OBJECTIVE: To determine the predictors of late lumen restenosis after coronary drug-coated balloon angioplasty, and to construct a nomogram-based clinical model to enhance prediction accuracy for late lumen restenosis. METHODS: The ambispective, observational study was conducted at Cangzhou People's Hospital, Cangzhou, China, between January 2021 and December 2024, and comprised patients who underwent coronary drug-coated balloon angioplasty. Data was collected retrospectively from medical records, and the patients were followed for 6-12 months postoperatively. The patients were categorised into late lumen restenosis group A and non-late lumen restenosis group B. Potential risk factors and independent predictors were determined. A nomogram model was developed based on the independent predictors. Internal validation was performed via bootstrap resampling, and the predictive performance and clinical utility of the model were comprehensively evaluated using receiver operating characteristic curves, calibration curves, and decision curve analysis. Data was analysed using SPSS 26. RESULTS: Of the 136 patients, 44(32.4%) were in group A; 30(68.8%) males and 14(31.82%) females with median age 57.5 (interquartile range: 53-65 years). There were 92(67.6%) patients in group B; 54(58.7%) males and 38(41.3%) females with median age 58 years (interquartile range: 51-64 years) (p>0.05). Risk factors significantly associated with late lumen restenosis included preoperative target lesion stenosis severity, history of hypertension, immediate postoperative residual lumen stenosis >30%, and major adverse cardiovascular events (p<0.05). Preoperative target lesion stenosis severity, history of hypertension, and immediate postoperative residual lumen stenosis >30% were independent predictors of late lumen restenosis (p<0.05). The nomogram model demonstrated an area under the curve of 0.792 (95% confidence interval: 0.71-0.875) in the bootstrap internal validation. The calibration curve indicated a high concordance between predicted and observed probabilities (Hosmer Lemeshow test: χ²=6.89, p=0.219), and decision curve analysis confirmed the good clinical applicability of the model. CONCLUSION: Preoperative target lesion stenosis severity, history of hypertension, and immediate postoperative residual lumen stenosis >30% were found to be predictors of late lumen restenosis following coronary drug-coated balloon angioplasty, enabling the development of a nomogram model with strong discriminatory power and clinical utility.