Files and links (1)
Accepted (AM)Open Access (License Unspecified), Open
Journal article
Prediction of bleb formation in intracranial aneurysms using machine learning models based on aneurysm hemodynamics, geometry, location, and patient population
Journal of neurointerventional surgery, v 14(10), pp 1002-1007
01 Oct 2022
PMID: 34686573
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
Bleb presence in intracranial aneurysms (IAs) is a known indication of instability and vulnerability.
To develop and evaluate predictive models of bleb development in IAs based on hemodynamics, geometry, anatomical location, and patient population.
Cross-sectional data (one time point) of 2395 IAs were used for training bleb formation models using machine learning (random forest, support vector machine, logistic regression, k-nearest neighbor, and bagging). Aneurysm hemodynamics and geometry were characterized using image-based computational fluid dynamics. A separate dataset with 266 aneurysms was used for model evaluation. Model performance was quantified by the area under the receiving operating characteristic curve (AUC), true positive rate (TPR), false positive rate (FPR), precision, and balanced accuracy.
The final model retained 18 variables, including hemodynamic, geometrical, location, multiplicity, and morphology parameters, and patient population. Generally, strong and concentrated inflow jets, high speed, complex and unstable flow patterns, and concentrated, oscillatory, and heterogeneous wall shear stress patterns together with larger, more elongated, and more distorted shapes were associated with bleb formation. The best performance on the validation set was achieved by the random forest model (AUC=0.82, TPR=91%, FPR=36%, misclassification error=27%).
Based on the premise that aneurysm characteristics prior to bleb formation resemble those derived from vascular reconstructions with their blebs virtually removed, machine learning models can identify aneurysms prone to bleb development with good accuracy. Pending further validation with longitudinal data, these models may prove valuable for assessing the propensity of IAs to progress to vulnerable states and potentially rupturing.
Metrics
Details
- Title
- Prediction of bleb formation in intracranial aneurysms using machine learning models based on aneurysm hemodynamics, geometry, location, and patient population
- Creators
- Seyedeh Fatemeh Salimi Ashkezari - George Mason UniversityFernando Mut - George Mason UniversityMartin Slawski - George Mason UniversityBoyle Cheng - Allegheny General HospitalAlexander K Yu - Allegheny General HospitalTim G White - Donald & Barbara Zucker School of Medicine at Hofstra/NorthwellHenry H Woo - Donald & Barbara Zucker School of Medicine at Hofstra/NorthwellMatthew J Koch - University of Illinois at ChicagoSepideh Amin-Hanjani - University of Illinois at ChicagoFady T Charbel - University of Illinois at ChicagoBehnam Rezai Jahromi - University of HelsinkiMika Niemelä - Töölö HospitalTimo Koivisto - Kuopio University HospitalJuhana Frosen - Tampere UniversityYasutaka Tobe - University of PittsburghSpandan Maiti - University of PittsburghAnne M Robertson - University of PittsburghJuan R Cebral - George Mason University
- Publication Details
- Journal of neurointerventional surgery, v 14(10), pp 1002-1007
- Publisher
- British Medical Journal (BMJ)
- Grant note
- R01 NS097457 / NINDS NIH HHS
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Surgery; Neurosurgery
- Web of Science ID
- WOS:000725061800001
- Scopus ID
- 2-s2.0-85138446605
- Other Identifier
- 991021930316504721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Neuroimaging
- Surgery