Application of machine learning to determine top predictors of noncalcified coronary burden in psoriasis: An observational cohort study.
atherosclerosis
cardiometabolic disease
coronary artery disease
machine learning
psoriasis
random forest algorithm
Journal
Journal of the American Academy of Dermatology
ISSN: 1097-6787
Titre abrégé: J Am Acad Dermatol
Pays: United States
ID NLM: 7907132
Informations de publication
Date de publication:
Dec 2020
Dec 2020
Historique:
received:
13
08
2019
revised:
12
10
2019
accepted:
18
10
2019
pubmed:
5
11
2019
medline:
24
4
2021
entrez:
4
11
2019
Statut:
ppublish
Résumé
Psoriasis is associated with elevated risk of heart attack and increased accumulation of subclinical noncalcified coronary burden by coronary computed tomography angiography (CCTA). Machine learning algorithms have been shown to effectively analyze well-characterized data sets. In this study, we used machine learning algorithms to determine the top predictors of noncalcified coronary burden by CCTA in psoriasis. The analysis included 263 consecutive patients with 63 available variables from the Psoriasis Atherosclerosis Cardiometabolic Initiative. The random forest algorithm was used to determine the top predictors of noncalcified coronary burden by CCTA. We evaluated our results using linear regression models. Using the random forest algorithm, we found that the top 10 predictors of noncalcified coronary burden were body mass index, visceral adiposity, total adiposity, apolipoprotein A1, high-density lipoprotein, erythrocyte sedimentation rate, subcutaneous adiposity, small low-density lipoprotein particle, cholesterol efflux capacity and the absolute granulocyte count. Linear regression of noncalcified coronary burden yielded results consistent with our machine learning output. We were unable to provide external validation and did not study cardiovascular events. Machine learning methods identified the top predictors of noncalcified coronary burden in psoriasis. These factors were related to obesity, dyslipidemia, and inflammation, showing that these are important targets when treating comorbidities in psoriasis.
Sections du résumé
BACKGROUND
BACKGROUND
Psoriasis is associated with elevated risk of heart attack and increased accumulation of subclinical noncalcified coronary burden by coronary computed tomography angiography (CCTA). Machine learning algorithms have been shown to effectively analyze well-characterized data sets.
OBJECTIVE
OBJECTIVE
In this study, we used machine learning algorithms to determine the top predictors of noncalcified coronary burden by CCTA in psoriasis.
METHODS
METHODS
The analysis included 263 consecutive patients with 63 available variables from the Psoriasis Atherosclerosis Cardiometabolic Initiative. The random forest algorithm was used to determine the top predictors of noncalcified coronary burden by CCTA. We evaluated our results using linear regression models.
RESULTS
RESULTS
Using the random forest algorithm, we found that the top 10 predictors of noncalcified coronary burden were body mass index, visceral adiposity, total adiposity, apolipoprotein A1, high-density lipoprotein, erythrocyte sedimentation rate, subcutaneous adiposity, small low-density lipoprotein particle, cholesterol efflux capacity and the absolute granulocyte count. Linear regression of noncalcified coronary burden yielded results consistent with our machine learning output.
LIMITATION
CONCLUSIONS
We were unable to provide external validation and did not study cardiovascular events.
CONCLUSION
CONCLUSIONS
Machine learning methods identified the top predictors of noncalcified coronary burden in psoriasis. These factors were related to obesity, dyslipidemia, and inflammation, showing that these are important targets when treating comorbidities in psoriasis.
Identifiants
pubmed: 31678339
pii: S0190-9622(19)32983-4
doi: 10.1016/j.jaad.2019.10.060
pmc: PMC7428853
mid: NIHMS1543599
pii:
doi:
Types de publication
Journal Article
Observational Study
Langues
eng
Sous-ensembles de citation
IM
Pagination
1647-1653Subventions
Organisme : NIAMS NIH HHS
ID : P30 AR075043
Pays : United States
Organisme : Intramural NIH HHS
ID : ZIA HL006193-05
Pays : United States
Commentaires et corrections
Type : ErratumIn
Informations de copyright
Published by Elsevier Inc.
Références
J Cardiovasc Comput Tomogr. 2013 Jul-Aug;7(4):256-66
pubmed: 24148779
Circ Res. 2017 Oct 13;121(9):1092-1101
pubmed: 28794054
Circulation. 2017 Jul 18;136(3):263-276
pubmed: 28483812
JAMA. 2003 Aug 20;290(7):891-7
pubmed: 12928465
JAMA. 2006 Oct 11;296(14):1735-41
pubmed: 17032986
J Am Coll Cardiol. 2015 Jul 28;66(4):337-46
pubmed: 26205589
J Clin Epidemiol. 2010 Aug;63(8):826-33
pubmed: 20630332
Eur Heart J. 2017 Feb 14;38(7):500-507
pubmed: 27252451
J Invest Dermatol. 2009 Oct;129(10):2411-8
pubmed: 19458634
Circ Arrhythm Electrophysiol. 2018 Jan;11(1):e005499
pubmed: 29326129
Radiology. 2014 Sep;272(3):690-9
pubmed: 24754493
Am J Med. 2011 Feb;124(2):95-102
pubmed: 21295188
Eur Heart J. 2010 Apr;31(8):1000-6
pubmed: 20037179
Am J Med. 2011 Aug;124(8):775.e1-6
pubmed: 21787906
J Cardiovasc Comput Tomogr. 2018 May - Jun;12(3):204-209
pubmed: 29753765
Eur Heart J. 2015 Oct 14;36(39):2662-5
pubmed: 26188212
Am J Physiol Heart Circ Physiol. 2017 May 1;312(5):H867-H873
pubmed: 28258057
Arterioscler Thromb Vasc Biol. 2015 Dec;35(12):2667-76
pubmed: 26449753
Eur Heart J. 2017 Feb 21;38(8):598-608
pubmed: 27436865
J Cardiovasc Comput Tomogr. 2014 Sep-Oct;8(5):368-74
pubmed: 25301042
Mediators Inflamm. 2010;2010:
pubmed: 20706689
Proc AMIA Symp. 2000;:156-60
pubmed: 11079864