Application of machine learning to determine top predictors of noncalcified coronary burden in psoriasis: An observational cohort study - 03/03/20

Doi : 10.1016/j.jaad.2019.10.060

Eric Munger, MS ^a, Harry Choi, MSE ^b, Amit K. Dey, MD ^b, Youssef A. Elnabawi, MD ^b, Jacob W. Groenendyk, MD ^b, Justin Rodante, PA-C ^b, Andrew Keel, RN ^b, Milena Aksentijevich, MSc ^b, Aarthi S. Reddy, BS ^b, Noor Khalil, BA ^b, Jenis Argueta-Amaya, BS ^b, Martin P. Playford, PhD ^b, Julie Erb-Alvarez, MPH ^b, Xin Tian, PhD ^b, Colin Wu, PhD ^b, Johann E. Gudjonsson, MD, PhD ^c, Lam C. Tsoi, PhD ^c, Mohsin Saleet Jafri, PhD ^a, Veit Sandfort, MD ^b, Marcus Y. Chen, MD ^b, Sanjiv J. Shah, MD ^d, David A. Bluemke, MD, PhD ^e, Benjamin Lockshin, MD ^f, Ahmed Hasan, MD, PhD ^b, Joel M. Gelfand, MD, MSCE ^g, Nehal N. Mehta, MD, MSCE ^b,^⁎
^a George Mason University, Fairfax, Virginia
^b National Heart, Lung, and Blood Institute, National Institutes of Health, Bethesda, Maryland
^c University of Michigan, Ann Arbor, Michigan
^d Northwestern University, Chicago, Illinois
^e University of Wisconsin, Madison, Wisconsin
^f DermAssociates, Silver Spring, Maryland
^g University of Pennsylvania, Philadelphia, Pennsylvania

^∗Correspondence to: Nehal N. Mehta, MD, MSCE, Chief, Section of Inflammation and Cardiometabolic Disease, National Heart, Lung, and Blood Institute, 10 Center Dr, Clinical Research Center, Room 5-5140, Bethesda, MD 20892.Section of Inflammation and Cardiometabolic DiseaseNational Heart, Lung, and Blood Institute10 Center DrClinical Research CenterRoom 5-5140BethesdaMD20892

Sous presse. Épreuves corrigées par l'auteur. Disponible en ligne depuis le Tuesday 03 March 2020
Cet article a été publié dans un numéro de la revue, cliquez ici pour y accéder

Abstract

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

In this study, we used machine learning algorithms to determine the top predictors of noncalcified coronary burden by CCTA in psoriasis.

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

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

We were unable to provide external validation and did not study cardiovascular events.

Conclusion

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.

Le texte complet de cet article est disponible en PDF.

Key words : atherosclerosis, cardiometabolic disease, coronary artery disease, machine learning, psoriasis, random forest algorithm

Abbreviations used : CCTA, CRP

Plan

Machine learning algorithm

Statistical analyses

Results

Discussion

	Funding sources: Supported by the National Heart, Lung, and Blood Institute Intramural Research Program (HL006193-05). This research was also made possible through the National Institutes of Health (NIH) Medical Research Scholars Program, a public-private partnership supported jointly by the NIH and generous contributions to the Foundation for the NIH from the Doris Duke Charitable Foundation (grant no. 2014194), the American Association for Dental Research, the Colgate-Palmolive Company, Genentech, Elsevier, and other private donors. The funding sources had no role in the design and conduct of the study; collection, management, analysis, and interpretation of the data; preparation, review, or approval of the manuscript; and decision to submit the manuscript for publication.
	Disclosure: Dr Gelfand is a copatent holder of resiquimod for treatment of cutaneous T-cell lymphoma and in the past 12 months has served as a consultant for Coherus (data and safety monitoring board), Dermira, Janssen Biologics, Merck (data and safety monitoring board), Novartis, Regeneron, Dr Reddy's Labs, Sanofi, and Pfizer, receiving honoraria; receives research grants (to the Trustees of the University of Pennsylvania) from AbbVie, Janssen, Novartis, Regeneron, Sanofi, Celgene, and Pfizer In; and received payment for continuing medical education work related to psoriasis that was supported indirectly by Lilly and AbbVie. Dr Mehta is a fulltime US government employee and has served as a consultant for Amgen, Eli Lilly, and Leo Pharma, receiving grants/other payments; as a principal investigator and/or investigator for AbbVie, Celgene, Janssen Pharmaceuticals, and Novartis, receiving grants and/or research funding; and as a principal investigator for the National Institutes of Health, receiving grants and/or research funding. Mr Munger; Mr Choi; Drs Dey, Elnabawi, and Groenendyk; Mr Rodante; Mr Keel; Ms Aksentijevich; Ms Reddy; Mr Khalil; Ms Argueta-Amaya; Dr Playford; Ms Erb-Alvarez; and Drs Tian, Wu, Gudjonsson, Tsoi, Jafri, Sandfort, Chen, Shah, Bluemke, Lockshin, and Hasan have no conflicts of interest to declare.
	IRB approval status: Approved.
	Reprints not available from the authors.