AUTHOR=Huang Guoqing , Jin Qiankai , Tian Xiaoqing , Mao Yushan 

TITLE=Development and validation of a carotid atherosclerosis risk prediction model based on a Chinese population

JOURNAL=Frontiers in Cardiovascular Medicine

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2022.946063

DOI=10.3389/fcvm.2022.946063

ISSN=2297-055X

ABSTRACT=Abstract
Purpose: This study aimed to identify independent risk factors for carotid atherosclerosis (CAS), and to construct and validate a CAS risk prediction model based on the Chinese population.
Methods: 4570 Chinese adults were included in this retrospective study, who underwent health checkups (including carotid ultrasound) at Zhenhai Lianhua Hospital, Ningbo, China in 2020. All participants were randomly assigned to the training and validation sets at a ratio of 7:3. Independent risk factors associated with CAS were identified by multivariate logistic regression analysis. The least absolute shrinkage and selection operator combined with 10-fold cross-validation screened for characteristic variables, while nomograms were plotted to demonstrate the risk prediction model. C-index and receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA) were used to evaluate the discrimination, calibration, and clinical applicability of the risk model.
Results: Age, body mass index (BMI), diastolic blood pressure (DBP), white blood cell count (WBC), mean platelet volume (MPV), ALT, AST, gamma-glutamyl transferase (GGT) were identified as independent risk factors for CAS. In the training set, internal validation set, and external validation set, the risk model showed good discriminatory power with a C-index of 0.961 (0.953-0.969), 0.953 (0.939-0.967), and 0.930 (0.920-0.940), and excellent calibration. The results of DCA showed that the prediction model could benefit when the risk threshold probabilities were 1%-100% in all set. Finally, a network computer (dynamic nomogram) was developed to facilitate the clinical operations of physicians. The website is as follows: https://nbuhgq.shinyapps.io/DynNomapp/.
Conclusion: The development of risk models contributes to the early identification and prevention of CAS, which is important for the prevention and reduction of adverse cardiovascular and cerebrovascular prognostic events.