Machine learning for multidimensional response and survival after cardiac resynchronization therapy using features from cardiac magnetic resonance.
Cardiac resynchronization therapy
Heart failure
Implantable cardioverter-defibrillator
Machine learning
Magnetic resonance imaging
Journal
Heart rhythm O2
ISSN: 2666-5018
Titre abrégé: Heart Rhythm O2
Pays: United States
ID NLM: 101768511
Informations de publication
Date de publication:
Oct 2022
Oct 2022
Historique:
entrez:
7
11
2022
pubmed:
8
11
2022
medline:
8
11
2022
Statut:
epublish
Résumé
Cardiac resynchronization therapy (CRT) response is complex, and better approaches are required to predict survival and need for advanced therapies. The objective was to use machine learning to characterize multidimensional CRT response and its relationship with long-term survival. Associations of 39 baseline features (including cardiac magnetic resonance [CMR] findings and clinical parameters such as glomerular filtration rate [GFR]) with a multidimensional CRT response vector (consisting of post-CRT left ventricular end-systolic volume index [LVESVI] fractional change, post-CRT B-type natriuretic peptide, and change in peak VO Among 200 patients (median age 67.4 years, 27.0% women) with CRT and CMR, associations with more than 1 response parameter were noted for the CMR CURE-SVD dyssynchrony parameter (associated with post-CRT brain natriuretic peptide [BNP] and LVESVI fractional change) and GFR (associated with peak VO Machine learning characterizes distinct CRT response clusters influenced by CMR features, kidney function, and other factors. These clusters have a strong and additive influence on long-term survival relative to baseline features.
Sections du résumé
Background
UNASSIGNED
Cardiac resynchronization therapy (CRT) response is complex, and better approaches are required to predict survival and need for advanced therapies.
Objective
UNASSIGNED
The objective was to use machine learning to characterize multidimensional CRT response and its relationship with long-term survival.
Methods
UNASSIGNED
Associations of 39 baseline features (including cardiac magnetic resonance [CMR] findings and clinical parameters such as glomerular filtration rate [GFR]) with a multidimensional CRT response vector (consisting of post-CRT left ventricular end-systolic volume index [LVESVI] fractional change, post-CRT B-type natriuretic peptide, and change in peak VO
Results
UNASSIGNED
Among 200 patients (median age 67.4 years, 27.0% women) with CRT and CMR, associations with more than 1 response parameter were noted for the CMR CURE-SVD dyssynchrony parameter (associated with post-CRT brain natriuretic peptide [BNP] and LVESVI fractional change) and GFR (associated with peak VO
Conclusion
UNASSIGNED
Machine learning characterizes distinct CRT response clusters influenced by CMR features, kidney function, and other factors. These clusters have a strong and additive influence on long-term survival relative to baseline features.
Identifiants
pubmed: 36340495
doi: 10.1016/j.hroo.2022.06.005
pii: S2666-5018(22)00148-9
pmc: PMC9626744
doi:
Types de publication
Journal Article
Langues
eng
Pagination
542-552Subventions
Organisme : NHLBI NIH HHS
ID : R01 HL159945
Pays : United States
Informations de copyright
© 2022 Heart Rhythm Society. Published by Elsevier Inc.
Références
Circulation. 2008 May 20;117(20):2608-16
pubmed: 18458170
J Am Coll Cardiol. 2019 Mar 26;73(11):1264-1272
pubmed: 30846338
JACC Cardiovasc Imaging. 2021 Dec;14(12):2369-2383
pubmed: 34419391
J Am Coll Cardiol. 2008 Dec 2;52(23):1834-1843
pubmed: 19038680
J Cardiol. 2012 Sep;60(3):228-35
pubmed: 22542140
JACC Clin Electrophysiol. 2021 Dec;7(12):1505-1515
pubmed: 34454883
Clin Med Res. 2010 Mar;8(1):7-12
pubmed: 19920165
Radiology. 2015 May;275(2):413-20
pubmed: 25581423
Heart Rhythm. 2013 Sep;10(9):1368-74
pubmed: 23851059
N Engl J Med. 2002 Jun 13;346(24):1845-53
pubmed: 12063368
Radiology. 2004 Mar;230(3):862-71
pubmed: 14739307
Am Heart J. 2022 Jan;243:1-10
pubmed: 34453882
JACC Clin Electrophysiol. 2021 Nov;7(11):1422-1432
pubmed: 34167929
Curr Heart Fail Rep. 2019 Dec;16(6):274-284
pubmed: 31741231
J Card Fail. 2008 Feb;14(1):9-18
pubmed: 18226768
IEEE Trans Med Imaging. 2007 Jan;26(1):15-30
pubmed: 17243581
Magn Reson Med. 2010 Oct;64(4):1089-97
pubmed: 20574967
Eur J Clin Invest. 2014;44(3):303-8
pubmed: 24372567
J Am Coll Cardiol. 2011 Feb 15;57(7):813-20
pubmed: 21310317
J Am Coll Cardiol. 2014 Apr 29;63(16):1657-66
pubmed: 24583155
Circ Arrhythm Electrophysiol. 2019 Jul;12(7):e007316
pubmed: 31216884
Heart Rhythm. 2012 Oct;9(10):1737-53
pubmed: 22975672
PLoS One. 2018 Dec 19;13(12):e0209325
pubmed: 30566512
J Magn Reson Imaging. 2017 Sep;46(3):887-896
pubmed: 28067978
N Engl J Med. 2004 May 20;350(21):2140-50
pubmed: 15152059
Eur J Heart Fail. 2012 Mar;14(3):287-94
pubmed: 22357576
JACC Clin Electrophysiol. 2021 Feb;7(2):135-147
pubmed: 33602393
JACC Cardiovasc Imaging. 2020 Apr;13(4):924-936
pubmed: 31864974