Related Experiment Video
Updated: Jul 12, 2026
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
Published on: September 25, 2019
A classification model for concurrent posterior circulation infarction in vertebrobasilar dolichoectasia using
Yilan Li1, Qiang Zhang2, Xujie Wang3
1Department of Radiology, Tianjin Fourth Central Hospital, Tianjin, China.
Insights
Researchers developed a machine learning model to identify posterior circulation infarction (PCI) in patients with vertebrobasilar dolichoectasia (VBD). This tool aids in classifying concurrent PCI, improving patient management.
Area of Science:
- Neurology
- Medical Imaging
- Machine Learning
Background:
- Vertebrobasilar dolichoectasia (VBD) is a cerebrovascular condition often associated with posterior circulation infarction (PCI).
- Lack of tools to classify concurrent PCI in VBD patients necessitates novel approaches.
- This study focuses on developing a machine learning model for this classification task.
Purpose of the Study:
- To develop and validate a machine learning-based classification model.
- To identify concurrent posterior circulation infarction (PCI) in patients with vertebrobasilar dolichoectasia (VBD).
- To provide a tool for clinical decision-making in VBD patients.
Main Methods:
- Retrospective data collection from 380 participants.
- Random forest and XGBoost models were trained and validated.
- Boruta feature selection and SHAP analysis were employed to identify key predictors.
Main Results:
- The XGBoost model achieved an AUC of 0.884, demonstrating strong performance.
- Key predictors for concurrent PCI included basilar artery diameter (BAD) and midline distance (BAMD).
- The model integrated clinical and imaging variables for classification.
Conclusions:
- A machine learning model was developed and internally validated to classify concurrent PCI in VBD.
- External validation and prospective studies are crucial for clinical implementation.
- A web calculator is available to aid in identifying individuals with concurrent PCI.
Background:
Vertebrobasilar dolichoectasia (VBD) is a cerebrovascular arteriopathy, and posterior circulation infarction (PCI) is frequently observed in this population. Currently, there are no widely available tools to classify the concurrent presence of PCI in patients with VBD. This study aimed to develop a machine learning-based classification model to identify concurrent PCI in this population using cross-sectional data.
Methods:
Clinical data were retrospectively collected from Tianjin Fourth Central Hospital. The cohort was randomly divided into a 70% training set and a 30% validation set. Eight candidate models were trained after Boruta feature selection. Model discrimination, calibration, and clinical utility were assessed using the receiver operating characteristic curve, calibration curve, and decision curve analysis. The best performing model was interpreted via SHAP-based variable importance and contribution analysis, and web calculator was subsequently deployed.
Results:
Our study included 380 participants, with median age 67 years, 262 (68.95%) male and 118 (31.05%) female, included 154 (40.53%) had PCI. Basilar artery diameter (BAD), basilar artery length (BAL), basilar artery midline distance (BAMD), systolic blood pressure, platelet, triglyceride, and uric acid were identified as factors associated with concurrent PCI. The Random Forest model (AUC: 0.846, 95% CI: 0.789-0.895) and the XGBoost model (AUC: 0.884, 95% CI: 0.842-0.925) exhibited the best discrimination, calibration, and clinical utility. SHAP summary of both optimal models indicated that BAD and BAMD were the dominant contributors to the classification of concurrent PCI.
Conclusion:
We developed and internally validated a machine learning model that integrates clinical and imaging variables to classify concurrent PCI status in VBD. As this is a cross-sectional classification model, external validation and prospective studies are strictly required before clinical implementation. A freely accessible web calculator is provided as a preliminary tool to assist in identifying individuals with concurrent PCI and supporting clinical decision-making.