Intracranial Aneurysm

ImportanceUnruptured intracranial aneurysms (UIAs) affect 3.2% of the general population, and approximately 85% of subarachnoid hemorrhages result from their rupture. Despite their classification as low risk by prediction tools such as PHASES (population, hypertension, age, size of aneurysm, earlier subarachnoid hemorrhage from another aneurysm, and site of aneurysm) and the Unruptured Cerebral Aneurysm Study (UCAS), UIAs less than 10 mm are susceptible to rupture.ObjectiveTo develop and externally validate a machine-learning model (MLM) predicting rupture risk of UIAs.Design, setting, and participantsThis retrospective multicenter prognostic study analyzed UIAs from 4 institutions across 3 continents from January 2003 to November 2022. Each UIA was characterized by 29 clinical and 18 morphological variables. For model development, patients with UIAs were drawn from a large institutional cohort. Statistical analysis was performed from April 2024 to March 2025.ExposureAn MLM based on the Light Gradient Boosting Machine algorithm was trained, and performance was assessed for validation externally.Main outcomes and measuresThe primary outcome was aneurysm rupture within 2 years after risk evaluation. Model performance was assessed using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), positive likelihood ratio (PLR), negative likelihood ratio (NLR), and the area under the receiver operating characteristic curve (AUROC) with 95% CIs.ResultsDrawing from 11 579 UIAs from multiple institutions of 8846 patients, there were 2750 patients with 3312 UIAs in the development cohort (median [IQR] age, 65.3 [54.9-73.6] years; 1856 females [67.5%]) and 1153 patients with 1501 UIAs in the external cohort (median [IQR] age, 63.6 [53.9-70.9] years; 828 females [71.8%]), for whom the MLM demonstrated a robust performance in risk estimation. In the development cohort, 71 UIAs (2.1%) ruptured during 8.5 years' median follow-up (IQR, 5.1-11.6 years), and in the external cohort, 48 UIAs (3.2%) ruptured during a median (IQR) follow-up of 5.4 (3.7-8.7) years. With a threshold of 0.52 for the MLM, performance in the development cohort for sensitivity was 0.78 (95% CI, 0.67-0.86); specificity, 0.82 (95% CI, 0.80-0.83); PPV, 0.09 (95% CI, 0.07-0.11); NPV, 0.99 (95% CI, 0.99-1.00); PLR, 4.23 (95% CI, 3.66-4.89); NLR, 0.28 (95% CI, 0.18-0.42); and AUROC, 0.88 (95% CI, 0.85-0.92) and in the external cohort, sensitivity was 0.90 (95% CI, 0.78-0.95); specificity, 0.70 (95% CI, 0.67-0.72); PPV, 0.09 (95% CI, 0.07-0.12); NPV, 1.00 (95% CI, 0.99-1.00); PLR, 2.94 (95% CI, 2.60-3.33); NLR, 0.15 (95% CI, 0.07-0.34); and AUROC, 0.90 (95% CI, 0.85-0.94). The MLM performed consistently in UIAs less than 10 mm (AUROC, 0.88 [95% CI, 0.82-0.94]), suggesting potential complementary value to PHASES and the UCAS.Conclusions and relevanceIn this prognostic study, the MLM consistently identified features of UIAs as significantly associated with rupture across different cohorts. These results support the MLM's potential to assist physicians and patients in UIA treatment decisions.

The Woven EndoBridge (WEB) device treats wide-necked bifurcation aneurysms, but occlusion rates vary. This study aims to identify factors associated with immediate WEB device occlusion. Data from patients treated with WEB devices across 36 sites were analyzed. Machine learning algorithms and ordinal regression models were developed to predict immediate incomplete occlusion for ruptured and unruptured aneurysms. The study included 1565 patients, with 436 ruptured and 1129 unruptured aneurysms. Immediate complete occlusion was achieved in 38.3% of ruptured and 32.8% of unruptured aneurysms. For ruptured aneurysms, the CatBoost classifier achieved an AUROC of 0.69. Key predictors of incomplete occlusion included pretreatment mRS, aneurysm diameter, and MCA location. Ordinal regression revealed that smoking history (OR: 1.95, p < 0.001), neck diameter (Odds Ratio [OR]: 1.50, p < 0.001), and presence of a branch from the aneurysm (OR: 2.06, p = 0.016) were associated with incomplete, while bifurcation aneurysms (OR: 0.55, p = 0.017) were associated with complete immediate occlusion. For unruptured aneurysms, the CatBoost classifier achieved an AUROC of 0.68. Significant predictors of immediate incomplete occlusion included aneurysm neck width, MCA location, and presence of daughter sac. Ordinal regression revealed that smoking history (OR: 1.29, p = 0.032), neck diameter (OR: 1.24, p < 0.001), and presence of a daughter sac (OR: 1.53, p = 0.005) were associated with incomplete, while bifurcation aneurysms (OR: 0.71, p = 0.02) and posterior circulation location (OR: 0.68, p = 0.01) were associated with complete immediate occlusion. Careful evaluation of patient demographics and specific aneurysm characteristics may help improve the outcomes of intracranial aneurysms treated with WEB device.

BackroundThe flow characteristics of bifurcation aneurysms in the posterior communicating artery (PCOM) have rarely been studied. The likelihood of a complete PCOM aneurysm occlusion after endovascular treatment is reduced with the presence of a fetal posterior communicating artery (fPCOM). As a result, anatomical variations in PCOM aneurysms represent a major challenge for the endovascular treatment. This study addresses hemodynamic variations in PCOM aneurysms of either fetal or adult type.Methods3D-DSA data of 14 patients with bifurcation aneurysms located in the PCOM junction were collected. Nine patients presented with a fPCOM and five patients an adult PCOM (aPCOM). Patient-specific 3D models containing at least one bifurcation distal the aneurysm in the anterior circulation as well as the PCOM itself were extracted using image-based blood flow simulations. Seven hemodynamic parameters were calculated for all aneurysm models to characterize the intra-aneurysmal blood flow. The PCOM outflow was artificially varied to represent both fPCOM and aPCOM conditions for each model resulting in 28 simulations.ResultsFetal‑type PCOM showed higher intra‑aneurysmal mean velocity (median 0.09 vs. 0.06 m/s), maximum velocity (0.17 vs. 0.14 m/s), averaged wall shear stress (1.67 vs. 1.27 Pa), neck inflow rate (40.9 vs. 22.4 ml/min), and inflow concentration index (0.56 vs. 0.40), with lower pulsatility index (1.73 vs. 1.89). Those differences were significant whereas mean oscillatory shear index did not differ significantly.ConclusionThe presence of anatomical variations affects the hemodynamic parameters of PCOM bifurcation aneurysms. In particular, the presence of an fPCOM has an unfavorable effect on the intra-aneurysmal flow dynamics.

The Surpass flow diverter, including Streamline and Evolve, features a unique design optimized for improved conformability, opening, and wall apposition. Its unique pore structure allows for deployment across a wide range of arterial diameters, contributing to its high occlusion rates. The current study aims to compare the efficacy and safety of the Surpass Streamline and Evolve in treating intracranial aneurysms, with a focus on location, size, and morphology. A systematic review and meta-analysis was carried out according to the PRISMA guidelines, utilizing PubMed, Web of Science, Scopus, and Embase, from inception to August 1st, 2024. Relevant data were extracted, and data synthesis was performed using STATA v.17. The analysis included 27 studies with 1,826 patients (76.7% female; ages 28-84 years) and 2,006 intracranial aneurysms (1,743 anterior, 222 posterior; 28 blister, 20 dissecting, 116 fusiform, and 1,597 saccular). The pooled complete occlusion rate at the final follow-up was 77%, with no significant differences between anterior (80%) and posterior (64%) circulation aneurysms (P = 0.15) or small (70%) and large/giant (79%) aneurysms (P = 0.36). Morphological analysis revealed that blister, dissecting, saccular, and fusiform aneurysms had 100%, 65%, 55%, and 79% complete occlusion rates, respectively (P < 0.001). Surpass Streamline had 81% complete occlusion success versus 69% for Evolve (P = 0.04). The overall adequate occlusion rate was 90%, with Streamline at 92% and Evolve at 88% (P = 0.35). Higher occlusion rates were observed in posterior aneurysms (100% vs. 92%; P < 0.001). Large/giant aneurysms had a higher rate of adequate occlusion (100% vs. 88%; P = 0.12). Morphological analysis showed that blister and dissecting aneurysms had 100% adequate occlusion, fusiform aneurysms had 75% adequate occlusion, and saccular aneurysms had 96% adequate occlusion (P = 0.04). Mortality, complications and in-stent thrombosis were significantly reduced with Evolve (P = 0.03, 0.001 and 0.000, respectively). Our study indicates the efficacy and safety of the Surpass flow diverter for treating intracranial aneurysms, offering a satisfactory occlusion rate. The surpass Evolve was associated with a lower incidence of major complications.