Interoperator reliability of an on-site machine learning-based prototype to estimate CT angiography-derived fractional flow reserve.
Biostatistics
CORONARY ARTERY DISEASE
Computed Tomography Angiography
Journal
Open heart
ISSN: 2053-3624
Titre abrégé: Open Heart
Pays: England
ID NLM: 101631219
Informations de publication
Date de publication:
03 2022
03 2022
Historique:
received:
23
12
2021
accepted:
07
03
2022
entrez:
22
3
2022
pubmed:
23
3
2022
medline:
15
4
2022
Statut:
ppublish
Résumé
Advances in CT and machine learning have enabled on-site non-invasive assessment of fractional flow reserve (FFR To assess the interoperator and intraoperator variability of coronary CT angiography-derived FFR We included 60 symptomatic patients who underwent coronary CT angiography. FFR A total of 535 coronary segments in 60 patients were assessed. The overall ICC was 0.986 per patient (95% CI 0.977 to 0.992) and 0.972 per segment (95% CI 0.967 to 0.977). The absolute mean difference in FFR A high degree of interoperator and intraoperator reproducibility can be achieved by on-site machine learning-based FFR
Sections du résumé
BACKGROUND
Advances in CT and machine learning have enabled on-site non-invasive assessment of fractional flow reserve (FFR
PURPOSE
To assess the interoperator and intraoperator variability of coronary CT angiography-derived FFR
MATERIALS AND METHODS
We included 60 symptomatic patients who underwent coronary CT angiography. FFR
RESULTS
A total of 535 coronary segments in 60 patients were assessed. The overall ICC was 0.986 per patient (95% CI 0.977 to 0.992) and 0.972 per segment (95% CI 0.967 to 0.977). The absolute mean difference in FFR
CONCLUSION
A high degree of interoperator and intraoperator reproducibility can be achieved by on-site machine learning-based FFR
Identifiants
pubmed: 35314508
pii: openhrt-2021-001951
doi: 10.1136/openhrt-2021-001951
pmc: PMC8938695
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
© Author(s) (or their employer(s)) 2022. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.
Déclaration de conflit d'intérêts
Competing interests: MHA-M receives research support from Siemens. CS, MC and JCRG are employed by Siemens.
Références
JACC Cardiovasc Imaging. 2016 Sep;9(9):1099-1113
pubmed: 27609151
J Am Coll Cardiol. 2014 Apr 1;63(12):1145-1155
pubmed: 24486266
Radiol Cardiothorac Imaging. 2019 Aug 29;1(3):e180012
pubmed: 33778507
J Cardiovasc Comput Tomogr. 2014 Jul-Aug;8(4):307-14
pubmed: 25151923
Tutor Quant Methods Psychol. 2012;8(1):23-34
pubmed: 22833776
JACC Cardiovasc Imaging. 2022 Feb;15(2):284-295
pubmed: 34656489
N Engl J Med. 2009 Jan 15;360(3):213-24
pubmed: 19144937
J Am Coll Cardiol. 2019 Oct 8;74(14):1772-1784
pubmed: 31582137
Eur Heart J Cardiovasc Imaging. 2019 Mar 1;20(3):343-352
pubmed: 30107511
JAMA. 2012 Sep 26;308(12):1237-45
pubmed: 22922562
JACC Cardiovasc Imaging. 2017 Nov;10(11):1350-1358
pubmed: 28412436
JACC Cardiovasc Imaging. 2018 Nov;11(11):1640-1650
pubmed: 29909103
J Cardiovasc Comput Tomogr. 2017 Nov;11(6):462-467
pubmed: 28986147
JAMA Cardiol. 2017 Oct 1;2(10):1100-1107
pubmed: 28813561
Sci Rep. 2018 Aug 1;8(1):11535
pubmed: 30069020
J Cardiovasc Comput Tomogr. 2018 Mar - Apr;12(2):101-107
pubmed: 29409717
J Cardiovasc Comput Tomogr. 2022 Jan-Feb;16(1):19-26
pubmed: 34518113
J Comput Assist Tomogr. 2018 Mar/Apr;42(2):256-262
pubmed: 28937495
J Am Coll Cardiol. 2011 Nov 1;58(19):1989-97
pubmed: 22032711
J Cardiovasc Comput Tomogr. 2016 Nov - Dec;10(6):435-449
pubmed: 27780758
J Appl Physiol (1985). 2016 Jul 1;121(1):42-52
pubmed: 27079692
J Cardiovasc Comput Tomogr. 2019 Mar - Apr;13(2):134-141
pubmed: 30385326
Circ Cardiovasc Imaging. 2018 Jun;11(6):e007217
pubmed: 29914866