Objective To develop and validate a risk prediction model for poor prognosis in patients treated with acute cerebral infarction undergoing endovascular therapy. Methods From January 1， 2020 to December 31， 2022， 180 patients with acute cerebral infarction who underwent early endovascular therapy in the Department of Neurology， Suzhou Hospital of Anhui Medical University were selected for the study. Patient general information and treatment process were collected through the Hospital Management Information System （HMIS）. The National Institutes of Health Stroke Scale（ NIHSS） was used to assess the degree of neurological deficit， the Alberta Stroke Program Early CT Score（ ASPECTS） was used to evaluate the degree of cerebral tissue damage caused by early ischemic changes， and the Modified Rankin Scale（ mRS） was used to evaluate the neurological recovery of stroke patients. Patients were categorized into a good prognosis group（ mRS score ≤2） and a poor prognosis group（ mRS score ＞2） based on the mRS score at 3 months. Risk factors of prognosis were analyzed using multifactorial Logistic regression， and the model was constructed and presented in the form of a nomogram. Consistency of the model was assessed by plotting the calibration curve using the Bootstrap method with 1 000 self-sampling iterations， and decision curve analysis（ DCA） was performed to assess its clinical applicability. Results There were 98 patients in good prognosis group and 82 patients in poor prognosis group. Multifactorial Logistic regression analysis showed that pre-onset mRS score［ OR（ 95%CI）=2.383（ 1.372，4.105）］， ASPECTS［ OR（ 95%CI）=0.481（0.272，0.874）］， and hemorrhagic transformation［ OR（95%CI）=16.370（1.941， 138.220）］ were independent risk factors of patients' prognosis， and the differences were statistically significant （all P＜ 0.05）. The area under the curve（ AUC） of the prediction model was 0.88［ 95%CI（ 0.82，0.94）］. The sensitivity was 0.887， the specificity was 0.792， and the optimal cutoff value was 0.482. The P-value of the Hosmer-Lemeshow test was 1.000， indicating good predictive performance of the model. Conclusions The risk prediction model based on pre-onset mRS score， ASPECTS score， hemorrhagic transformation， and other risk factors of the prognosis of patients after treatment can assist in predicting the prognosis of patients treated with endovascular therapy for acute cerebral infarction.