Development and validation of a nomogram to predict symptomatic intracranial hemorrhage following endovascular treatment in acute ischemic stroke: A single center retrospective, observational study

Symptomatic intracranial hemorrhage (SICH) is a severe post-endovascular treatment (EVT) complication of acute ischemic stroke, leading to high morbidity, mortality, and neurological deficits. However, despite these risk factors, there is currently no clinically accepted predictive model to predict SICH risk in EVT patients. This study aimed to identify independent perioperative risk factors for SICH and to provide a new nomogram-based predictive model for large vessel occlusion patients. This study retrospectively examined 127 acute ischemic stroke patients receiving EVT from the First Affiliated Hospital of Wenzhou Medical University. Inclusion criteria included the National Institutes of Health Stroke Scale (NIHSS), Alberta Stroke Program Early CT Score (ASPECTS), and American Society of Interventional and Therapeutic Neuroradiology/Society of Interventional Radiology (ASITN/SIR) collateral scores. Using these predictors, a logistic regression model was used to generate the NIHSS/ASPECTS/ASITN (NAA) nomogram. The predictive ability was measured with the area under the receiver operating characteristic curve and calibration plots. Our data demonstrated that SICH patients had significantly higher baseline NIHSS scores (median: 22.38 vs 15.03; P < .001), ASPECTS (median: 5.89 vs 7.69; P < .001), and ASITN/SIR scores (median: 1.62 vs 2.69; P < .001). The NAA nomogram exhibited an area under the receiver operating characteristic curve value of 0.845 (95% confidence interval: 0.763-0.928), which is superior to the predictive performance. Calibration plots were robust in predicting and observing values. The NAA nomogram is a robust predictor of SICH after EVT that is more accurate than any scoring system. More external validation is needed to make it generalizable to diverse clinical settings.