Article Text
PDF
Abstract
Background Cerebral arteriovenous malformation (AVM) is a cerebrovascular disorder posing a risk for intracranial hemorrhage. However, there are few reliable quantitative indices to predict hemorrhage risk accurately. This study aimed to identify potential biomarkers for hemorrhage risk by quantitatively analyzing the hemodynamic and morphological features within the AVM nidus.
Methods This study included three datasets comprising consecutive patients with untreated AVMs between January 2008 to December 2023. Training and test datasets were used to train and evaluate the model. An independent validation dataset of patients receiving conservative treatment was used to evaluate the model performance in predicting subsequent hemorrhage during follow-up. Hemodynamic and morphological features were quantitatively extracted based on digital subtraction angiography (DSA). Individual models using various machine learning algorithms and an ensemble model were constructed on the training dataset. Model performance was assessed using the confusion matrix-related metrics.
Results This study included 844 patients with AVMs, distributed across the training (n=597), test (n=149), and validation (n=98) datasets. Five hemodynamic and 14 morphological features were quantitatively extracted for each patient. The ensemble model, constructed based on five individual machine-learning models, achieved an area under the curve of 0.880 (0.824–0.937) on the test dataset and 0.864 (0.769–0.959) on the independent validation dataset.
Conclusion Quantitative hemodynamic and morphological features extracted from DSA data serve as potential indicators for assessing the rupture risk of AVM. The ensemble model effectively integrated multidimensional features, demonstrating favorable performance in predicting subsequent rupture of AVM.
- Angiography
- Arteriovenous Malformation
- Vascular Malformation
- Intervention
- Hemorrhage
Data availability statement
Data are available upon reasonable request. The data that support the findings of this study are available from the corresponding author on reasonable request.
Statistics from Altmetric.com
Data availability statement
Data are available upon reasonable request. The data that support the findings of this study are available from the corresponding author on reasonable request.
Footnotes
Contributors All authors made substantial contributions to the conception and design of the study. Material preparation, data collection, and analysis were performed by LL and HZ. Formal analysis and investigation were performed by SL, XF and CM. YC, LZ, and YS performed manuscript review and editing. CJ and YZ performed supervision. HZ and JZ wrote the first draft of the manuscript, and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript. CJ is the guarantor for this study.
Funding The authors have not declared a specific grant for this research from any funding agency in the public, commercial or not-for-profit sectors.
Competing interests None declared.
Provenance and peer review Not commissioned; externally peer reviewed.
Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.