Search

BackgroundAmbulance-based telemedicine is an innovative strategy through which transport time can be used to rapidly and accurately triage stroke patients (i.e., mobile telestroke). The acute phase of stroke is a time-sensitive emergency, and delays in care during this phase worsen outcomes. In this literature review, we analyzed studies that investigated the feasibility and reliability of ambulance based telestroke.MethodsWe followed PRISMA guidelines to perform a keyword-based search of PubMed, Web of Science, CINHAL, and Academic Search Complete databases. We reviewed references of search-identified articles to screen for additional articles. Articles for inclusion were selected according to author consensus in consideration of the studies' investigation of feasibility, reliability, or validity of ambulance-based telestroke.ResultsWe identified 67 articles for secondary screening from which 19 articles were selected for full text review. The selected studies reported diverse methods of development, implementation, and assessment of ambulance-based telestroke systems. Although the methods and results varied among these studies, most concluded that the implementation of ambulance based telestroke is feasible.ConclusionThis topical review suggests that ambulance based telestroke is a feasible method for enhanced prehospital stroke care in a variety of settings. Further prospective research is needed to assess the real-world challenges and to identify additional strategies that bolster rapid and accurate prehospital assessment of acute stroke patients.

Abstract Background Mixed data exist regarding the association between hyperglycemia and functional outcome after acute ischemic stroke when accounting for the impact of leptomeningeal collateral flow. We sought to determine whether collateral status modifies the association between treatment group and functional outcome in a subset of patients with large vessel occlusion enrolled in the Stroke Hyperglycemia Insulin Network Effort (SHINE) trial. Methods In this post-hoc analysis, we analyzed patients enrolled into the SHINE trial with anterior circulation large vessel occlusion who underwent imaging with CT angiography prior to glucose control treatment group assignment. The primary analysis assessed the degree to which collateral status modified the effect between treatment group and functional outcome as defined by the 90-day modified Rankin Scale score. Logistic regression was used to model the data, with adjustments made for thrombectomy status, age, post-perfusion thrombolysis in cerebral infarction (TICI) score, tissue plasminogen activator (tPA) use, and baseline National Institutes of Health Stroke Scale (NIHSS) score. Five SHINE trial centers contributed data for this analysis. Statistical significance was defined as a p-value

BackgroundCurrent EMS stroke screening tools facilitate early detection and triage, but the tools' accuracy and reliability are limited and highly variable. An automated stroke screening tool could improve stroke outcomes by facilitating more accurate prehospital diagnosis and delivery. We hypothesize that a machine learning algorithm using video analysis can detect common signs of stroke. As a proof-of-concept study, we trained a computer algorithm to detect presence and laterality of facial weakness in publically available videos with comparable accuracy, sensitivity, and specificity to paramedics.Methods and ResultsWe curated videos of people with unilateral facial weakness (n = 93) and with a normal smile (n = 96) from publicly available web-based sources. Three board certified vascular neurologists categorized the videos according to the presence or absence of weakness and laterality. Three paramedics independently analyzed each video with a mean accuracy, sensitivity and specificity of 92.6% [95% CI 90.1–94.7%], 87.8% [95% CI 83.9–91.7%] and 99.3% [95% CI 98.2–100%]. Using a 5-fold cross validation scheme, we trained a computer vision algorithm to analyze the same videos producing an accuracy, sensitivity and specificity of 88.9% [95% CI 83.5–93%], 90.3% [95% CI 82.4–95.5%] and 87.5 [95% CI 79.2–93.4%].ConclusionsThese preliminary results suggest that a machine learning algorithm using computer vision analysis can detect unilateral facial weakness in pre-recorded videos with an accuracy and sensitivity comparable to trained paramedics. Further research is warranted to pursue the concept of augmented facial weakness detection and external validation of this algorithm in independent data sets and prospective patient encounters.