Random forest vs. logistic regression: Predicting angiographic in-stent restenosis after second-generation drug-eluting stent implantation

Abstract

As the rate of percutaneous coronary intervention increases, in-stent restenosis (ISR) has become a burden. Random forest (RF) could be superior to logistic regression (LR) for predicting ISR due to its robustness. We developed an RF model and compared its performance with the LR one for predicting ISR. We retrospectively included 1501 patients (age: 64.0 ± 10.3; male: 76.7%; ISR events: 279) who underwent coronary angiography at 9 to 18 months after implantation of 2nd generation drug-eluting stents. The data were randomly split into a pair of train and test datasets for model development and validation with 50 repeats. The predictive performance was assessed by the area under the curve (AUC) of the receiver operating characteristic (ROC). The RF models predicted ISR with larger AUC-ROCs of 0.829 ± 0.025 compared to 0.784 ± 0.027 of the LR models. The difference was statistically significant in 29 of the 50 repeats. The RF and LR models had similar sensitivity using the same cutoff threshold, but the specificity was significantly higher in the RF models, reducing 25% of the false positives. By removing the high leverage outliers, the LR models had comparable AUC-ROC to the RF models. Compared to the LR, the RF was more robust and significantly improved the performance for predicting ISR. It could cost-effectively identify patients with high ISR risk and help the clinical decision of coronary stenting.

A risk score for predicting in-stent restenosis in patients with premature acute myocardial infarction undergoing percutaneous coronary intervention with drug-eluting stent

“…Lastly, our study in premature AMI patients identified metabolic variables, including DM, elevated LDLC, SBP, and BMI, as independent predictors of ISR, thus supporting and expanding upon existing research findings. While some studies indicated that metabolic syndrome did not heighten ISR risk, others have provided evidence that specific metabolic indicators independently forecasted ISR risk [ 24 , 33 , 34 ]. Restenosis progression commenced shortly after the intervention, with ISR arising from endothelial damage caused by PCI and subsequent neointimal and vascular smooth muscle cell (VSMC) proliferation.…”

“…However, when combined, the CKM score achieved an AUC-ROC of 0.834, outperforming other established ISR risk prediction models [ 4 , 6 , 9 ]. Furthermore, the predictive power of the CKM score was externally validated in an independent cohort, which is a rarity in most models [ 5 , 24 , 34 ]. In light of these findings, the newly proposed CKM score holds three practical implications for the assessment and management of patients with premature AMI.…”