Objective To construct an acute cerebral infarction risk nomogram prediction model to evaluate the risk of symptomatic intracranial hemorrhage in patients after percutaneous intracranial artery thrombolysis.Methods A total of 272 patients with acute cere-bral infarction who underwent percutaneous intracranial artery thrombolysis in our hospital from January 2021 to February 2024 were selected as the study participants and divided into the training set(n=190)and validation set(n=82)at a ratio of 7∶3.The training set was divided into a bleeding group(n=61)and non-bleeding group(n=129)based on the presence or absence of symptomatic intracranial hemorrhage during the postoperative period,and the general data of the patients in the two groups were compared.Binary logistic regres-sion was used to analyze the factors influencing symptomatic intracranial hemorrhage.The R Language 4.3.3 toolkit was used to construct a predictive model for the risk of symptomatic intracranial hemorrhage.The predictive efficacy,calibration,and clinical applicability of the model were assessed using subject operating characteristic(ROC),calibration,and decision curves.Results Atrial fibrillation,fasting blood glucose level,and preoperative NIHSS scores were identified as factors influencing symptomatic intracranial hemorrhage after percutaneous intracranial artery thrombolysis in patients with acute cerebral infarction.The AUC of the training and validation sets for predicting symptomatic intracranial hemorrhage was 0.986(95％CI:0.974-0.999)and 0.986(95％CI:0.967-1.000),with a sensitivity of 95.08％and 99.98％,and a specificity of 95.35％and 92.98％.Conclusion The risk nomogram prediction model constructed in this study provides an effective tool of clinical value for assessing the risk of symptomatic intracranial hemorrhage after percutaneous intracra-nial artery thrombolysis in patients with acute cerebral infarction.

Objective To construct an acute cerebral infarction risk nomogram prediction model to evaluate the risk of symptomatic intracranial hemorrhage in patients after percutaneous intracranial artery thrombolysis.Methods A total of 272 patients with acute cere-bral infarction who underwent percutaneous intracranial artery thrombolysis in our hospital from January 2021 to February 2024 were selected as the study participants and divided into the training set(n=190)and validation set(n=82)at a ratio of 7∶3.The training set was divided into a bleeding group(n=61)and non-bleeding group(n=129)based on the presence or absence of symptomatic intracranial hemorrhage during the postoperative period,and the general data of the patients in the two groups were compared.Binary logistic regres-sion was used to analyze the factors influencing symptomatic intracranial hemorrhage.The R Language 4.3.3 toolkit was used to construct a predictive model for the risk of symptomatic intracranial hemorrhage.The predictive efficacy,calibration,and clinical applicability of the model were assessed using subject operating characteristic(ROC),calibration,and decision curves.Results Atrial fibrillation,fasting blood glucose level,and preoperative NIHSS scores were identified as factors influencing symptomatic intracranial hemorrhage after percutaneous intracranial artery thrombolysis in patients with acute cerebral infarction.The AUC of the training and validation sets for predicting symptomatic intracranial hemorrhage was 0.986(95％CI:0.974-0.999)and 0.986(95％CI:0.967-1.000),with a sensitivity of 95.08％and 99.98％,and a specificity of 95.35％and 92.98％.Conclusion The risk nomogram prediction model constructed in this study provides an effective tool of clinical value for assessing the risk of symptomatic intracranial hemorrhage after percutaneous intracra-nial artery thrombolysis in patients with acute cerebral infarction.