Development of a prediction model for hemorrhagic transformation after intravenous thrombolysis in patients with acute ischemic stroke: a retrospective analysis.

Background: Hemorrhagic transformation (HT) is a serious and common complication following intravenous thrombolysis in acute ischemic stroke (AIS), often leading to worsened outcomes. Identifying risk factors for HT and developing accurate predictive models are essential for improving patient management and prognosis.

Methods: A retrospective analysis was performed on 159 patients with acute ischemic stroke who received intravenous thrombolytic therapy at Hubei Third People's Hospital Affiliated to Jianghan University School of Medicine from March 2019 to July 2022. Boruta algorithm and multivariable logistic regression analysis were used to identify independent factors associated with bleeding transformation. A nomogram was built based on these factors and internally verified using the bootstrap resampling method.

Results: Our analysis showed that the independent factors affecting HT were Hyperdense middle cerebral artery sign (HMCAS), pre-thrombolytic glucose, pre-thrombolytic neutrophil count and construct a nomogram based on these predictors. The area under the ROC curve (AUC) of the line graph was 0.885 (95%CI = 0.816 ~ 0.953), and the calibration curve showed that the probability predicted by the line graph was in good agreement with the actual observed values. The ROC curve and decision curve analysis (DCA), which assesses clinical usefulness, showed that the nomogram provided greater net benefit than the three individual predictors.

Conclusions: In this study, a static and dynamic online nomogram with good differentiation, calibration and accuracy was constructed to help identify high-risk patients before thrombolysis, help physicians make decisions and improve patient outcomes.