Cover Image

Predictive modeling of long-term improvement in occlusion outcomes following Woven EndoBridge treatment of cerebral aneurysms: A machine learning approach

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Karandish, Alireza (Author) , Essibayi, Muhammed Amir (Author) , Jabal, Mohamed Sobhi (Author) , Salim, Hamza Adel (Author) , Musmar, Basel (Author) , Adeeb, Nimer (Author) , Dibas, Mahmoud (Author) , Simonato, Davide (Author) , Li, Yan-Lin (Author) , Grist, James (Author) , Zaccagna, Fulvio (Author) , Algin, Oktay (Author) , Ghozy, Sherief (Author) , Lay, Sovann V (Author) , Guenego, Adrien (Author) , Renieri, Leonardo (Author) , Carnevale, Joseph (Author) , Saliou, Guillaume (Author) , Mastorakos, Panagiotis (Author) , El Naamani, Kareem (Author) , Shotar, Eimad (Author) , Möhlenbruch, Markus Alfred (Author) , Kral, Michael (Author) , Chung, Charlotte (Author) , Salem, Mohamed M (Author) , Lylyk, Ivan (Author) , Foreman, Paul M (Author) , Shaikh, Hamza (Author) , Župančić, Vedran (Author) , Hafeez, Muhammad U (Author) , Catapano, Joshua (Author) , Waqas, Muhammad (Author) , Kazanci, Atilla (Author) , Ayberk, Giyas (Author) , Rabinov, James D (Author) , Maingard, Julian (Author) , Schirmer, Clemens M (Author) , Piano, Mariangela (Author) , Kühn, Anna L (Author) , Michelozzi, Caterina (Author) , Starke, Robert M (Author) , Hassan, Ameer (Author) , Ogilvie, Mark (Author) , Nguyen, Anh (Author) , Jones, Jesse (Author) , Brinjikji, Waleed (Author) , Nawka, Marie T (Author) , Psychogios, Marios (Author) , Ulfert, Christian (Author) , Pukenas, Bryan (Author) , Burkhardt, Jan-Karl (Author) , Huynh, Thien (Author) , Martinez-Gutierrez, Juan Carlos (Author) , Sheth, Sunil A (Author) , Slawski, Diana (Author) , Tawk, Rabih (Author) , Pulli, Benjamin (Author) , Lubicz, Boris (Author) , Panni, Pietro (Author) , Puri, Ajit S (Author) , Pero, Guglielmo (Author) , Raz, Eytan (Author) , Griessenauer, Christoph J (Author) , Asadi, Hamed (Author) , Siddiqui, Adnan (Author) , Levy, Elad I (Author) , Haranhalli, Neil (Author) , Ducruet, Andrew F (Author) , Albuquerque, Felipe C (Author) , Regenhardt, Robert W (Author) , Stapleton, Christopher J (Author) , Kan, Peter (Author) , Kalousek, Vladimir (Author) , Lylyk, Pedro (Author) , Boddu, Srikanth (Author) , Knopman, Jared (Author) , Tjoumakaris, Stavropoula I (Author) , Cuellar-Saenz, Hugo H (Author) , Jabbour, Pascal M (Author) , Clarençon, Frédéric (Author) , Limbucci, Nicola (Author) , Patel, Aman B (Author) , Fuschi, Maurizio (Author) , Altschul, David (Author) , Dmytriw, Adam A (Author)
Format: Article (Journal)
Language:English
Published: 3 November 2025
In: Interventional neuroradiology
Year: 2025, Pages: 1-9
ISSN:2385-2011
DOI:10.1177/15910199251391915
Online Access:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1177/15910199251391915
Verlag, lizenzpflichtig, Volltext: https://journals.sagepub.com/doi/full/10.1177/15910199251391915
Get full text
Author Notes:Alireza Karandish, Muhammed Amir Essibayi, Mohamed Sobhi Jabal, Hamza Adel Salim, Basel Musmar, Nimer Adeeb, Mahmoud Dibas, Davide Simonato, Yan-Lin Li, James Grist, Fulvio Zaccagna, Oktay Algin, Sherief Ghozy, Sovann V Lay, Adrien Guenego, Leonardo Renieri, Joseph Carnevale, Guillaume Saliou, Panagiotis Mastorakos, Kareem El Naamani, Eimad Shotar, Markus Möhlenbruch, Michael Kral, Charlotte Chung, Mohamed M Salem, Ivan Lylyk, Paul M Foreman, Hamza Shaikh, Vedran Župančić, Muhammad U Hafeez, Joshua Catapano, Muhammad Waqas, Atilla Kazanci, Giyas Ayberk, James D Rabinov, Julian Maingard, Clemens M Schirmer, Mariangela Piano, Anna L Kühn, Caterina Michelozzi, Robert M Starke, Ameer Hassan, Mark Ogilvie, Anh Nguyen, Jesse Jones, Waleed Brinjikji, Marie T Nawka, Marios Psychogios, Christian Ulfert, Bryan Pukenas, Jan-Karl Burkhardt, Thien Huynh, Juan Carlos Martinez-Gutierrez, Sunil A Sheth, Diana Slawski, Rabih Tawk, Benjamin Pulli, Boris Lubicz, Pietro Panni, Ajit S Puri, Guglielmo Pero, Eytan Raz, Christoph J Griessenauer, Hamed Asadi, Adnan Siddiqui, Elad I Levy, Neil Haranhalli, Andrew F Ducruet, Felipe C Albuquerque, Robert W Regenhardt, Christopher J Stapleton, Peter Kan, Vladimir Kalousek, Pedro Lylyk, Srikanth Boddu, Jared Knopman, Stavropoula I Tjoumakaris, Hugo H Cuellar-Saenz, Pascal M Jabbour, Frédéric Clarençon, Nicola Limbucci, Aman B Patel, Maurizio Fuschi, David Altschul, Adam A Dmytriw
Description
Summary: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.
Item Description:Gesehen am 28.05.2026
Online veröffentlicht: 3. November 2025
Physical Description:Online Resource
ISSN:2385-2011
DOI:10.1177/15910199251391915

Similar Items