Risk Prediction Study Of Spontaneous Hemorrhagic Transformation After Acute Ischemic Stroke

Objective:Most of the current acute ischemic stroke prediction studies focus on post-reperfusion therapy,and there are fewer studies on spontaneous hemorrhagic transformation,while the reperfusion rate of our patients is low.To establish a quantitative and visual prediction model for spontaneous hemorrhagic transformation after acute ischemic stroke,and to validate the efficacy.Methods:A total of 240 patients with acute ischemic stroke who were admitted to the Department of Neurology of the First Affiliated Hospital of Hainan Medical College from January 2019 to June 2021 were selected,and the patients’ general data,serological tests and imaging findings were collected and randomly grouped into a modeling group(175 cases)and a validation group(65 cases),and the study subjects were divided into non-hemorrhagic transformation and hemorrhagic transformation groups according to the imaging findings.The R 4.1.1 software package and rms program package were used to build the column line graph model,while Bootstrap method was applied to repeat sampling 1000 times for internal and external validation,and H-L goodness-of-fit test,clinical decision curve and ROC curve were used to assess the calibration and discrimination of the column line graph model,respectively.Results:1.A total of 240 acute ischemic stroke patients were included in this study,and hemorrhagic transformation occurred in 60 cases(25.0%).In the modeling group,the results of multifactorial logistics regression showed that a previous history of AF could be considered(OR=8.134,95% CI: 1.712-46.660,P =0.011),higher NIHSS score(OR=1.263,95% CI: 1.145-1.430,P <0.001),HB(OR= 1.052,95% CI:1.009-1.107,P =0.032),elevated HDL(OR=17.287,95% CI: 2.453-165.645,P =0.007),and larger infarct size(OR=24.819,95% CI: 6.200-138.744,P <0.001)were the most important factors in acute ischemic risk factors for spontaneous hemorrhage conversion after stroke.2.To establish a predictive model of risk of spontaneous hemorrhage conversion after acute ischemic stroke column line graph model.The values of the H-L goodness-of-fit test were 5.61 and 0.74 for the modeling and validation groups,respectively,with corresponding P values of 0.13 and 0.69,indicating that the developed column line graph model had good predictive accuracy;the area under the ROC curve for the modeling and validation groups was 0.963 [95% CI(0.926-1.000)]and 0.977 [95% CI(0.950-1.000)]],and the results suggest that the model has good discrimination.Decision curve analysis showed that the use of the column line graph model developed in this study had a higher net benefit than the strategy of no intervention for all patients or intervention for all patients at thresholds greater than5% in the in-progress group.Conclusions:1.Previous history of atrial fibrillation,large NIHSS score at onset,elevated HB,decreased HDL-C and large infarct size are independent influencing factors for spontaneous hemorrhagic transformation after acute ischemic stroke.2.The visualized columnar line graph model can effectively predict the risk of spontaneous hemorrhage conversion after acute ischemic stroke.