Related Experiment Video
Updated: May 24, 2026
10:41
Analysis of Cerebral Vasospasm in a Murine Model of Subarachnoid Hemorrhage with High Frequency Transcranial Duplex Ultrasound
Published on: June 3, 2021
OPTIMA-DAW: Improving Cerebral Vasospasm Detection After Aneurysmal Subarachnoid Haemorrhage Using Machine Learning
Claire Charamel1,2, Arthur Le Gall2, Marc Cuggia1
1Univ Rennes, CHU Rennes, INSERM, LTSI-UMR 1099, Rennes, France.
Studies in Health Technology and Informatics
|May 23, 2026
Summary
Machine learning models can predict cerebral vasospasm after aneurysmal subarachnoid hemorrhage (aSAH). XGBoost demonstrated strong performance in identifying this serious complication using clinical data.
Area of Science:
- Neurology
- Medical Informatics
- Artificial Intelligence
Background:
- Cerebral vasospasm is a significant risk following aneurysmal subarachnoid hemorrhage (aSAH).
- Early detection and prediction of cerebral vasospasm are crucial for patient management.
- Standardized clinical data formats facilitate large-scale analysis.
Purpose of the Study:
- To develop and evaluate machine learning models for predicting cerebral vasospasm post-aSAH.
- To assess the performance of different machine learning algorithms using real-world clinical data.
Main Methods:
- Trained machine learning models on a dataset of 168 patients with aneurysmal subarachnoid hemorrhage.
- Utilized 225 computed tomography angiography (CTA) timepoints for model training.
- Employed the Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) for standardized clinical data.
Main Results:
- The XGBoost model achieved the highest predictive performance.
- The area under the receiver operating characteristic curve (AUROC) for XGBoost was 0.79 (95% CI 0.65-0.91).
Conclusions:
- Machine learning, particularly XGBoost, shows promise in predicting cerebral vasospasm after aSAH.
- Standardized clinical data and machine learning can aid in identifying patients at risk for this complication.
