TY - JOUR
T1 - Predictive modeling of long-term improvement in occlusion outcomes following Woven EndoBridge treatment of cerebral aneurysms
T2 - A machine learning approach
AU - for the WorldWideWEB Investigators
AU - Karandish, Alireza
AU - Essibayi, Muhammed Amir
AU - Jabal, Mohamed Sobhi
AU - Salim, Hamza Adel
AU - Musmar, Basel
AU - Adeeb, Nimer
AU - Dibas, Mahmoud
AU - Simonato, Davide
AU - Li, Yan Lin
AU - Grist, James
AU - Zaccagna, Fulvio
AU - Algin, Oktay
AU - Ghozy, Sherief
AU - Lay, Sovann V.
AU - Guenego, Adrien
AU - Renieri, Leonardo
AU - Carnevale, Joseph
AU - Saliou, Guillaume
AU - Mastorakos, Panagiotis
AU - El Naamani, Kareem
AU - Shotar, Eimad
AU - Möhlenbruch, Markus
AU - Kral, Michael
AU - Chung, Charlotte
AU - Salem, Mohamed M.
AU - Lylyk, Ivan
AU - Foreman, Paul M.
AU - Shaikh, Hamza
AU - Župančić, Vedran
AU - Hafeez, Muhammad U.
AU - Catapano, Joshua
AU - Waqas, Muhammad
AU - Kazanci, Atilla
AU - Ayberk, Giyas
AU - Rabinov, James D.
AU - Maingard, Julian
AU - Schirmer, Clemens M.
AU - Piano, Mariangela
AU - Kühn, Anna L.
AU - Michelozzi, Caterina
AU - Starke, Robert M.
AU - Hassan, Ameer
AU - Ogilvie, Mark
AU - Nguyen, Anh
AU - Jones, Jesse
AU - Brinjikji, Waleed
AU - Nawka, Marie T.
AU - Psychogios, Marios
AU - Siddiqui, Adnan
AU - Levy, Elad I.
N1 - Publisher Copyright:
© The Author(s) 2025
PY - 2025
Y1 - 2025
N2 - Background: The Woven EndoBridge (WEB) device represents an innovative solution for cerebral aneurysm occlusion, particularly for challenging wide-neck bifurcation aneurysms. However, factors affecting sustained occlusion remain poorly understood. We utilized machine learning to attempt to identify predictors of favorable long-term outcomes following WEB treatment. Methods: In this multicenter retrospective study, we collected patient demographics, aneurysm characteristics, procedural details, and clinical outcomes. The primary endpoint was improvement in occlusion status, defined as maintained Raymond-Roy Occlusion Classification (RROC) grade 1, or improvement from grade 2 to 1, or from grade 3 to either 2 or 1 on final angiographic follow up. The dataset was split into training (75%) and validation (25%) sets. The CatBoost algorithm was selected based on performance metrics, with Shapley Additive exPlanations (SHAP) values calculated to determine feature importance. Furthermore, a multivariable binomial logistic regression model was performed to validate machine learning findings. Results: Among 720 aneurysms from 36 hospitals, 84% showed improvement in occlusion at follow up. Both machine learning and multivariable logistic regression identified aneurysm height as the most consistent correlate of nonimprovement (odds ratio (OR) 0.90 per mm, p = 0.022). In the CatBoost model, the highest-ranking features by SHAP included aneurysm height, patient age, treatment acuity, ACom location, WEB-SLS device, bifurcation anatomy, aneurysm multiplicity, baseline modified Rankin Scale, access route, and partial thrombosis. Conclusions: Machine-learning and regression analyses identified consistent predictors of occlusion improvement after WEB treatment, with aneurysm height most strongly linked to nonimprovement. These insights may guide patient selection and follow up. Findings require cautious interpretation and external validation in larger cohorts.
AB - Background: The Woven EndoBridge (WEB) device represents an innovative solution for cerebral aneurysm occlusion, particularly for challenging wide-neck bifurcation aneurysms. However, factors affecting sustained occlusion remain poorly understood. We utilized machine learning to attempt to identify predictors of favorable long-term outcomes following WEB treatment. Methods: In this multicenter retrospective study, we collected patient demographics, aneurysm characteristics, procedural details, and clinical outcomes. The primary endpoint was improvement in occlusion status, defined as maintained Raymond-Roy Occlusion Classification (RROC) grade 1, or improvement from grade 2 to 1, or from grade 3 to either 2 or 1 on final angiographic follow up. The dataset was split into training (75%) and validation (25%) sets. The CatBoost algorithm was selected based on performance metrics, with Shapley Additive exPlanations (SHAP) values calculated to determine feature importance. Furthermore, a multivariable binomial logistic regression model was performed to validate machine learning findings. Results: Among 720 aneurysms from 36 hospitals, 84% showed improvement in occlusion at follow up. Both machine learning and multivariable logistic regression identified aneurysm height as the most consistent correlate of nonimprovement (odds ratio (OR) 0.90 per mm, p = 0.022). In the CatBoost model, the highest-ranking features by SHAP included aneurysm height, patient age, treatment acuity, ACom location, WEB-SLS device, bifurcation anatomy, aneurysm multiplicity, baseline modified Rankin Scale, access route, and partial thrombosis. Conclusions: Machine-learning and regression analyses identified consistent predictors of occlusion improvement after WEB treatment, with aneurysm height most strongly linked to nonimprovement. These insights may guide patient selection and follow up. Findings require cautious interpretation and external validation in larger cohorts.
KW - Woven EndoBridge (WEB)
KW - endovascular
KW - intracranial aneurysm
KW - machine learning
UR - https://www.scopus.com/pages/publications/105020801415
U2 - 10.1177/15910199251391915
DO - 10.1177/15910199251391915
M3 - Article
C2 - 41182964
AN - SCOPUS:105020801415
SN - 1591-0199
JO - Interventional Neuroradiology
JF - Interventional Neuroradiology
M1 - 15910199251391915
ER -