BACKGROUND In-stent restenosis (ISR) remains a major cause of failure of contemporary percutaneous revascularization therapies. Invasive biomarkers to improve the prognosis of ISR should be considered. This study aimed to investigate the association between plasma ANRIL expression and ISR. MATERIAL AND METHODS A total of 444 patients were included in this research. Serial coronary angiography was performed at baseline (before and after intervention) and within 36 months' follow-up. ISR was defined as >50% diameter stenosis at follow-up. ANRIL expression was quantified using reverse transcription-PCR. An area under the ROC curve (auROC) was generated to assess the diagnostic values of ANRIL. Logistic regression models were used to assess the independent risk factors for ISR. RESULTS Plasma ANRIL expression was significantly increased in patients with ISR, as compared with that in patients without ISR (1.6 [1.1-2.5] vs. 0.9 [0.6-1.3], P<0.001). The auROC (95% confidence interval [CI]) of plasma ANRIL in diagnosing ISR was 0.745 (0.687-0.811). Multiple logistic regression models indicated that drinking (odds ratio [OR]=2.09, 95% CI: 1.08-4.04, P=0.028), hypertension (OR=2.01, 95% CI: 1.14-3.57, P=0.017), diabetes (OR=3.15, 95% CI: 1.63-3.57, P<0.001), low-density lipoprotein (OR=3.14, 95% CI: 1.57-6.31, P=0.001), and ANRIL (OR=2.21, 95% CI: 1.68-2.92, P<0.001) were the independent risk factors for ISR. CONCLUSIONS We found that higher ANRIL expression is associated with ISR, indicating that ANRIL may be an optimal prognostic factor for ISR.