, Schoepf UJ. Influence of Coronary Calcium on Diagnostic Performance of Machine Learning CT-FFR: Results From MACHINE Registry. JACC Cardiovasc Imaging. 2020 Mar;13(3):760-770. doi: 10.1016/j.jcmg.2019.06.027. Epub 2019 Aug 14.
PMID: 31422141DERIVED
MeSH Terms
Conditions
Condition Hierarchy (Ancestors)
Study Officials
- PRINCIPAL INVESTIGATOR
Koen Nieman, MD PHD
Erasmus Medical Center
Study Design
- Study Type
- observational
- Observational Model
- COHORT
- Time Perspective
- RETROSPECTIVE
- Sponsor Type
- OTHER
- Responsible Party
- PRINCIPAL INVESTIGATOR
- PI Title
- dr
Study Record Dates
First Submitted
June 15, 2016
First Posted
June 20, 2016
Study Start
April 1, 2016
Primary Completion
January 1, 2017
Study Completion
January 1, 2017
Last Updated
January 4, 2017
Record last verified: 2017-01
Data Sharing
- IPD Sharing
- Will not share