AI Article Synopsis

  • Psoriasis patients face a higher risk of heart attacks and increased noncalcified coronary burden, which can be evaluated using coronary computed tomography angiography (CCTA).
  • This study utilized machine learning algorithms on data from 263 patients to identify key predictors of noncalcified coronary burden, focusing on variables related to body composition and inflammation.
  • The top predictors included factors like body mass index and levels of certain lipoproteins, suggesting that addressing obesity, dyslipidemia, and inflammation is vital in managing psoriasis-related health risks.

Article 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.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7428853PMC
http://dx.doi.org/10.1016/j.jaad.2019.10.060DOI Listing

Publication Analysis

Top Keywords

noncalcified coronary
28
coronary burden
24
machine learning
20
top predictors
16
predictors noncalcified
16
determine top
12
coronary
8
learning algorithms
8
burden ccta
8
random forest
8

Similar Publications

Impact of diabetes mellitus on coronary artery plaque characteristics and outcomes in the SCOT-HEART trial.

J Cardiovasc Comput Tomogr

January 2025

British Heart Foundation Centre for Cardiovascular Science, University of Edinburgh, United Kingdom; Edinburgh Imaging, University of Edinburgh, United Kingdom. Electronic address:

Background: Diabetes mellitus is an established cardiovascular risk factor. We assessed the impact of diabetes mellitus on quantitative plaque and long-term outcomes in patients with and without diabetes mellitus in the Scottish COmputed Tomography of the HEART (SCOT-HEART) trial.

Methods: Coronary artery calcium (CAC) was assessed on non-contrast computed tomography (CT).

View Article and Find Full Text PDF

Aim: To evaluate characteristics of atherosclerotic plaques (ASP) remaining after percutaneous coronary intervention (PCI) in patients with acute coronary syndrome (ACS) by coronary computed tomography angiography (CCTA).

Material And Methods: Among 249 patients (193 men) with ACS aged 58±10 years, 183 (73.5%) had myocardial infarction, 66 (26.

View Article and Find Full Text PDF

Epicardial Adipose Tissue from Computed Tomography: a Missing Link in Premature Coronary Artery Disease?

Eur Heart J Cardiovasc Imaging

January 2025

Sorbonne Université, unité d'imagerie cardiovasculaire et thoracique, Hôpital La Pitié Salpêtrière (AP-HP), Laboratoire d'Imagerie Biomédicale, INSERM, CNRS, Institute of Cardiometabolism and Nutrition, ACTION Group, Paris, France.

Purpose: Epicardial adipose tissue (EAT) could contribute to the specific atherosclerosis profile observed in premature coronary artery disease (pCAD) characterized by accelerated plaque burden (calcified and non-calcified), high risk plaque features (HRP) and ischemic recurrence. Our aims were to describe EAT volume and density in pCAD compared to asymptomatic individuals matched on CV risk factors and to study their relationship with coronary plaque severity extension and vulnerability.

Materials And Methods: 208 patients who underwent coronary computed tomography angiography (CCTA) were analyzed.

View Article and Find Full Text PDF

Background: Preliminary research indicates that higher iron levels are associated with worse outcomes in patients with coronary artery disease.

Aims: The study aimed to investigate the relationship between iron levels and the type and composition of coronary plaques.

Methods: In patients with ≥1 coronary stenosis ≥50% on computed tomography angiography, iron levels, presence of high-risk plaque features, such as low-attenuation plaque (LAP), napkin-ring sign, positive remodeling, and spotty calcium, as well as type and plaque composition (calcified/fibrous/fibro-fatty/necrotic core) were evaluated.

View Article and Find Full Text PDF

This systematic review explores the relationship between achieving minimal disease activity in psoriasis and the progression of atherosclerosis. It investigates how biologic therapies and other treatments impact atherosclerosis markers, offering insights into therapeutic strategies. A comprehensive search of PubMed, Embase, and Web of Science was conducted from January 1, 2000, to April 1, 2023, using terms such as psoriasis, psoriatic arthritis, atherosclerosis, biologic therapy, vascular stiffness, carotid intima-media thickness (CIMT), and coronary computed tomography angiography (CCTA).

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!