A predictive model of symptomatic intracerebral hemorrhage after thrombolysis for acute ischemic stroke: A retrospective study

Accurate prediction of symptomatic intracerebral hemorrhage (sICH) after intravenous thrombolysis (IVT) for acute ischemic stroke (AIS) is essential for improving clinical decision-making. This study aimed to develop and validate a novel predictive model that incorporates updated sICH criteria in a Chinese cohort. This study conducted a retrospective cohort study including patients who underwent IVT for AIS between January 2014 and December 2020. The primary outcome was the occurrence of sICH within 7 days of treatment. A multivariable logistic regression model was constructed to predict sICH. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration plots (assessed with the Hosmer–Lemeshow test), and decision curve analysis (DCA) to estimate clinical utility. All predictors included in the final model were assessed before thrombolysis administration. A total of 462 consecutive patients treated with IVT for AIS were enrolled. Among them, 42 patients (9.1 %) developed sICH. The final model incorporated door-to-needle time, baseline National Institutes of Health Stroke Scale (NIHSS) score, D -dimer level, and the presence of a hyperdense cerebral artery sign (HCAS). The model demonstrated strong discriminatory power, with an AUC of 0.832 (95 % confidence interval: 0.767–0.897), specificity of 86.3 %, sensitivity of 75.0 %, and overall accuracy of 85.7 %. Calibration plots confirmed good model fit, while DCA indicated favorable clinical utility across a wide range of threshold probabilities. The prediction model developed and validated in this study shows high accuracy in identifying AIS patients at risk of sICH following IVT, supporting its potential use in clinical practice.