Effect of atrial fibrillation on endovascular thrombectomy for acute ischemic stroke. A meta-analysis of individual patient data from six randomised trials: Results from the HERMES collaboration

Background

Atrial fibrillation is an important risk factor for ischemic stroke, and is associated with an increased risk of poor outcome after ischemic stroke. Endovascular thrombectomy is safe and effective in acute ischemic stroke patients with large vessel occlusion of the anterior circulation. This meta-analysis aims to investigate whether there is an interaction between atrial fibrillation and treatment effect of endovascular thrombectomy, and secondarily whether atrial fibrillation is associated with worse outcome in patients with ischemic stroke due to large vessel occlusion.

Methods

Individual patient data were from six of the recent randomised clinical trials (MR CLEAN, EXTEND-IA, REVASCAT, SWIFT PRIME, ESCAPE, PISTE) in which endovascular thrombectomy plus standard care was compared to standard care alone. Primary outcome measure was the shift on the modified Rankin scale (mRS) at 90 days. Secondary outcomes were functional independence (mRS 0–2) at 90 days, National Institutes of Health Stroke Scale score at 24 h, symptomatic intracranial hemorrhage and mortality at 90 days. The primary effect parameter was the adjusted common odds ratio, estimated with ordinal logistic regression (shift analysis); treatment effect modification of atrial fibrillation was assessed with a multiplicative interaction term.

Results

Among 1351 patients, 447 patients had atrial fibrillation, 224 of whom were treated with endovascular thrombectomy. We found no interaction of atrial fibrillation with treatment effect of endovascular thrombectomy for both primary (p-value for interaction: 0.58) and secondary outcomes. Regardless of treatment allocation, we found no difference in primary outcome (mRS at 90 days: aOR 1.11 (95% CI 0.89–1.38) and secondary outcomes between patients with and without atrial fibrillation.

Conclusion

We found no interaction of atrial fibrillation on treatment effect of endovascular thrombectomy, and no difference in outcome between large vessel occlusion stroke patients with and without atrial fibrillation.

Data-efficient deep learning of radiological image data for outcome prediction after endovascular treatment of patients with acute ischemic stroke

Treatment selection is becoming increasingly more important in acute ischemic stroke patient care. Clinical variables and radiological image biomarkers (old age, pre-stroke mRS, NIHSS, occlusion location, ASPECTS, among others) have an important role in treatment selection and prognosis. Radiological biomarkers require expert annotation and are subject to inter-observer variability. Recently, Deep Learning has been introduced to reproduce these radiological image biomarkers. Instead of reproducing these biomarkers, in this work, we investigated Deep Learning techniques for building models to directly predict good reperfusion after endovascular treatment (EVT) and good functional outcome using CT angiography images. These models do not require image annotation and are fast to compute. We compare the Deep Learning models to Machine Learning models using traditional radiological image biomarkers. We explored Residual Neural Network (ResNet) architectures, adapted them with Structured Receptive Fields (RFNN) and auto-encoders (AE) for network weight initialization. We further included model visualization techniques to provide insight into the network's decision-making process. We applied the methods on the MR CLEAN Registry dataset with 1301 patients. The Deep Learning models outperformed the models using traditional radiological image biomarkers in three out of four cross-validation folds for functional outcome (average AUC of 0.71) and for all folds for reperfusion (average AUC of 0.65). Model visualization showed that the arteries were relevant features for functional outcome prediction. The best results were obtained for the ResNet models with RFNN. Auto-encoder initialization often improved the results. We concluded that, in our dataset, automated image analysis with Deep Learning methods outperforms radiological image biomarkers for stroke outcome prediction and has the potential to improve treatment selection.