Dataset Information

Predicting Poor Outcome Before Endovascular Treatment in Patients With Acute Ischemic Stroke.

ABSTRACT: 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 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.

SUBMITTER: Ramos LA

PROVIDER: S-EPMC7593486 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting Poor Outcome Before Endovascular Treatment in Patients With Acute Ischemic Stroke.

Ramos Lucas A LA Kappelhof Manon M van Os Hendrikus J A HJA Chalos Vicky V Van Kranendonk Katinka K Kruyt Nyika D ND Roos Yvo B W E M YBWEM van der Lugt Aad A van Zwam Wim H WH van der Schaaf Irene C IC Zwinderman Aeilko H AH Strijkers Gustav J GJ van Walderveen Marianne A A MAA Wermer Mariekke J H MJH Olabarriaga Silvia D SD Majoie Charles B L M CBLM Marquering Henk A HA

Frontiers in neurology 20201015

<b>Background:</b> 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 trea ...[more]

PMID: 33178123

Similar Datasets

Project description:Background: Endovascular treatment (EVT) is effective for stroke patients with a large vessel occlusion (LVO) of the anterior circulation. To further improve personalized stroke care, it is essential to accurately predict outcome after EVT. Machine learning might outperform classical prediction methods as it is capable of addressing complex interactions and non-linear relations between variables. Methods: We included patients from the Multicenter Randomized Clinical Trial of Endovascular Treatment for Acute Ischemic Stroke in the Netherlands (MR CLEAN) Registry, an observational cohort of LVO patients treated with EVT. We applied the following machine learning algorithms: Random Forests, Support Vector Machine, Neural Network, and Super Learner and compared their predictive value with classic logistic regression models using various variable selection methodologies. Outcome variables were good reperfusion (post-mTICI ? 2b) and functional independence (modified Rankin Scale ?2) at 3 months using (1) only baseline variables and (2) baseline and treatment variables. Area under the ROC-curves (AUC) and difference of mean AUC between the models were assessed. Results: We included 1,383 EVT patients, with good reperfusion in 531 (38%) and functional independence in 525 (38%) patients. Machine learning and logistic regression models all performed poorly in predicting good reperfusion (range mean AUC: 0.53-0.57), and moderately in predicting 3-months functional independence (range mean AUC: 0.77-0.79) using only baseline variables. All models performed well in predicting 3-months functional independence using both baseline and treatment variables (range mean AUC: 0.88-0.91) with a negligible difference of mean AUC (0.01; 95%CI: 0.00-0.01) between best performing machine learning algorithm (Random Forests) and best performing logistic regression model (based on prior knowledge). Conclusion: In patients with LVO machine learning algorithms did not outperform logistic regression models in predicting reperfusion and 3-months functional independence after endovascular treatment. For all models at time of admission radiological outcome was more difficult to predict than clinical outcome.

Project description:Background and Purpose- We determined the effect of sex on outcome after endovascular stroke thrombectomy in acute ischemic stroke, including lifelong disability outcomes. Methods- We analyzed patients treated with the Solitaire stent retriever in the combined SWIFT (Solitaire FR With the Intention for Thrombectomy), STAR (Solitaire FR Thrombectomy for Acute Revascularization), and SWIFT PRIME (Solitaire FR With the Intention for Thrombectomy as Primary Endovascular Treatment) cohorts. Ordinal and logistic regression were used to examine known factors influencing outcome after endovascular stroke thrombectomy and study the effect of sex on the association between these factors and outcomes, including age and time to reperfusion. Years of optimal life after thrombectomy were defined as disability-adjusted life years and calculated by projecting disability through adjusted poststroke life expectancy by sex. Results- Among 389 patients treated with endovascular stroke thrombectomy, 55% were females, and median National Institutes of Health Stroke Scale was 17 (interquartile range, 8-28). There were no differences between females versus males in presenting deficit severity (National Institutes of Health Stroke Scale score, 17 versus 17, P=0.21), occlusion location (69% versus 64% M1, P=0.62), presenting infarct extent (Alberta Stroke Program Early CT Score 8 versus 8, P=0.24), rate of substantial reperfusion (Thrombolysis in Cerebral Infarction 2b/3, 87% versus 83%, P=0.37), onset to reperfusion time (294 versus 302 minutes, P=0.46). Despite older ages (69 versus 64, P<0.001) and higher rate of atrial fibrillation (45% versus 30%, P=0.002) for females compared with males, adjusted rates of functional independence at 90 days were similar (odds ratio, 1.0; 95% CI, 0.6-1.6). After adjusting for age at presentation and stroke severity, females had more years of optimal life (disability-adjusted life year) after endovascular stroke thrombectomy, 10.6 versus 8.5 years (P<0.001). Conclusions- Despite greater age and higher rate of atrial fibrillation, females experienced comparable functional outcomes and greater years of optimal life after intervention compared with males.

Project description:Background Patients aged ≥90 were excluded or under-represented in past thrombectomy trials; thus, uncertainty remains whether treatment benefits can be expected regardless of age. This study investigates outcome and safety of thrombectomy in nonagenarians to improve decision making in a real-world setting. Methods and Results All currently available data of patients aged ≥90 enrolled in the GSR-ET (German Stroke Registry-Endovascular Treatment) were combined with a smaller cohort from 3 tertiary stroke centers. Baseline characteristics, procedural (Thrombolysis in Cerebral Infarction scale) and functional outcomes (modified Rankin Scale; mRS), as well as complications (symptomatic intracranial hemorrhage, serious adverse events; SAEs) were analyzed. Good functional outcome was defined as mRS ≤3 at 90-days. 203 patients with anterior circulation stroke and prestroke mRS ≤3 were included. The rate of successful recanalization (Thrombolysis in Cerebral Infarction scale ≥2b) was 75.9% (154/203). Good functional outcome (mRS ≤3) was observed in 21.6% (41 of 193) at 90-days. In-hospital mortality was 27.1% (55 of 203) and increased significantly at 90 days to 48.9% (93 of 190; P<0.001). Symptomatic intracranial hemorrhage occurred in 3% (6 of 203) of patients. Logistic regression analysis identified Alberta Stroke Program Early CT Score (adjusted odds ratio, 1.93; 95% CI, 1.01-3.70; P=0.046) and initial National Institute of Health Stroke Scale (adjusted odds ratio, 0.85; 95% CI, 0.76-0.97; P=0.014) as independent predictors for good outcome. Patients with successful recanalization had a significant (P=0.001) shift of mRS distribution with higher rates of good functional outcomes (23.8% [34 of 143] versus 14.9% [7 of 47]) and lower mortality at 90-days (46.8% [67 of 143] versus 55.3% [26 of 47]). Conclusions Despite high mortality and less frequent favorable outcome, our data suggest that thrombectomy is still effective and safe for nonagenarians. Decision making for thrombectomy in patients aged ≥90 should be based on a case-by-case basis with regard to initial National Institute of Health Stroke Scale and Alberta Stroke Program Early CT Score.

Project description:The impact of reperfusion therapies on cognition has been poorly explored and little knowledge exists. We explored the influence of endovascular treatment (EVT) on cognitive outcome in patients with anterior circulation ischemic stroke. Patients presenting with ischemic stroke due to anterior large vessel occlusion who underwent intravenous thrombolysis (IVT) alone or EVT plus IVT were recruited. Cognitive abilities were evaluated at 6 months from stroke through a neuropsychological test battery. A total of 88 patients with a mean age of 66.3 ± 12.9 years were included, of which 38 treated with IVT alone and 50 with IVT plus EVT. Compared to patients treated with IVT alone, patients who received EVT plus IVT performed significantly better at the neuropsychological tests exploring executive functions, attention, abstract reasoning, visuospatial ability, visual and verbal and memory. At multivariable regression analysis, the EVT was independently associated with the 6-month cognitive performance after the adjustment for age, sex, admission National Institutes of Health Stroke Scale score, systolic blood pressure, glucose level, Alberta Stroke Program Early CT score, side of stroke, site of occlusion, and Back Depression Inventory score [Stroop Test Word Reading: adjβ = 13.99, 95% confidence interval (CI) 8.47-19.50, p < 0.001; Stroop Test Colour Naming: adjβ = 6.63, 95% CI 2.46-10.81, p = 0.002; Trail Making Test-A: adjβ = - 92.98, 95% CI - 153.76 to - 32.20, p = 0.003; Trail Making Test-B: adjβ = - 181.12, 95% CI - 266.09 to - 96.15; p < 0.001; Digit Span Test Forward: adjβ = 1.44, 95% CI 0.77-2.10, p < 0.001; Digit Span Test Backward: adjβ = 1.10, 95% CI 0.42-1.77, p = 0.002; Coloured Progressive Matrices: adjβ = 5.82, 95% CI 2.71-8.93, p < 0.001; Rey Complex Figure Test-Copy: adjβ = 6.02, 95% CI 2.74-9.30, p < 0.001; Rey Complex Figure Test-Immediate recall: adjβ = 6.00, 95% CI 2.34-9.66, p = 0.002; Rey Complex Figure Test-Delayed recall: adjβ = 5.73, 95% CI 1.95-9.51, p = 0.003; Rey Auditory Verbal Learning Test-Immediate recall: adjβ = 12.60, 95% CI 6.69-18.52, p < 0.001; Rey Auditory Verbal Learning Test-Delayed recall: adjβ = 1.85, 95% CI 0.24-3.45, p = 0.025]. Patients treated with EVT plus IVT had better cognitive performance than patients treated with IVT alone at 6 months from anterior circulation ischemic stroke.

Dataset Information

Predicting Poor Outcome Before Endovascular Treatment in Patients With Acute Ischemic Stroke.

Publications

Predicting Poor Outcome Before Endovascular Treatment in Patients With Acute Ischemic Stroke.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets