Objective To investigate the independent risk factors for epilepsy after reperfusion therapy in acute ischemic stroke and construct a nomogram prediction model.

Methods A total of 386 patients with acute ischemic stroke who received reperfusion therapy were selected as the study subjects. Based on whether they developed secondary epilepsy, the patients were divided into epilepsy group (n=55) and non-epilepsy group (n=331). Clinical data of the two groups were collected and compared. Univariate and multivariate logistic regression analyses were used to screen for independent risk factors for epilepsy after reperfusion therapy. A nomogram prediction model was constructed based on the aforementioned factors, and its predictive performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve. Calibration was assessed using calibration curves and the Hosmer-Lemeshow test, clinical utility was examined through decision curve analysis, and internal validation of the model was performed using ten-fold cross-validation and Bootstrap resampling.

Results Multivariate logistic regression analysis revealed that cortical involvement (OR=3.79, 95%CI, 1.64 to 8.75), hemorrhagic transformation (OR=5.00, 95%CI, 1.82 to 13.75) and early-onset seizures (OR=5.87, 95%CI, 2.06 to 16.73) were independent risk factors for epilepsy after reperfusion therapy (P < 0.05). The nomogram prediction model constructed based on these factors demonstrated good predictive performance, with AUC of 0.809 (95%CI, 0.735 to 0.871), sensitivity of 0.602, and specificity of 0.906. The model was well-calibrated (Hosmer-Lemeshow test, P=0.566), and the decision curve indicated its clinical utility within a wide range of threshold probabilities (0.10 to 0.63). The ten-fold cross-validation AUC was 0.807 (95%CI, 0.717 to 0.897), and the Bootstrap resampling AUC was 0.802 (95%CI, 0.794 to 0.806).

Conclusion Cortical involvement, hemorrhagic transformation and early-onset seizures are independent risk factors for epilepsyafter reperfusion therapy in acute ischemic stroke. The nomogram prediction model constructed in this study demonstrates good predictive accuracy and clinical utility, providing a reference for individualized risk assessment.