This study was a retrospective cohort study which established a predictive model of adjacent vertebral re-fracture (VRF) after percutaneous kyphoplasty (PKP) for osteoporotic vertebral compression fracture (OVCF). To establish a predictive model to evaluate the risk of adjacent vertebral re-fracture after PKP for OVCF based on perioperative imaging data. Patients who underwent PKP for OVCF in our hospital between January 2018 and December 2020 were enrolled and divided into re-fracture group and normal group. Perioperative imaging data including preoperative bone mineral density (BMD), fatty infiltration (FI%) of paravertebral muscle, sagittal parameters of spine and pelvis, recovery rate of vertebral height were collected. The prediction model is obtained by multi-factor logistic regression analysis. A total of 242 patients were included, including 23 cases of VRF group and 219 cases of normal group. There were statistical differences in BMD, FI%, recovery rate of vertebral height and sagittal imbalance between the two groups. ROC curve analysis of continuous variables showed that BMD≤-2.80, FI%≥40% and recovery rate of vertebral height≥10% were the cut-off values. Logistic regression analysis showed that BMD≤-2.80, FI%≥40% and sagittal imbalance were independent risk factors for VRF. The area under the curve (AUC) according to the predicted probability was 0.85 (P<0.05). After simplifying the model, the total point of the model was 7 points, with a cut-off value of 5 points. The prediction model obtained in this study can predict re-fracture after PKP for OVCF early and effectively. It has an excellent predictive effect which is suitable for clinicians.