Search results
Found 21095 matches for
Early identification of high-risk TIA or minor stroke using artificial neural network
Background and purpose: The risk of recurrent stroke following a transient ischemic attack (TIA) or minor stroke is high, despite of a significant reduction in the past decade. In this study, we investigated the feasibility of using artificial neural network (ANN) for risk stratification of TIA or minor stroke patients. Methods: Consecutive patients with acute TIA or minor ischemic stroke presenting at a tertiary hospital during a two-year period were recruited. We collected demographics, clinical and imaging data at baseline. The primary outcome was recurrent ischemic stroke within 1 year. We developed ANN models to predict the primary outcome. We randomly down-sampled patients without a primary outcome to 1:1 match with those with a primary outcome to mitigate data imbalance. We used a 5-fold cross-validation approach to train and test the ANN models to avoid overfitting. We employed 19 independent variables at baseline as the input neurons in the ANN models, using a learning algorithm based on backpropagation to minimize the loss function. We obtained the sensitivity, specificity, accuracy and the c statistic of each ANN model from the 5 rounds of cross-validation and compared that of support vector machine (SVM) and Naïve Bayes classifier in risk stratification of the patients. Results: A total of 451 acute TIA or minor stroke patients were enrolled. Forty (8.9%) patients had a recurrent ischemic stroke within 1 year. Another 40 patients were randomly selected from those with no recurrent stroke, so that data from 80 patients in total were used for 5 rounds of training and testing of ANN models. The median sensitivity, specificity, accuracy and c statistic of the ANN models to predict recurrent stroke at 1 year was 75%, 75%, 75% and 0.77, respectively. ANN model outperformed SVM and Naïve Bayes classifier in our dataset for predicting relapse after TIA or minor stroke. Conclusion: This pilot study indicated that ANN may yield a novel and effective method in risk stratification of TIA and minor stroke. Further studies are warranted for verification and improvement of the current ANN model.
Guidelines for evaluation and management of cerebral collateral circulation in ischaemic stroke 2017
<jats:p>Collateral circulation plays a vital role in sustaining blood flow to the ischaemic areas in acute, subacute or chronic phases after an ischaemic stroke or transient ischaemic attack. Good collateral circulation has shown protective effects towards a favourable functional outcome and a lower risk of recurrence in stroke attributed to different aetiologies or undergoing medical or endovascular treatment. Over the past decade, the importance of collateral circulation has attracted more attention and is becoming a hot spot for research. However, the diversity in imaging methods and criteria to evaluate collateral circulation has hindered comparisons of findings from different cohorts and further studies in exploring the clinical relevance of collateral circulation and possible methods to enhance collateral flow. The statement is aimed to update currently available evidence and provide evidence-based recommendations regarding grading methods for collateral circulation, its significance in patients with stroke and methods under investigation to improve collateral flow.</jats:p>
Impact of side branches on the computation of fractional flow in intracranial arterial stenosis using the computational fluid dynamics method
BACKGROUND: Computational fluid dynamics (CFD) allows noninvasive fractional flow (FF) computation in intracranial arterial stenosis. Removal of small artery branches is necessary in CFD simulation. The consequent effects on FF value needs to be judged. METHODS: An idealized vascular model was built with 70% focal luminal stenosis. A branch with one third or one half of the radius of the parent vessel was added at a distance of 5, 10, 15 and 20 mm to the lesion. With pressure and flow rate applied as inlet and outlet boundary conditions, CFD simulations were performed. Flow distribution at bifurcations followed Murray's law. By including or removing side branches, five patient-specific intracranial artery models were simulated. Transient simulation was performed on a patient-specific model, with a larger branch for validation. Branching effect was considered trivial if the FF difference between paired models (branches included or removed) was within 5%. RESULTS: Compared with the control model without a branch, in all idealized models the relative differences of FF was within 2%. In five pairs of cerebral arteries (branches included/removed), FFs were 0.876 and 0.877, 0.853 and 0.858, 0.874 and 0.869, 0.865 and 0.858, 0.952 and 0.948. The relative difference in each pair was less than 1%. In transient model, the relative difference of FF was 3.5%. CONCLUSION: The impact of removing side branches with radius less than 50% of the parent vessel on FF measurement accuracy is negligible in static CFD simulations, and minor in transient CFD simulation.