Yanan Lin ¹ Yan Li ² Yayin Luo ¹ Jie Han ^1*

• ¹ First Affiliated Hospital, Dalian Medical University, Dalian, China
• ² Dalian Institute of Chemical Physics, Chinese Academy of Sciences (CAS), Dalian, Liaoning Province, China

Objective: To develop and validate an explainable machine learning (ML) model predicting the risk of hemorrhagic transformation (HT) after intravenous thrombolysis.We retrospectively enrolled patients who received intravenous tissue plasminogen activator (IV-tPA) thrombolysis within 4.5 hours after symptom onset to form the original modeling cohort. HT was defined as any hemorrhage on head CT scan completed within 48 hours after IV-tPA administration. We utilized the Random Forest (RF), Multilayer Perceptron (MLP), Adaptive Boosting (AdaBoost), and Gaussian Naive Bayes (GauNB) algorithms to develop ML-HT models. The models' predictive performance was evaluated using confusion matrix (including accuracy, precision, recall, and F1 score), and discriminative analysis (area under the receiver-operatingcharacteristic curve, ROC-AUC) in the original cohort, followed by validation in an independent external cohort. The models' explainability was assessed using SHapley Additive exPlanations (SHAP) global feature plot, SHAP summary plot, and partial dependence plot.Results: A total of 1007 patients were included in the original modeling cohort, with an HT incidence of 8.94%. The RF-based ML-HT model showed metrics of 0.874 (accuracy), 0.972 (precision), 0.890 (recall), 0.929 (F1 score); with ROC-AUC of 0.7847 in the original cohort and 0.7119 in the external validation cohort.