Nikhil Paliwal, Prakhar Jaiswal, Vincent M. Tutino, Hussain Shallwani, Jason M. Davies, Adnan H. Siddiqui, Rahul Rai and Hui Meng
Flow diverters (FDs) are designed to occlude intracranial aneurysms (IAs) while preserving flow to essential arteries. Incomplete occlusion exposes patients to risks of thromboembolic complications and rupture. A priori assessment of FD treatment outcome could enable treatment optimization leading to better outcomes. To that end, the authors applied image-based computational analysis to clinically FD-treated aneurysms to extract information regarding morphology, pre- and post-treatment hemodynamics, and FD-device characteristics and then used these parameters to train machine learning algorithms to predict 6-month clinical outcomes after FD treatment.
Data were retrospectively collected for 84 FD-treated sidewall aneurysms in 80 patients. Based on 6-month angiographic outcomes, IAs were classified as occluded (n = 63) or residual (incomplete occlusion, n = 21). For each case, the authors modeled FD deployment using a fast virtual stenting algorithm and hemodynamics using image-based computational fluid dynamics. Sixteen morphological, hemodynamic, and FD-based parameters were calculated for each aneurysm. Aneurysms were randomly assigned to a training or testing cohort in approximately a 3:1 ratio. The Student t-test and Mann-Whitney U-test were performed on data from the training cohort to identify significant parameters distinguishing the occluded from residual groups. Predictive models were trained using 4 types of supervised machine learning algorithms: logistic regression (LR), support vector machine (SVM; linear and Gaussian kernels), K-nearest neighbor, and neural network (NN). In the testing cohort, the authors compared outcome prediction by each model trained using all parameters versus only the significant parameters.
The training cohort (n = 64) consisted of 48 occluded and 16 residual aneurysms and the testing cohort (n = 20) consisted of 15 occluded and 5 residual aneurysms. Significance tests yielded 2 morphological (ostium ratio and neck ratio) and 3 hemodynamic (pre-treatment inflow rate, post-treatment inflow rate, and post-treatment aneurysm averaged velocity) discriminants between the occluded (good-outcome) and the residual (bad-outcome) group. In both training and testing, all the models trained using all 16 parameters performed better than all the models trained using only the 5 significant parameters. Among the all-parameter models, NN (AUC = 0.967) performed the best during training, followed by LR and linear SVM (AUC = 0.941 and 0.914, respectively). During testing, NN and Gaussian-SVM models had the highest accuracy (90%) in predicting occlusion outcome.
NN and Gaussian-SVM models incorporating all 16 morphological, hemodynamic, and FD-related parameters predicted 6-month occlusion outcome of FD treatment with 90% accuracy. More robust models using the computational workflow and machine learning could be trained on larger patient databases toward clinical use in patient-specific treatment planning and optimization.
Leonardo Rangel-Castilla, Gary B. Rajah, Hakeem J. Shakir, Hussain Shallwani, Sirin Gandhi, Jason M. Davies, Kenneth V. Snyder, Elad I. Levy and Adnan H. Siddiqui
Acute tandem occlusions of the cervical internal carotid artery and an intracranial large vessel present treatment challenges. Controversy exists regarding which lesion should be addressed first. The authors sought to evaluate the endovascular approach for revascularization of these lesions at Gates Vascular Institute.
The authors performed a retrospective review of a prospectively maintained, single-institution database. They analyzed demographic, procedural, radiological, and clinical outcome data for patients who underwent endovascular treatment for tandem occlusions. A modified Rankin Scale (mRS) score ≤ 2 was defined as a favorable clinical outcome.
Forty-five patients were identified for inclusion in the study. The average age of these patients was 64 years; the mean National Institutes of Health Stroke Scale score at presentation was 14.4. Fifteen patients received intravenous thrombolysis before undergoing endovascular treatment. Thirty-seven (82%) of the 45 proximal cervical internal carotid artery occlusions were atherothrombotic in nature. Thirty-eight patients underwent a proximal-to-distal approach with carotid artery stenting first, followed by intracranial thrombectomy, whereas 7 patients underwent a distal-to-proximal approach (that is, intracranial thrombectomy was performed first). Thirty-seven (82%) procedures were completed with local anesthesia. For intracranial thrombectomy procedures, aspiration alone was used in 15 cases, stent retrieval alone was used in 5, and a combination of aspiration and stent-retriever thrombectomy was used in the remaining 25. The average time to revascularization was 81 minutes. Successful recanalization (thrombolysis in cerebral infarction Grade 2b/3) was achieved in 39 (87%) patients. Mean National Institutes of Health Stroke Scale scores were 9.3 immediately postprocedure (p < 0.05) (n = 31), 5.1 at discharge (p < 0.05) (n = 31), and 3.6 at 3 months (p < 0.05) (n = 30). There were 5 in-hospital deaths (11%); and 2 patients (4.4%) had symptomatic intracranial hemorrhage within 24 hours postprocedure. Favorable outcomes (mRS score ≤ 2) were achieved at 3 months in 22 (73.3%) of 30 patients available for follow-up, with an mRS score of 3 for 7 of 30 (23%) patients.
Tandem occlusions present treatment challenges, but high recanalization rates were possible in the present series using acute carotid artery stenting and mechanical thrombectomy concurrently. Proximal-to-distal and aspiration approaches were most commonly used because they were safe, efficacious, and feasible. Further study in the setting of a randomized controlled trial is needed to determine the best sequence for the treatment approach and the best technology for tandem occlusion.