Related Experiment Video
Updated: Aug 14, 2025
Modeling Stroke in Mice: Permanent Coagulation of the Distal Middle Cerebral Artery
Published on: July 31, 2014
Machine learning prediction of malignant middle cerebral artery infarction after mechanical thrombectomy for anterior
Haydn Hoffman1, Jacob S Wood1, John R Cote1
1Department of Neurosurgery, State University of New York Upstate Medical University, Syracuse, NY, USA.
Objective:
Prediction of malignant middle cerebral artery infarction (MMI) could identify patients for early intervention. We trained and internally validated a ML model that predicts MMI following mechanical thrombectomy (MT) for ACLVO.
Methods:
All patients who underwent MT for ACLVO between 2015 - 2021 at a single institution were reviewed. Data was divided into 80% training and 20% test sets. 10 models were evaluated on the training set. The top 3 models underwent hyperparameter tuning using grid search with nested 5-fold CV to optimize the area under the receiver operating curve (AUROC). Tuned models were evaluated on the test set and compared to logistic regression.
Results:
A total of 381 patients met the inclusion criteria. There were 50 (13.1%) patients who developed MMI. Out of the 10 ML models screened on the training set, the top 3 performing were neural network (median AUROC 0.78, IQR 0.72 - 0.83), support vector machine ([SVM] median AUROC 0.77, IQR 0.72 - 0.83), and random forest (median AUROC 0.75, IQR 0.68 - 0.81). On the test set, random forest (median AUROC 0.78, IQR 0.73 - 0.83) and neural network (median AUROC 0.78, IQR 0.73 - 0.83) were the top performing models, followed by SVM (median AUROC 0.77, IQR 0.70 - 0.83). These scores were significantly better than those for logistic regression (AUROC 0.72, IQR 0.66 - 0.78), individual risk factors, and the Malignant Brain Edema score (p < 0.001 for all).
Conclusion:
ML models predicted MMI with good discriminative ability. They outperformed standard statistical techniques and individual risk factors.
Insights
Machine learning models accurately predict malignant middle cerebral artery infarction (MMI) after mechanical thrombectomy for anterior circulation large vessel occlusion (ACLVO). These AI tools offer improved diagnostic capabilities over traditional methods.
Area of Science:
- Neurology
- Artificial Intelligence
- Medical Imaging
Background:
- Malignant middle cerebral artery infarction (MMI) is a severe complication following mechanical thrombectomy (MT) for anterior circulation large vessel occlusion (ACLVO).
- Early identification of patients at risk for MMI is crucial for timely intervention and improved outcomes.
Purpose of the Study:
- To develop and validate a machine learning (ML) model for predicting MMI in patients undergoing MT for ACLVO.
- To compare the performance of ML models against traditional statistical methods and clinical risk scores.
Main Methods:
- A retrospective review of 381 patients who underwent MT for ACLVO between 2015-2021.
- Ten ML models were trained and evaluated, with the top three undergoing hyperparameter tuning.
- Model performance was assessed using the area under the receiver operating curve (AUROC) on a held-out test set.
Main Results:
- The study identified 50 (13.1%) patients who developed MMI.
- Neural network and random forest models achieved the highest median AUROC of 0.78 on the test set.
- ML models significantly outperformed logistic regression, individual risk factors, and the Malignant Brain Edema score (p < 0.001).
Conclusions:
- Machine learning models demonstrate strong discriminative ability in predicting MMI post-MT for ACLVO.
- These AI-driven approaches offer superior predictive performance compared to conventional methods, paving the way for enhanced clinical decision-making.
