6 December 2021 in Stroke
Background: Prehospital automated large vessel occlusion (LVO) detection in Mobile Stroke Units (MSUs) could accelerate identification and treatment of patients with LVO acute ischemic stroke. Here, we evaluate the performance of a machine learning (ML) model on CT angiograms (CTAs) obtained from 2 MSUs to detect LVO. Methods: Patients evaluated on MSUs in Houston and Los Angeles with out-of-hospital CTAs were identified. Anterior circulation LVO was defined as an occlusion of the intracranial internal carotid artery, middle cerebral artery (M1 or M2), or anterior cerebral artery vessels and determined by an expert human reader. A ML model to detect LVO was trained and tested on independent data sets consisting of in-hospital CTAs and then tested on MSU CTA images. Model performance was determined using area under the receiver-operator curve statistics. Results: Among 68 patients with out-of-hospital MSU CTAs, 40% had an LVO. The most common occlusion location was the middle cerebral artery M1 segment (59%), followed by the internal carotid artery (30%), and middle cerebral artery M2 (11%). Median time from last known well to CTA imaging was 88.0 (interquartile range, 59.5–196.0) minutes. After training on 870 in-hospital CTAs, the ML model performed well in identifying LVO in a separate in-hospital data set of 441 images with area under receiver-operator curve of 0.84 (95% CI, 0.80–0.87). ML algorithm analysis time was under 1 minute. The performance of the ML model on the MSU CTA images was comparable with area under receiver-operator curve 0.80 (95% CI, 0.71–0.89). There was no significant difference in performance between the Houston and Los Angeles MSU CTA cohorts. Conclusions: In this study of patients evaluated on MSUs in 2 cities, a ML algorithm was able to accurately and rapidly detect LVO using prehospital CTA acquisitions.
1 February 2023 in Stroke
FGfor the BEST-MSU Study Group
for the BEST-MSU Study Group
+8
Background: Treatment of patients with acute ischemic stroke on mobile stroke units (MSUs) improves outcomes compared with management by standard emergency medical services ambulances and is associated with more patients treated with intravenous tPA (tissue-type plasminogen activator) in the first golden hour after last known normal. We explored the predictors and outcomes of first-hour treatment (FHT) compared with later treatment in an alternating-week cluster-controlled trial of MSUs. Methods: We analyzed all patients treated with intravenous tPA in the BEST-MSU Study (Benefits of Stroke Treatment Delivered by a Mobile Stroke Unit Compared to Standard Management by Emergency Medical Services). After stratifying by treatment timeframe, we identified factors associated with FHT. We performed adjusted analyses of the association between FHT and clinical outcome and modeled the shape of the relationship between last known normal–to–treatment time and excellent outcome. Results: Among 941 tPA-treated patients, 206 (21.8%) had lytic started within 60 minutes. Treatment on the MSU, older age, male sex, alert by 911, faster arrival on-scene and imaging, more severe stroke, atrial fibrillation, and absence of heart failure and pretreatment antihypertensive treatment were associated with FHT. Compared with later treatment, FHT was associated with higher adjusted odds ratio for 90-day modified Rankin Scale score of 0 to 1 (odds ratio, 1.87 [95% CI, 1.25–2.84]; P =0.003). Among FHT patients, 68% achieved a 90-day modified Rankin Scale of 0 or 1 or returned to their baseline status. FHT was not associated with higher risk of hemorrhage and was associated with reduced risk of treating neurovascular mimics. Conclusions: FHT almost doubles the odds of excellent clinical outcome without increased risk compared with later treatment, which supports the use of MSUs.
5 July 2023 in International Journal of Stroke
Background: Few data exist on acute stroke treatment in patients with pre-existing disability (PD) since they are usually excluded from clinical trials. A recent trial of mobile stroke units (MSUs) demonstrated faster treatment and improved outcomes, and included PD patients. Aim: To determine outcomes with tissue plasminogen activator (tPA), and benefit of MSU versus management by emergency medical services (EMS), for PD patients. Methods: Primary outcomes were utility-weighted modified Rankin Scale (uw-mRS). Linear and logistic regression models compared outcomes in patients with versus without PD, and PD patients treated by MSU versus standard management by EMS. Time metrics, safety, quality of life, and health-care utilization were compared. Results: Of the 1047 tPA-eligible ischemic stroke patients, 254 were with PD (baseline mRS 2–5) and 793 were without PD (baseline mRS 0–1). Although PD patients had worse 90-day uw-mRS, higher mortality, more health-care utilization, and worse quality of life than non-disabled patients, 53% returned to at least their baseline mRS, those treated faster had better outcome, and there was no increased bleeding risk. Comparing PD patients treated by MSU versus EMS, 90-day uw-mRS was 0.42 versus 0.36 (p = 0.07) and 57% versus 46% returned to at least their baseline mRS. There was no interaction between disability status and MSU versus EMS group assignment (p = 0.67) for 90-day uw-mRS. Conclusion: PD did not prevent the benefit of faster treatment with tPA in the BEST-MSU study. Our data support inclusion of PD patients in the MSU management paradigm.