Predicting the likelihood of cardiovascular disease in patients with rheumatoid arthritis: development and Validation of a Novel Model
Year: 2023
Type: preprint
Study design: Observational Study
Abstract: BackgroundPatients with rheumatoid arthritis (RA) have increased mortality and morbidity due to cardiovascular disease (CVD). Distinguishing RA with CVD, RA with CVD risk factors and patients with RA only (pure RA), is still a challenge. The study aimed to develop a better model to predict the likelihood of CVD in RA.MethodsPure RA (n = 402), RA with CVD risk factors (n = 394), and RA with CVD (n = 201) were ultimately recruited into the study and their peripheral bloods were collected to measure the levels of routine examination indicators, vascular endothelial growth factor (VEGF) and immune cells. Univariate analysis, the least absolute shrinkage and selection operator (LASSO), the random forest (RF) and the logistic regression models (LR) were employed to screen characteristic variables between each two groups, and individualized nomograms were further established to more conveniently predict the likelihood of CVD in RA.ResultsUnivariate analysis showed that the levels of WBC, BUN, creatinine, CK, LDH and VEGF were significantly elevated in RA with CVD, as well as serum TC, TG, LDL, ApoB100 and ApoE, while ApoA1 and HDL/CHOL were decreased. Furthermore, the ratio of Treg cells, exhibiting excellent separation performance, in RA with CVD was significantly lower than that in other groups, while the ratio of Th1/Th2/NK and Treg were significantly elevated. LASSO, RF and LR models were also used to find the risk factors for CVD in RA. Through the final selected indicators screened by three machine learning models and univariate analysis, a convenient nomogram was established for predicting CVD risk in RA.ConclusionsSerum lipids, lipoproteins, and Treg cells have been identified as risk factors for CVD in patients with RA, and three nomograms combining various risk factors were constructed and were used for individualized prediction of CVD in patients with RA (pure RA and/or with CVD risk factors).
Source: Research Square
Authors: Min Feng, Fanxing Meng, Jiali Yu, Yanlin Wang, Yan Qin, Yuhan Jia, Guozhen Ji, Zhaojun Liang, Chong Gao, Hui Guo, Jing Luo
Language: English
Subfield: Rheumatology
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W4377820217