Related Experiment Video
Updated: Jun 10, 2025
05:19
A Mouse Model for Vascular Cognitive Impairment and Dementia Based on Needle-guided Asymmetric Bilateral Common Carotid Artery Stenosis
Published on: November 22, 2024
406
Combining Computational Fluid Dynamics, Structural Analysis, and Machine Learning to Predict Cerebrovascular Events:
Panagiotis K Siogkas1, Dimitrios Pleouras1, Vasileios Pezoulas1
1Unit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina, 45110 Ioannina, Greece.
Diagnostics (Basel, Switzerland)
|October 16, 2024
Summary
Predicting strokes from carotid artery disease is now possible using a novel approach combining computational fluid dynamics, structural analysis, and machine learning. This method accurately identifies patients at high risk for cerebrovascular events.
Area of Science:
- Biomedical Engineering
- Medical Imaging
- Machine Learning
Background:
- Atherosclerotic plaques in carotid arteries can rupture, leading to cerebrovascular events like strokes.
- Accurate prediction of these events is crucial for timely clinical intervention and improved patient outcomes.
Purpose of the Study:
- To develop a predictive model for cerebrovascular events by integrating computational fluid dynamics (CFD), structural analysis, and machine learning (ML).
- To combine imaging and non-imaging data for enhanced risk assessment of carotid atherosclerosis and subsequent events.
Main Methods:
- Utilized 3D reconstruction and blood-flow simulations to extract plaque characteristics from 134 asymptomatic individuals.
- Integrated plaque data with patient-specific clinical information for risk evaluation.
- Employed Gradient Boosting Tree (GBT) classifier, addressing data imbalance to train the predictive model.
Main Results:
- The optimized GBT model demonstrated high predictive power with 88% balanced accuracy.
- Achieved a Receiver Operating Characteristic Area Under the Curve (ROC AUC) of 0.92.
- Reported sensitivity of 0.88 and specificity of 0.91, indicating robust performance.
Conclusions:
- The novel approach effectively integrates CFD, structural analysis, and ML for predicting cerebrovascular event risk.
- This predictive tool can significantly aid clinicians in risk assessment for carotid artery disease patients.
- Enhanced risk stratification has the potential to improve clinical decision-making and patient outcomes.
