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

Nick M. Murray, Mathias Unberath, Gregory Hager, Ferdinand Hui

Research output: Contribution to journalReview article

Abstract

Background and purpose: Acute 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. Methods: A 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. Results: Variations 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). Conclusions: AI may improve LVO stroke detection and rapid triage necessary for expedited treatment. Standardization of performance assessment is needed in future studies.

Original languageEnglish (US)
JournalJournal of neurointerventional surgery
DOIs
StateAccepted/In press - Jan 1 2019

Fingerprint

Artificial Intelligence
Stroke
Learning
Thrombectomy
Alberta
Software
Triage
Emergency Treatment
Validation Studies
PubMed
Therapeutics
Perfusion
Machine Learning
Morbidity

Keywords

  • artificial intelligence
  • ischemic stroke diagnosis
  • large vessel occlusion detection
  • machine learning

ASJC Scopus subject areas

  • Surgery
  • Clinical Neurology

Cite this

@article{cf88e2bca72242d9bc25e817ac0fe124,
title = "Artificial intelligence to diagnose ischemic stroke and identify large vessel occlusions: A systematic review",
abstract = "Background and purpose: Acute 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. Methods: A 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. Results: Variations 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). Conclusions: AI may improve LVO stroke detection and rapid triage necessary for expedited treatment. Standardization of performance assessment is needed in future studies.",
keywords = "artificial intelligence, ischemic stroke diagnosis, large vessel occlusion detection, machine learning",
author = "Murray, {Nick M.} and Mathias Unberath and Gregory Hager and Ferdinand Hui",
year = "2019",
month = "1",
day = "1",
doi = "10.1136/neurintsurg-2019-015135",
language = "English (US)",
journal = "Journal of NeuroInterventional Surgery",
issn = "1759-8478",
publisher = "BMJ Publishing Group",

}

TY - JOUR

T1 - Artificial intelligence to diagnose ischemic stroke and identify large vessel occlusions

T2 - A systematic review

AU - Murray, Nick M.

AU - Unberath, Mathias

AU - Hager, Gregory

AU - Hui, Ferdinand

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Background and purpose: Acute 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. Methods: A 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. Results: Variations 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). Conclusions: AI may improve LVO stroke detection and rapid triage necessary for expedited treatment. Standardization of performance assessment is needed in future studies.

AB - Background and purpose: Acute 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. Methods: A 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. Results: Variations 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). Conclusions: AI may improve LVO stroke detection and rapid triage necessary for expedited treatment. Standardization of performance assessment is needed in future studies.

KW - artificial intelligence

KW - ischemic stroke diagnosis

KW - large vessel occlusion detection

KW - machine learning

UR - http://www.scopus.com/inward/record.url?scp=85073161182&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073161182&partnerID=8YFLogxK

U2 - 10.1136/neurintsurg-2019-015135

DO - 10.1136/neurintsurg-2019-015135

M3 - Review article

C2 - 31594798

AN - SCOPUS:85073161182

JO - Journal of NeuroInterventional Surgery

JF - Journal of NeuroInterventional Surgery

SN - 1759-8478

ER -