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

BackgroundThe 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.MethodsIn 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.ResultsAmong 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.ConclusionsMachine-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.

Authors

Institutions

Publication Details

Journal
Interventional Neuroradiology
Published
2025-11-03
DOI
https://doi.org/10.1177/15910199251391915
Citations
1
Primary Topic
Intracranial Aneurysms: Treatment and Complications
Type
article
Field-Weighted Citation Impact
1.39
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

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

Sunil A. Sheth, Joshua S. Catapano, Atilla Kazancı, Eytan Raz et al.
1 citations
Interventional Neuroradiology
Intracranial Aneurysms: Treatment and Complications
1.39
article

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

Sunil A. Sheth, Joshua S. Catapano, Atilla Kazancı, Eytan Raz, Thien J Huynh, Maurizio Fuschi, Hamza A. Shaikh, Pedro Nicolas Lylyk, Oktay Algın, Davide Simonato, Benjamin Pulli, Vedran Župančić, Muhammad Ubaid Hafeez, Neil Haranhalli, Guillaume Saliou, Mohamed Sobhi Jabal, Mark Ogilvie, Christoph J. Griessenauer, Hamza Adel Salim, Sovann V. Lay, Elad I. Levy, Guglielmo Pero, Charlotte Y. Chung, Pietro Panni, James D. Rabinov, Stavropoula I. Tjoumakaris, Nimer Adeeb, Juan Carlos Martínez-Gutiérrez, David Altschul, Christopher J. Stapleton, Rabih G. Tawk, Paul M. Foreman, Adnan H. Siddiqui, Muhammed Amir Essibayi, Boris Lubicz, Srikanth Boddu, Jesse George Atherton Jones, Mahmoud Dibas, Clemens Maria Schirmer, Fulvio Zaccagna, Iván Lylyk, Anna Luisa Kühn, Adam Andrew Dmytriw, Mohamed M Salem, Sherief A. Ghozy, Waleed Brinjikji, Peter Kan, Anh Nguyên, Diana Slawski, Christian Ulfert, Felipe C Albuquerque, Nicola Limbucci, Joseph A. Carnevale, Caterina Michelozzi, Marie Teresa Nawka, Robert William Regenhardt, Pascal M. Jabbour, Frédéric Clarençon, Vladimir Kalousek, Panagiotis Mastorakos, Yan-Lin Li, Gıyas Ayberk, James T. Grist, Julian Maingard, Michael Kral, Ameer E Hassan, Hugo Cuellar, Hamed Asadi, Jared Knopman, Adrien Guenego, Jan‐Karl Burkhardt, Mariangela Piano, Basel Musmar, Eimad Shotar, Aman B. Patel, Muhammad Waqas, Andrew F. Ducruet, Markus Möhlenbruch, Leonardo Renieri, Ajit S. Puri, Bryan Pukenas, Robert M. Starke, Marios Psychogios, Alireza Karandish
article en
1 citations

Abstract

BackgroundThe 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.MethodsIn 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.ResultsAmong 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.ConclusionsMachine-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.

Interventional Neuroradiology
Louisiana State University (US), Brigham and Women's Hospital (US), Geisinger Medical Center (US), St. Michael's Hospital (CA), Albert Einstein College of Medicine (US), UMass Memorial Health Care (US), Barrow Neurological Institute (US), Montefiore Medical Center (US), NewYork–Presbyterian Hospital (US), The University of Texas MD Anderson Cancer Center (US), Harvard University (US), Johns Hopkins University (US), University of Miami (US), Orlando Health (US), Ankara University (TR), Universität Hamburg (DE), Cornell University (US), Heidelberg University (DE), Louisiana State University in Shreveport (US), Thomas Jefferson University Hospital (US), New York Hospital Queens (US), University Hospital Heidelberg (DE), Centre Hospitalier Universitaire Vaudois (CH), WinnMed (US), University Hospital of Basel (CH), Johns Hopkins Bayview Medical Center (US), Centre Hospitalier Universitaire de Toulouse (FR), University of Alabama at Birmingham (US), Sorbonne Université (FR), NYU Langone Health (US), Massachusetts General Hospital (US), Azienda Socio Sanitaria Territoriale Grande Ospedale Metropolitano Niguarda (IT), Presbyterian Hospital (US), Mercy University Hospital (IE), Christian Doppler Klinik (AT), Baylor School (US), University Medical Center Hamburg-Eppendorf (DE), Azienda Ospedaliero-Universitaria Careggi (IT), Pitié-Salpêtrière Hospital (FR), Mayo Clinic in Arizona (US), Valley Baptist Medical Center (US), IRCCS Ospedale San Raffaele (IT), University of Pittsburgh Medical Center (US), Hôpital Universitaire Dupuytren (FR), Sisters of Mercy of the Americas (US), Mayo Clinic in Florida (US), Oxford University Hospitals NHS Trust (GB), Ankara Yıldırım Beyazıt University (TR), Memorial Hospital (US), Geisinger Neuroscience Institute (US), Austin Health (AU), University at Buffalo, State University of New York (US), University of Pennsylvania (US), The University of Texas Health Science Center at Houston (US), Stanford University (US)
Openalex Percentile: Top 14%
Intracranial Aneurysms: Treatment and Complications
1.39
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.