Objective:To investigate the predictive value of a nomogram based on multimodal CT parameters for the outcome of endovascular therapy (EVT) in patients with acute vertebrobasilar artery occlusion (AVBAO).Methods:Patients with AVBAO underwent EVT at Xuzhou Central Hospital from January 2021 to March 2024 were included retrospectively. At 90 days after EVT, the modified Rankin Scale was used to evaluate clinical outcome. 0-3 points were defined as good outcome and 4-6 points were defined as poor outcome. Multivariate stepwise logistic regression model was used to screen for predictive variables. Then a nomogram was drawn and the prediction model was evaluated. Results:A total of 91 patients with AVBAO were included. There were 60 males (65.9%), aged 69.09±10.57 years. Thirty-eight patients (41.8%) had good outcome, 53 (58.2%) had poor outcome, and 35 (38.5%) died. Univariate analysis showed that there were significant differences in white blood cell count, neutrophil count, National Institutes of Health Stroke Scale (NIHSS) score, Glasgow Coma Scale (GCS) score, posterior circulation Alberta Stroke Program Early CT Score (pc-ASPECTS), Basilar Artery on Computed Tomography Angiography (BATMAN) score, core infarct volume, mismatched volume ratio, onset to door time between the poor outcome group and the good outcome group (all P<0.05). The above indicators were included in a binary multivariate stepwise logistic regression model. The results showed that higher NIHSS scores (odds ratio [ OR] 1.154, 95% confidence interval [ CI] 1.070-1.244; P<0.001), lower BATMAN scores ( OR 0.626, 95% CI 0.416-0.943; P=0.025), and larger core infarct volumes ( OR 1.147, 95% CI 1.046-1.258; P=0.004) on admission were the independent risk factors for poor outcome. A nomogram was plotted using the above three independent risk factors as predictor variables. Its area under the receiver operating characteristic curve for predicting poor outcome was 0.942 (95% CI 0.894-0.990). The sensitivity and specificity were 81.1% and 97.4%, respectively. The calibration curve fluctuates within a small range around the ideal curve. A mean absolute error was 0.027 and a mean square error was 0.001. The clinical decision curve suggested that the model had good clinical applicability. The dynamic nomogram is shown in: https://yuepeng.shinyapps.io/VBAO_model/. Conclusion:The nomogram prediction model based on multimodal CT parameters has good predictive performance for poor outcome in patients with AVBAO after EVT.