Using clinical and radiographic variables to predict intracranial aneurysm rupture status with machine learning
Surgical Neurology International · 18.07.2025 · 16 · 298
DOI: 10.25259/sni_498_2025 ↗Kurz gefasst
Fachartikel in der Zeitschrift Surgical Neurology International, online erschienen am 18.07.2025. Verfasst von Mark D Johnson und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurosurgery, University of Cincinnati, Cincinnati, Ohio, United States. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
With excitement in the medical community around artificial intelligence, machine learning (ML) techniques have been applied to correlate clinical and radiographic variables with intracranial aneurysm (IA) rupture status. In this study, we applied various ML techniques, including random forest (RF), XGBoost (XGB), support vector machines (SVM), and multi-layer perceptron (MLP), to predict IA rupture status.
Methods
The dataset consisted of 178 IAs each with 53 clinical and radiographic features for analysis. We removed features with high correlation (>0.8) with respect to the target variable to reduce redundancy. We applied grid search to fine-tune the hyperparameters for each model. Each model was evaluated across five iterations of 5-fold cross-validation. Overall performance metrics (accuracy, precision, recall, and F1-score) were extracted. The Wilcoxon signed-rank test was used to compare the area under the curve (AUC) scores between models.
Results
The most common locations were internal carotid artery (42), anterior communicating artery (41), middle cerebral artery (32), and posterior communicating artery (25). The AUC for the RF (0.85) and XGB (0.76) models were significantly higher than those for the SVM (0.69) and MLP (0.65) models ( P < 0.05). There was no statistical difference in accuracy between RF and XBG models ( P = 0.144). Fractal dimension ranked as the most important feature for model performance across all models. Three-dimensional (3D) shape features made up 8 of the 15 most important features driving model performance.
Conclusion
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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Neurosurgery, University of Cincinnati, Cincinnati, Ohio, United States.
- Department of Computer Science, University of Cincinnati, Cincinnati, Ohio, United States.
Zitieren
APA
Johnson, M. D., Elavarthi, P., Street, S., Hoz, S. S., Ralescu, A. L., & Prestigiacomo, C. J. (2025). Using clinical and radiographic variables to predict intracranial aneurysm rupture status with machine learning. Surgical Neurology International, 16, 298. https://doi.org/10.25259/sni_498_2025
Vancouver
Johnson MD, Elavarthi P, Street S, Hoz SS, Ralescu AL, Prestigiacomo CJ. Using clinical and radiographic variables to predict intracranial aneurysm rupture status with machine learning. Surgical Neurology International. 2025;16:298. doi:10.25259/sni_498_2025
BibTeX
@article{Johnson2025,
author = {Johnson, Mark D and Elavarthi, Pradyumna and Street, Seth and Hoz, Samer S and Ralescu, Anca L and Prestigiacomo, Charles J},
title = {Using clinical and radiographic variables to predict intracranial aneurysm rupture status with machine learning},
journal = {Surgical Neurology International},
year = {2025},
volume = {16},
pages = {298},
doi = {10.25259/sni_498_2025}
}
EUVIMED