Pre-hospital detection of acute ischemic stroke secondary to emergent large vessel occlusion: lessons learned from electrocardiogram and acute myocardial infarction

217

163

Background and purposeAcute stroke caused by large vessel occlusions (LVOs) requires emergent detection and treatment by endovascular thrombectomy. However, radiologic LVO detection and treatment is subject to variable delays and human expertise, resulting in morbidity. Imaging software using artificial intelligence (AI) and machine learning (ML), a branch of AI, may improve rapid frontline detection of LVO strokes. This report is a systematic review of AI in acute LVO stroke identification and triage, and characterizes LVO detection software.MethodsA systematic review of acute stroke diagnostic-focused AI studies from January 2014 to February 2019 in PubMed, Medline, and Embase using terms: ‘artificial intelligence’ or ‘machine learning or deep learning’ and ‘ischemic stroke’ or ‘large vessel occlusion’ was performed.ResultsVariations of AI, including ML methods of random forest learning (RFL) and convolutional neural networks (CNNs), are used to detect LVO strokes. Twenty studies were identified that use ML. Alberta Stroke Program Early CT Score (ASPECTS) commonly used RFL, while LVO detection typically used CNNs. Image feature detection had greater sensitivity with CNN than with RFL, 85% versus 68%. However, AI algorithm performance metrics use different standards, precluding ideal objective comparison. Four current software platforms incorporate ML: Brainomix (greatest validation of AI for ASPECTS, uses CNNs to automatically detect LVOs), General Electric, iSchemaView (largest number of perfusion study validations for thrombectomy), and Viz.ai (uses CNNs to automatically detect LVOs, then automatically activates emergency stroke treatment systems).ConclusionsAI may improve LVO stroke detection and rapid triage necessary for expedited treatment. Standardization of performance assessment is needed in future studies.

Section: Introduction: Ischemic Stroke and Artificial Intelligencementioning

confidence: 99%

Artificial intelligence to diagnose ischemic stroke and identify large vessel occlusions: a systematic review

Murray

Unberath

Hager

et al. 2019

217

163

“…Prehospital stroke severity scales may aid in identifying patients with AIS with suspected LVOs13; however, there is a paucity of data on the long-term implementation of prehospital LVO scales in a ’real-world' setting 14 15. The Rapid Arterial oCclusion Evaluation (RACE) Scale is one of the few prehospital scales that have been prospectively validated in the field, and has been recently revalidated in a large cohort in Catalonia 16 17.…”

Section: Introductionmentioning

confidence: 99%

Long-term implementation of a prehospital severity scale for EMS triage of acute stroke: a real-world experience

Jumaa

Castonguay

Salahuddin

et al. 2019

BackgroundData on the implementation of prehospital large vessel occlusion (LVO) scales to identify and triage patients with acute ischemic stroke (AIS) in the field are limited, with the majority of studies occurring outside the USA.ObjectiveTo report our long-term experience of a US countywide emergency medical services (EMS) acute stroke triage protocol using the Rapid Arterial oCclusion Evaluation (RACE) score.MethodsOur prospective database was used to identify all consecutive patients triaged within Lucas County, Ohio by the EMS with (1) a RACE score ≥5, taken directly to an endovascular capable center (ECC) as RACE-alerts (RA) and (2) a RACE score <5, taken to the nearest hospital as stroke-alerts (SA). Baseline demographics, RACE score, time metrics, final diagnosis, treatments, and clinical and angiographic outcomes were captured. The sensitivity and specificity for patients with a RACE score ≥5 with LVO, eligible for mechanical thrombectomy (MT), were calculated.ResultsBetween July 2015 and June 2018, 492 RA and 1147 SA were triaged within our five-hospital network. Of the RA, 37% had AIS secondary to LVOs. Of the 492 RA and 1147 SA, 125 (25.4%) and 38 (3.3%), respectively, underwent MT (OR=9.9; 95% CI 6.8 to 14.6; p<0.0001). Median times from onset-to-ECC arrival (74 vs 167 min, p=0.03) and dispatch-to-ECC arrival (31 vs 46 min, p=0.0002) were shorter in the RA-MT than in the SA-MT cohort. A RACE cut-off point ≥5 showed a sensitivity and specificity of 0.77 and 0.75 for detection of patients with LVO eligible for MT, respectively.ConclusionsWe have demonstrated the long-term feasibility of a countywide EMS-based prehospital triage protocol using the RACE Scale within our hospital network.

“…While approximately half of patients with acute myocardial infarction have ST segment elevations (STEMI), first responders using computer-assisted EKG have up to a 98.7% specificity and 92.8% sensitivity for identifying in the field these candidates for reperfusion therapy. 4 Having early diagnostics allows for earlier activation of interventional teams and subsequently more reperfusions, faster reperfusions, shorter ED triage, and shorter door-to-balloon times. 4 This clearly identified advantage and the ease of use of EKG led to widespread adoption.…”

Section: Lessons From History For Prehospital Technologiesmentioning

confidence: 99%

“…4 Having early diagnostics allows for earlier activation of interventional teams and subsequently more reperfusions, faster reperfusions, shorter ED triage, and shorter door-to-balloon times. 4 This clearly identified advantage and the ease of use of EKG led to widespread adoption. Paramedics now all receive training in STEMI identification, and currently many ambulances possess the on-board capacity of transmitting EKGs to the center they on October 2, 2020 by guest.…”

Section: Lessons From History For Prehospital Technologiesmentioning

confidence: 99%

Technological innovation for prehospital stroke triage: ripe for disruption

Martínez-Gutiérrez

Chandra

Hirsch

et al. 2019

BackgroundWith the benefit of mechanical thrombectomy firmly established, the focus has shifted to improved delivery of care. Reducing time from symptom onset to reperfusion is a primary goal. Technology promises tremendous opportunities in the prehospital space to achieve this goal.MethodsThis review explores existing, fledgling, and potential future technologies for application in the prehospital space.ResultsThe opportunity for technology to improve stroke care resides in the detection, evaluation, triage, and transport of patients to an appropriate healthcare facility. Most prehospital technology remains in the early stages of design and implementation.ConclusionThe major challenges to tackle for future improvement in prehospital stroke care are that of public awareness, emergency medical service detection, and triage, and improved systems of stroke care. Thoughtfully applied technology will transform all these areas.