• Yuan Zhang, Tingting Zheng, Hao Wang, Jie Zhu, Shaofeng Duan, and Bin Song.
• Department of Radiology, Minhang Hospital, Fudan University, Shanghai, China.
• World Neurosurg. 2024 Oct 28.

BackgroundEndovascular thrombectomy (EVT) is recommended for acute ischemic stroke (AIS) due to large-vessel occlusion. However, approximately 50% of patients still face poor outcomes post-procedure. This study aimed to assess whether a nomogram model that integrates CT angiography radiomics features and clinical variables can predict EVT outcomes in AIS patients.Methods159 EVT patients were randomly divided into training and validation groups at a 7:3 ratio. A modified Rankin Scale (mRS) ≤ 2 at 90 days indicated a favorable outcome. We used univariate and multivariate logistic regression to identify analytic and radiomic predictors and create predictive models. Model performance was evaluated using the AUC, Hosmer-Lemeshow test, and decision curve analysis for discrimination, calibration, and clinical utility.ResultsA 19-feature radiomic signature reached an AUC of 0.79. Combining it with age, baseline NIHSS, diabetes, and statin use raised the clinical-radiomics nomogram's AUC to 0.85. Both decision curve and calibration curve analyses showed strong performance.ConclusionCombining radiomics nomogram with clinical predictors could effectively forecast EVT outcomes in acute anterior circulation large vessel occlusion stroke patients.Copyright © 2024 The Author(s). Published by Elsevier Inc. All rights reserved.

5 keywords...

hide…