Using clinical and radiographic variables to predict intracranial aneurysm rupture status with machine learning.
Among the models, RF achieved the highest accuracy (85%) with balanced precision and recall. Across models 3D geometric features drove model performance, highlighting the importance of these features in predicting rupture status.
Authors
- Charles Joseph Prestigiacomo (ORCID: https://orcid.org/0000-0002-5979-2378)
- Anca Ralescu (ORCID: https://orcid.org/0000-0002-7564-3540)
- Samer S. Hoz (ORCID: https://orcid.org/0000-0003-4584-5931)
- Pradyumna Elavarthi (ORCID: https://orcid.org/0000-0003-3957-2420)
- Seth Street (ORCID: https://orcid.org/0000-0003-0301-0426)
- Mark D. Johnson (ORCID: https://orcid.org/0000-0001-6469-3959)
Institutions
- University of Cincinnati (US)
Publication Details
- Journal
- PubMed
- Published
- 2025-01-01
- DOI
- https://doi.org/10.25259/sni_498_2025
- Primary Topic
- Intracranial Aneurysms: Treatment and Complications
- Type
- article
- Field-Weighted Citation Impact
- 0.00