Nomogram for predicting delayed intraparenchymal hemorrhage after pipeline embolization device treatment in patients with intracranial aneurysms: a multicenter, retrospective model development and validation study

Background Delayed intraparenchymal hemorrhage (DIPH) is a severe complication after pipeline embolization device (PED) deployment for intracranial aneurysms (IAs). However, predictive models are lacking. This study aims to develop and validate a new nomogram to predict DIPH risk in IA patients. Methods This retrospective study included 959 IA patients treated with PEDs at three institutions between October 2018 and June 2024. Patients were categorized into a training cohort (n=685) and a validation cohort (n=274). Predictors were identified using the least absolute shrinkage and selection operator and multivariable regression analyses. A nomogram was developed based on these predictors. The area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA) were utilized to assess the predictive accuracy and clinical value of the nomograms. Results The incidence of DIPH was 2.3% in the training cohort. Multivariate logistic regression analysis demonstrated that age (odds ratio [OR] per 10 years, 2.063, P=0.005), maximum diameter (OR, 1.099, P=0.004), adenosine diphosphate-induced maximal platelet aggregation (OR, 0.896, P<0.001), and overlapping devices (OR, 7.226, P=0.007) were independent risk factors for DIPH. A nomogram was developed based on these four predictors. The AUCs of the nomogram in the training and validation cohorts were 0.875 (95% CI, 0.762 to 0.988) and 0.886 (95% CI, 0.757 to 1.000), respectively. The calibration curve and DCA analyses confirmed the utility and clinical applicability of the nomogram. Conclusion A simple to use nomogram for the individualized prediction of DIPH after PED treatment in patients with IAs was constructed, which may facilitate early identification of high-risk patients and the development of advanced treatment strategies.