Abstract: ob＜x＞jective To explore the predictive value of systemic immune -inflammation index in stroke-associated pneumonia in patients with acute ischemic stroke. Methods A total of 305 cases with AIS admitted to The Affiliated Hospital of Xuzhou Medical University from January 2020 to December 2020 were retrospectively enrolled.All patients were divided into into SAP group and non-SAP group ba＜x＞sed on whether stroke-associated pneumonia occurred.Collect the patient’s general demographic information such as gender,age,history of smoking,drinking,hypertension,diabetes,hyperlipidemia,coronary heart disease, atrial fibrillation,stroke,and record the patient’s OCSP classification of acute cerebral infarction , NIHSS score at admission,the presence or absence of dysphagia,nasal feeding,use of antacids, preventive use of antibiotics, etc, the laboratory indexes of peripheral venous blood were recorded 24 hours after admission,Including blood routine (white blood cell count, neutrophil count, lymphocyte count, platelet count, etc.), blood biochemistry (blood lipids, fasting blood glucose) , and calculate SII ba＜x＞sed on the results of blood routine. Univariate and multivariate logistic regression analyses were used to assess the independent correlation between SII and SAP. The receiver operating characteristic (ROC) curve was used to evaluate the predictive value of SII to SAP. Results Among 305 patients with AIS, 39 cases (12.79%) developed SAP,and 266 cases (87.21%) did not develop SAP. Univariate analysis showed that the SII in SAP group was higher than that in non-SAP group(P<0.05). Logistic regression analysis showed that SII is an independent risk factor for SAP. ROC curve analysis showed that the area under the curve of SII was 0.843(95% CI:0.798～0.882), the cut-off value for predicting SAP was 885.05,the sensitivity and specificity was 79.5% and 85.0% . Conclusion SII was a potential independent risk factor for the occurrence of SAP in AIS patients, which has a certain predictive value