Abstract: Objective To explore the predictive value of systemic immune-inflammation index (SII) for stroke-associated pneumonia (SAP) in patients with acute ischemic stroke (AIS). Methods A total of 305 AIS patients who were admitted to the Affiliated Hospital of Xuzhou Medical University from January 2020 to December 2020 were retrospectively enrolled. According to the presence of SAP, the patients were divided into two groups: an SAP group and a non-SAP group. Their general information was collected, including gender, age, and disease history. Their OCSP classification of acute cerebral infarction and NIHSS score at admission, as well as the presence of dysphagia, nasal feeding, the use of antacids, and preventive use of antibiotics were recorded. The laboratory indexes of their peripheral venous blood were recorded within 24 h after admission, including blood routine and blood biochemical test, so as to calculate SII. 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 AIS patients, there were 39 patients (12.79%) who developed SAP, and 266 patients (87.21%) without SAP. According to univariate analysis, the SAP group presented a higher SII than the non-SAP group (P<0.05). Logistic regression analysis showed that SII was an independent risk factor for SAP. According to ROC curve analysis, the area under the curve of SII to predict SAP was 0.843 (95% CI: 0.798-0.882). When the cut-off value of SII in predicting SAP in AI patients was set as 885.05, the sensitivity was 79.5% and the specificity was 85.0%. Conclusions SII is a potential independent risk factor for SAP in AIS patients, which has certain predictive value.