Background: Accurate prediction of clinical outcome is of utmost importance for choices regarding the endovascular treatment (EVT) of acute stroke. Recent studies on the prediction modeling for... Show moreBackground: Accurate prediction of clinical outcome is of utmost importance for choices regarding the endovascular treatment (EVT) of acute stroke. Recent studies on the prediction modeling for stroke focused mostly on clinical characteristics and radiological scores available at baseline. Radiological images are composed of millions of voxels, and a lot of information can be lost when representing this information by a single value. Therefore, in this study we aimed at developing prediction models that take into account the whole imaging data combined with clinical data available at baseline. Methods: We included 3,279 patients from the MR CLEAN Registry; a prospective, observational, multicenter registry of patients with ischemic stroke treated with EVT. We developed two approaches to combine the imaging data with the clinical data. The first approach was based on radiomics features, extracted from 70 atlas regions combined with the clinical data to train machine learning models. For the second approach, we trained 3D deep learning models using the whole images and the clinical data. Models trained with the clinical data only were compared with models trained with the combination of clinical and image data. Finally, we explored feature importance plots for the best models and identified many known variables and image features/brain regions that were relevant in the model decision process. Results: From 3,279 patients included, 1,241 (37%) patients had a good functional outcome [modified Rankin Scale (mRS) <= 2] and 1,954 (60%) patients had good reperfusion [modified Thrombolysis in Cerebral Infarction (eTICI) >= 2b]. There was no significant improvement by combining the image data to the clinical data for mRS prediction [mean area under the receiver operating characteristic (ROC) curve (AUC) of 0.81 vs. 0.80] above using the clinical data only, regardless of the approach used. Regarding predicting reperfusion, there was a significant improvement when image and clinical features were combined (mean AUC of 0.54 vs. 0.61), with the highest AUC obtained by the deep learning approach. Conclusions: The combination of radiomics and deep learning image features with clinical data significantly improved the prediction of good reperfusion. The visualization of prediction feature importance showed both known and novel clinical and imaging features with predictive values. Show less
Despite the large overall beneficial effects of endovascular treatment in patients with acute ischemic stroke, severe disability or death still occurs in almost one-third of patients. These... Show moreDespite the large overall beneficial effects of endovascular treatment in patients with acute ischemic stroke, severe disability or death still occurs in almost one-third of patients. These patients, who might not benefit from treatment, have been previously identified with traditional logistic regression models, which may oversimplify relations between characteristics and outcome, or machine learning techniques, which may be difficult to interpret. We developed and evaluated a novel evolutionary algorithm for fuzzy decision trees to accurately identify patients with poor outcome after endovascular treatment, which was defined as having a modified Rankin Scale score (mRS) higher or equal to 5. The created decision trees have the benefit of being comprehensible, easily interpretable models, making its predictions easy to explain to patients and practitioners. Insights in the reason for the predicted outcome can encourage acceptance and adaptation in practice and help manage expectations after treatment. We compared our proposed method to CART, the benchmark decision tree algorithm, on classification accuracy and interpretability. The fuzzy decision tree significantly outperformed CART: using 5-fold cross-validation with on average 1090 patients in the training set and 273 patients in the test set, the fuzzy decision tree misclassified on average 77 (standard deviation of 7) patients compared to 83 (+/- 7) using CART. The mean number of nodes (decision and leaf nodes) in the fuzzy decision tree was 11 (+/- 2) compared to 26 (+/- 1) for CART decision trees. With an average accuracy of 72% and much fewer nodes than CART, the developed evolutionary algorithm for fuzzy decision trees might be used to gain insights into the predictive value of patient characteristics and can contribute to the development of more accurate medical outcome prediction methods with improved clarity for practitioners and patients. Show less
Ramos, L.A.; Kappelhof, M.; Os, H.J.A. van; Chalos, V.; Kranendonk, K. van; Kruyt, N.D.; ... ; Marquering, H.A. 2020
Background: Although endovascular treatment (EVT) has greatly improved outcomes in acute ischemic stroke, still one third of patients die or remain severely disabled after stroke. If we could... Show moreBackground: Although endovascular treatment (EVT) has greatly improved outcomes in acute ischemic stroke, still one third of patients die or remain severely disabled after stroke. If we could select patients with poor clinical outcome despite EVT, we could prevent futile treatment, avoid treatment complications, and further improve stroke care. We aimed to determine the accuracy of poor functional outcome prediction, defined as 90-day modified Rankin Scale (mRS) score >= 5, despite EVT treatment.Methods: We included 1,526 patients from the MR CLEAN Registry, a prospective, observational, multicenter registry of ischemic stroke patients treated with EVT. We developed machine learning prediction models using all variables available at baseline before treatment. We optimized the models for both maximizing the area under the curve (AUC), reducing the number of false positives.Results: From 1,526 patients included, 480 (31%) of patients showed poor outcome. The highest AUC was 0.81 for random forest. The highest area under the precision recall curve was 0.69 for the support vector machine. The highest achieved specificity was 95% with a sensitivity of 34% for neural networks, indicating that all models contained false positives in their predictions. From 921 mRS 0-4 patients, 27-61 (3-6%) were incorrectly classified as poor outcome. From 480 poor outcome patients in the registry, 99-163 (21-34%) were correctly identified by the models.Conclusions: All prediction models showed a high AUC. The best-performing models correctly identified 34% of the poor outcome patients at a cost of misclassifying 4% of non-poor outcome patients. Further studies are necessary to determine whether these accuracies are reproducible before implementation in clinical practice. Show less
BackgroundThe Thrombolysis in Cerebral Infarction (TICI) scale is an important outcome measure to evaluate the quality of endovascular stroke therapy. The TICI scale is ordinal and observer... Show moreBackgroundThe Thrombolysis in Cerebral Infarction (TICI) scale is an important outcome measure to evaluate the quality of endovascular stroke therapy. The TICI scale is ordinal and observer-dependent, which may result in suboptimal prediction of patient outcome and inconsistent reperfusion grading.AimsWe present a semi-automated quantitative reperfusion measure (quantified TICI (qTICI)) using image processing techniques based on the TICI methodology.MethodsWe included patients with an intracranial proximal large vessel occlusion with complete, good quality runs of anteroposterior and lateral digital subtraction angiography from the MR CLEAN Registry. For each vessel occlusion, we identified the target downstream territory and automatically segmented the reperfused area in the target downstream territory on final digital subtraction angiography. qTICI was defined as the percentage of reperfused area in target downstream territory. The value of qTICI and extended TICI (eTICI) in predicting favorable functional outcome (modified Rankin Scale 0-2) was compared using area under receiver operating characteristics curve and binary logistic regression analysis unadjusted and adjusted for known prognostic factors.ResultsIn total, 408 patients with M1 or internal carotid artery occlusion were included. The median qTICI was 78 (interquartile range 58-88) and 215 patients (53%) had an eTICI of 2C or higher. qTICI was comparable to eTICI in predicting favorable outcome with area under receiver operating characteristics curve of 0.63 vs. 0.62 (P = 0.8) and 0.87 vs. 0.86 (P = 0.87), for the unadjusted and adjusted analysis, respectively. In the adjusted regression analyses, both qTICI and eTICI were independently associated with functional outcome.ConclusionqTICI provides a quantitative measure of reperfusion with similar prognostic value for functional outcome to eTICI score. Show less
