Abstract: Objective To analyze the clinical characteristics of acute diquat poisoning complicated by central nervous system injury (CNSI) and identify early risk factors, aiming to provide a theoretical basis for reducing mortality in diquat poisoning with CNSI. Methods Clinical data from patients with acute diquat poisoning admitted to the Emergency Department of Fuyang People's Hospital Affiliated to Anhui Medical University between October 2019 and October 2024 were retrospectively analyzed. Patients were divided into CNSI and non-CNSI groups based on complications. Clinical features were compared between groups, and variables with statistical significance were subjected to binary logistic regression to identify independent risk factors for CNSI. Receiver operating characteristic (ROC) curves were generated to evaluate the predictive value of these factors. Results A total of 63 eligible patients were included, with 18 deaths (28.57%) and 26 cases (41.27%) complicated by CNSI. The median time from diquat ingestion to CNSI onset was 15.5 (9.8-31.3) hours. The CNSI group exhibited significantly higher mortality rates and required more frequent respiratory support and anti-shock therapy than the non-CNSI group (P <0.05 for all). Multivariate binary logistic regression identified diquat plasma concentration (≥ 549.95 ng/mL) and APACHE II score as independent risk factors for CNSI (P <0.05). Both factors demonstrated predictive value for CNSI, with combined use showing superior predictive performance compared to individual indicators (P <0.05). Conclusion CNSI is a fatal complication of acute diquat poisoning with high mortality. Diquat plasma concentration (≥ 549.95 ng/mL) and APACHE II score are independent risk factors for CNSI, and their combined application enhances predictive accuracy. These findings underscore the importance of early risk stratification and targeted interventions in high-risk populations.