Objective：To construct a predictive model for poor 90-day prognosis after endovascular treatment（EVT）in patients with large vessel occlusion-acute ischemic stroke（LVO-AIS）and to explore its predictive value. Methods：Two hundred patients with LVOAIS diagnosed and treated in Zhumadian Central Hospital from January 2020 to December 2023 were retrospectively selected. According to the prognosis，the patients were divided into a good prognosis group（112 cases）and a poor prognosis group（88 cases）. The clinical data and treatment-related indicators of the two groups were compared. Lasso-Logistic regression was used to analyze the influencing factors of poor 90-day prognosis after EVT in patients with LVO-AIS. The prediction model was constructed and visualized by nomogram. The prediction accuracy and predictive value of the prediction model were evaluated by calibration curve and receiver operating characteristic（ROC）curve，and external validation was performed. Results：Compared with the good prognosis group，the proportion of hypertension，the National Institutes of Health stroke scale（NIHSS）score at admission，the neutrophil-to-lymphocyte ratio （NLR）at admission，and the number of occluded vessels ≥ 2 were higher in the poor prognosis group. The Alberta stroke program early CT（ASPECT）score was lower at admission（P ＜ 0.05）. The time from onset to operation and the time from onset to recanalization in the poor prognosis group were longer than those in the good prognosis group，and the proportion of modified thrombolysis in cerebral infarction（mTICI）grade ≥ 2b in the poor prognosis group was lower than that in the good prognosis group（P ＜ 0.05）. Hypertension， NHISS score at admission，NLR at admission，ASPECT score at admission，time from onset to recanalization，and mTICI grade were independent prognostic factors（P ＜ 0.05）. The AUC of the combined model based on each index to predict the poor 90-day prognosis after EVT of LVO-AIS patients was 0.900，and the predictive value was high. The external validation further showed that the model had reliable predictive value. Conclusion：Hypertension，NHISS score at admission，NLR at admission，ASPECTS score at admission，time from onset to reperfusion，and mTICI classification are related to the prognosis of patients with LVO - AIS. The combined model constructed based on these indicators can provide a reference for predicting the 90 - day prognosis of patients after EVT，and guide clinical treatment accordingly.