Risk Factors and Prediction Model of Intrastent Restenosis after Coronary Stent Implantation

WEI Ke; WANG He; LUO Minghua; CHEN Yushan; GUAN Huaimin

doi:10.12102/j.issn.1672-1349.2025.07.016

Abstract：Objective: To analyze the risk factors for in-stent restenosis (ISR) after coronary stent implantation and to construct a risk prediction model for ISR, aiming to identify high-risk patients after percutaneous coronary intervention (PCI). Methods: A total of 576 patients who underwent coronary stent implantation at the First Affiliated Hospital of Henan University of Traditional Chinese Medicine between January 2015 and December 2016 and underwent coronary angiography for follow-up 12–18 months postoperatively were selected. According to the results of coronary angiography, the patients were divided into two groups: the non-ISR group (525 cases) and the ISR group (51 cases). The medical history, blood biochemical indicators, coronary artery lesion characteristics, and stent conditions of the two groups were analyzed. Multivariate logistic regression analysis was used to identify the risk factors for ISR after PCI. Additionally, predictive models for ISR after PCI were constructed based on logistic regression, random forest, and support vector machine algorithms. Results: Hypertension (OR=2.177), diabetes (OR=2.122), smoking (OR=2.505), fibrinogen (OR=1.624), number of stents (OR=1.839), and stent length (OR=1.063) were identified as independent risk factors for ISR after PCI. The areas under the receiver operating characteristic (ROC) curves (AUC) of the ISR prediction models constructed using logistic regression, random forest, and support vector machine algorithms were 0.83, 0.81, and 0.78, respectively. Conclusion: Smoking, diabetes, hypertension, plasma fibrinogen, number of stents, and stent length are independent risk factors for ISR after PCI. Constructing a risk prediction model for ISR after PCI based on logistic regression, random forest, and support vector machine algorithms is feasible and can help doctors identify high-risk patients after PCI.