Risk factors based vessel-specific prediction for stages of coronary artery disease using Bayesian quantile regression machine learning method: Results from the PARADIGM registry.
cardiovascular risk factors
coronary artery disease
machine learning
Journal
Clinical cardiology
ISSN: 1932-8737
Titre abrégé: Clin Cardiol
Pays: United States
ID NLM: 7903272
Informations de publication
Date de publication:
Mar 2023
Mar 2023
Historique:
revised:
12
12
2022
received:
07
11
2022
accepted:
19
12
2022
pubmed:
25
1
2023
medline:
21
3
2023
entrez:
24
1
2023
Statut:
ppublish
Résumé
The recently introduced Bayesian quantile regression (BQR) machine-learning method enables comprehensive analyzing the relationship among complex clinical variables. We analyzed the relationship between multiple cardiovascular (CV) risk factors and different stages of coronary artery disease (CAD) using the BQR model in a vessel-specific manner. From the data of 1,463 patients obtained from the PARADIGM (NCT02803411) registry, we analyzed the lumen diameter stenosis (DS) of the three vessels: left anterior descending (LAD), left circumflex (LCx), and right coronary artery (RCA). Two models for predicting DS and DS changes were developed. Baseline CV risk factors, symptoms, and laboratory test results were used as the inputs. The conditional 10%, 25%, 50%, 75%, and 90% quantile functions of the maximum DS and DS change of the three vessels were estimated using the BQR model. The 90th percentiles of the DS of the three vessels and their maximum DS change were 41%-50% and 5.6%-7.3%, respectively. Typical anginal symptoms were associated with the highest quantile (90%) of DS in the LAD; diabetes with higher quantiles (75% and 90%) of DS in the LCx; dyslipidemia with the highest quantile (90%) of DS in the RCA; and shortness of breath showed some association with the LCx and RCA. Interestingly, High-density lipoprotein cholesterol showed a dynamic association along DS change in the per-patient analysis. This study demonstrates the clinical utility of the BQR model for evaluating the comprehensive relationship between risk factors and baseline-grade CAD and its progression.
Sections du résumé
BACKGROUND AND HYPOTHESIS
OBJECTIVE
The recently introduced Bayesian quantile regression (BQR) machine-learning method enables comprehensive analyzing the relationship among complex clinical variables. We analyzed the relationship between multiple cardiovascular (CV) risk factors and different stages of coronary artery disease (CAD) using the BQR model in a vessel-specific manner.
METHODS
METHODS
From the data of 1,463 patients obtained from the PARADIGM (NCT02803411) registry, we analyzed the lumen diameter stenosis (DS) of the three vessels: left anterior descending (LAD), left circumflex (LCx), and right coronary artery (RCA). Two models for predicting DS and DS changes were developed. Baseline CV risk factors, symptoms, and laboratory test results were used as the inputs. The conditional 10%, 25%, 50%, 75%, and 90% quantile functions of the maximum DS and DS change of the three vessels were estimated using the BQR model.
RESULTS
RESULTS
The 90th percentiles of the DS of the three vessels and their maximum DS change were 41%-50% and 5.6%-7.3%, respectively. Typical anginal symptoms were associated with the highest quantile (90%) of DS in the LAD; diabetes with higher quantiles (75% and 90%) of DS in the LCx; dyslipidemia with the highest quantile (90%) of DS in the RCA; and shortness of breath showed some association with the LCx and RCA. Interestingly, High-density lipoprotein cholesterol showed a dynamic association along DS change in the per-patient analysis.
CONCLUSIONS
CONCLUSIONS
This study demonstrates the clinical utility of the BQR model for evaluating the comprehensive relationship between risk factors and baseline-grade CAD and its progression.
Identifiants
pubmed: 36691990
doi: 10.1002/clc.23964
pmc: PMC10018106
doi:
Types de publication
Clinical Trial
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
320-327Subventions
Organisme : Korea Medical Device Development Fund
ID : 202016B02
Organisme : National Research Foundation of Korea
ID : RS-2022-00165404
Organisme : National Research Foundation of Korea
ID : 2022R1A5A6000840
Organisme : National Research Foundation of Korea
ID : 2020R1I1A1A01073151
Commentaires et corrections
Type : ErratumIn
Informations de copyright
© 2023 The Authors. Clinical Cardiology published by Wiley Periodicals, LLC.
Références
JAMA. 2003 Aug 20;290(7):898-904
pubmed: 12928466
Eur Heart J. 2011 Jun;32(11):1316-30
pubmed: 21367834
Clin Cardiol. 2023 Mar;46(3):320-327
pubmed: 36691990
Am Heart J. 2014 Jun;167(6):846-52.e2
pubmed: 24890534
Circulation. 2010 Feb 23;121(7):e46-e215
pubmed: 20019324
JAMA. 2003 Aug 20;290(7):891-7
pubmed: 12928465
Radiol Cardiothorac Imaging. 2021 Jun 17;3(3):e200486
pubmed: 34235441
Inquiry. 2022 Jan-Dec;59:469580221082356
pubmed: 35373630
JACC Cardiovasc Imaging. 2018 Mar;11(3):437-446
pubmed: 28624401
Am J Cardiol. 1980 Jul;46(1):13-20
pubmed: 6966888
Comput Math Methods Med. 2021 Dec 14;2021:2370496
pubmed: 34950223
Lancet. 2018 Nov 10;392(10159):1736-1788
pubmed: 30496103
Eur Heart J. 2019 May 7;40(18):1426-1435
pubmed: 30561616
Chest. 1970 Jan;57(1):41-6
pubmed: 5410429
Adv Exp Med Biol. 2020;1177:1-36
pubmed: 32246442
Am J Cardiol. 1974 Mar;33(3):423-30
pubmed: 4273043
Am J Cardiol. 1999 Aug 15;84(4):396-9
pubmed: 10468075
Am Heart J. 2016 Dec;182:72-79
pubmed: 27914502
Am J Cardiol. 2015 Aug 15;116(4):504-7
pubmed: 26081064
N Engl J Med. 2010 Mar 11;362(10):886-95
pubmed: 20220183
Health Policy Plan. 2009 May;24(3):175-88
pubmed: 19282483
N Engl J Med. 1979 Jun 14;300(24):1350-8
pubmed: 440357
Am J Epidemiol. 2014 Aug 1;180(3):330-1
pubmed: 24989240