Rupture-Related Features of Cerebral Arteriovenous Malformations and Their Utility in Predicting Hemorrhage

Yupeng Zhang; Haoyu Zhu; Tingliang Cao; Longhui Zhang; Yuzhou Chang; Shikai Liang; Chao Ma; Fei Liang; Yuqi Song; Jiarui Zhang; Changxuan Li; Chuhan Jiang

doi:10.1161/STROKEAHA.123.045456

Rupture-Related Features of Cerebral Arteriovenous Malformations and Their Utility in Predicting Hemorrhage

Stroke. 2024 May;55(5):1339-1348. doi: 10.1161/STROKEAHA.123.045456. Epub 2024 Mar 21.

Authors

Yupeng Zhang^#^{1

2}, Haoyu Zhu^#^{1

2}, Tingliang Cao³, Longhui Zhang⁴, Yuzhou Chang^{1

2}, Shikai Liang⁵, Chao Ma⁵, Fei Liang⁶, Yuqi Song^{1

2}, Jiarui Zhang^{1

2}, Changxuan Li⁷, Chuhan Jiang^{1

2}

Affiliations

¹ Department of Neurosurgery, Beijing Neurosurgical Institute (Y.Z., H.Z., Y.C., Y.S., J.Z., C.J.), Capital Medical University, China.
² Department of Neurosurgery, Beijing Tiantan Hospital (Y.Z., H.Z., Y.C., Y.S., J.Z., C.J.), Capital Medical University, China.
³ Department of Neurosurgery, Kaifeng Central Hospital, Henan, China (T.C.).
⁴ Department of Neurology, Beijing Tiantan Hospital (L.Z.), Capital Medical University, China.
⁵ Department of Neurosurgery, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University, China (S.L., C.M.).
⁶ Department of Interventional Radiology and Vascular Surgery, Peking University Third Hospital, Beijing, China (F.L.).
⁷ Department of Neurosurgery, The First Affiliated Hospital of Hainan Medical University, Hainan, China (C.L.).

^# Contributed equally.

PMID: 38511314
DOI: 10.1161/STROKEAHA.123.045456

Abstract

Background: Evaluating rupture risk in cerebral arteriovenous malformations currently lacks quantitative hemodynamic and angioarchitectural features necessary for predicting subsequent hemorrhage. We aimed to derive rupture-related hemodynamic and angioarchitectural features of arteriovenous malformations and construct an ensemble model for predicting subsequent hemorrhage.

Methods: This retrospective study included 3 data sets, as follows: training and test data sets comprising consecutive patients with untreated cerebral arteriovenous malformations who were admitted from January 2015 to June 2022 and a validation data set comprising patients with unruptured arteriovenous malformations who received conservative treatment between January 2009 and December 2014. We extracted rupture-related features and developed logistic regression (clinical features), decision tree (hemodynamic features), and support vector machine (angioarchitectural features) models. These 3 models were combined into an ensemble model using a weighted soft-voting strategy. The performance of the models in discriminating ruptured arteriovenous malformations and predicting subsequent hemorrhage was evaluated with confusion matrix-related metrics in the test and validation data sets.

Results: A total of 896 patients (mean±SD age, 28±14 years; 404 women) were evaluated, with 632, 158, and 106 patients in the training, test, and validation data sets, respectively. From the training set, 9 clinical, 10 hemodynamic, and 2912 pixel-based angioarchitectural features were extracted. A logistic regression model was built using 4 selected clinical features (age, nidus size, location, and venous aneurysm), whereas a decision-tree model was constructed from 4 hemodynamic features (outflow time, stasis index, cerebral blood flow, and outflow volume ratio). A support vector machine model was designed using 5 pixel-based angioarchitectural features. In the validation data set, the accuracy, sensitivity, specificity, and area under the curve of the ensemble model for predicting subsequent hemorrhages were 0.840, 0.889, 0.823, and 0.911, respectively.

Conclusions: The ensemble model incorporating clinical, hemodynamic, and angioarchitectural features showed favorable performance in predicting subsequent hemorrhage of cerebral arteriovenous malformations.

Keywords: angioarchitecture; arteriovenous malformation; hemodynamics; hemorrhage; radiomics.