Development of a Novel Statistical Model for Predicting Clinical Outcomes in Stroke Patients With Tandem Occlusions After Endovascular Therapy

Background: Tandem occlusions are intracranial large vessel occlusions (LVOs) with a concomitant ipsilateral extracranial internal carotid artery occlusion and can cause more severe stroke symptoms. Aim: To develop a simple, rigorously cross -validated novel tool to predict clinical outcomes following tandem occlusion in patients with acute LVO stroke, based on data that are easily available to clinicians. To have used machine learning approaches to utilize the available information from clinical and angiographic data to make predictive models able to distinguish between mortality versus survival and good (modified Rankin Scale (mRS) <= 2) versus unfavorable neurological outcomes (mRs >= 3) Materials and methods: Retrospective data from 87 consecutive patients with anterior circulation stroke and tandem occlusions who underwent mechanical thrombectomy and stenting between December 2009 and January 2020 were analyzed. Patients were stratified into three groups based on the location of their LVO, and these groups were compared using statistical tests. Predictive models were built and cross -validated 1000 times to estimate their predictive power, measured by accuracy and area under the receiver operating curve (AUROC). Results: For distinguishing good outcome (mRS <= 2) versus poor outcome (mRS >= 3), the model comprised age, initial National Institute of Health Stroke Scale (NIHSS) score, Alberta Stroke Program Early CT Score (ASPECTS), NIHSS at 24 hours, NIHSS at discharge and intracranial haemorrhage and yielded an accuracy of 83% and the AUROC of 0.91. For mortality prediction, the model comprised age, initial NIHSS, intravenous thrombolysis, NIHSS at 24 hours and NIHSS at discharge and yielded an accuracy of 91% and an AUROC of 0.94. Conclusions: Models developed exhibit strong predictive performance and can distinguish between both the instances of survival versus mortality and good versus poor outcome with an aim to support clinicians in deciding on optimal management for these complex patients. The developed model will help identify those at risk of poorer outcomes and the prospective better selection of patients with acute ischaemic large vessel stroke secondary to tandem occlusions.