Diagnostic Value of Artificial Intelligence—Based Software in Detection of Large Vessel Occlusion in Acute Ischemic Stroke

Background: Aim of the study was to test the accuracy of AI-based software for detection of large vessel occlusion (LVO) with computed tomography angiography (CTA) in stroke patients using an experienced neuroradiologist’s evaluation as the reference. Methods: Consecutive patients who underwent mult...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Marcin Sawicki, Krzysztof Safranow, Lidia Wiska, Igor Pasek, Aleksandra Gajdziel, Michał Gruszewski, Wojciech Poncyljusz
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
T
Acceso en línea:https://doaj.org/article/36598c86816640139dc0318af5722f3f
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:36598c86816640139dc0318af5722f3f
record_format dspace
spelling oai:doaj.org-article:36598c86816640139dc0318af5722f3f2021-11-11T15:06:03ZDiagnostic Value of Artificial Intelligence—Based Software in Detection of Large Vessel Occlusion in Acute Ischemic Stroke10.3390/app1121100172076-3417https://doaj.org/article/36598c86816640139dc0318af5722f3f2021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10017https://doaj.org/toc/2076-3417Background: Aim of the study was to test the accuracy of AI-based software for detection of large vessel occlusion (LVO) with computed tomography angiography (CTA) in stroke patients using an experienced neuroradiologist’s evaluation as the reference. Methods: Consecutive patients who underwent multimodal brain CT for suspected acute ischemic stroke were retrospectively identified. The presence and site (classified as proximal and distal) of LVO were assessed in CTA by an experienced neuroradiologist as a reference and compared to readings of three medical students and AI-based software, the e-CTA. Results: One-hundred-eight participants with a mean age of 70 years (±12.6); 55 (50.9%) females were included. Neuroradiologist found LVO in 70 (64.8%) cases: 45 (41.7%) proximal, and 25 (23.1%) distal. The overall sensitivity for e-CTA was 0.67 (95%CI 0.55–0.78); 0.84 (95%CI 0.71–0.94) for proximal, and 0.36 (95%CI 0.18–0.57) for distal LVOs. Overall specificity and accuracy for e-CTA were 0.95 (95%CI 0.82–0.99) and 0.77 (95%CI 0.68–0.84), respectively. The student’s performance was similar to e-CTA. Conclusions: The tested software’s performance is acceptable for the detection of proximal LVOs, while it appears to be not accurate enough for distal LVOs.Marcin SawickiKrzysztof SafranowLidia WiskaIgor PasekAleksandra GajdzielMichał GruszewskiWojciech PoncyljuszMDPI AGarticleartificial intelligencecerebral angiographyspiral computed tomographyacute strokecerebrovascular occlusionTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10017, p 10017 (2021)
institution DOAJ
collection DOAJ
language EN
topic artificial intelligence
cerebral angiography
spiral computed tomography
acute stroke
cerebrovascular occlusion
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
spellingShingle artificial intelligence
cerebral angiography
spiral computed tomography
acute stroke
cerebrovascular occlusion
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
Marcin Sawicki
Krzysztof Safranow
Lidia Wiska
Igor Pasek
Aleksandra Gajdziel
Michał Gruszewski
Wojciech Poncyljusz
Diagnostic Value of Artificial Intelligence—Based Software in Detection of Large Vessel Occlusion in Acute Ischemic Stroke
description Background: Aim of the study was to test the accuracy of AI-based software for detection of large vessel occlusion (LVO) with computed tomography angiography (CTA) in stroke patients using an experienced neuroradiologist’s evaluation as the reference. Methods: Consecutive patients who underwent multimodal brain CT for suspected acute ischemic stroke were retrospectively identified. The presence and site (classified as proximal and distal) of LVO were assessed in CTA by an experienced neuroradiologist as a reference and compared to readings of three medical students and AI-based software, the e-CTA. Results: One-hundred-eight participants with a mean age of 70 years (±12.6); 55 (50.9%) females were included. Neuroradiologist found LVO in 70 (64.8%) cases: 45 (41.7%) proximal, and 25 (23.1%) distal. The overall sensitivity for e-CTA was 0.67 (95%CI 0.55–0.78); 0.84 (95%CI 0.71–0.94) for proximal, and 0.36 (95%CI 0.18–0.57) for distal LVOs. Overall specificity and accuracy for e-CTA were 0.95 (95%CI 0.82–0.99) and 0.77 (95%CI 0.68–0.84), respectively. The student’s performance was similar to e-CTA. Conclusions: The tested software’s performance is acceptable for the detection of proximal LVOs, while it appears to be not accurate enough for distal LVOs.
format article
author Marcin Sawicki
Krzysztof Safranow
Lidia Wiska
Igor Pasek
Aleksandra Gajdziel
Michał Gruszewski
Wojciech Poncyljusz
author_facet Marcin Sawicki
Krzysztof Safranow
Lidia Wiska
Igor Pasek
Aleksandra Gajdziel
Michał Gruszewski
Wojciech Poncyljusz
author_sort Marcin Sawicki
title Diagnostic Value of Artificial Intelligence—Based Software in Detection of Large Vessel Occlusion in Acute Ischemic Stroke
title_short Diagnostic Value of Artificial Intelligence—Based Software in Detection of Large Vessel Occlusion in Acute Ischemic Stroke
title_full Diagnostic Value of Artificial Intelligence—Based Software in Detection of Large Vessel Occlusion in Acute Ischemic Stroke
title_fullStr Diagnostic Value of Artificial Intelligence—Based Software in Detection of Large Vessel Occlusion in Acute Ischemic Stroke
title_full_unstemmed Diagnostic Value of Artificial Intelligence—Based Software in Detection of Large Vessel Occlusion in Acute Ischemic Stroke
title_sort diagnostic value of artificial intelligence—based software in detection of large vessel occlusion in acute ischemic stroke
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/36598c86816640139dc0318af5722f3f
work_keys_str_mv AT marcinsawicki diagnosticvalueofartificialintelligencebasedsoftwareindetectionoflargevesselocclusioninacuteischemicstroke
AT krzysztofsafranow diagnosticvalueofartificialintelligencebasedsoftwareindetectionoflargevesselocclusioninacuteischemicstroke
AT lidiawiska diagnosticvalueofartificialintelligencebasedsoftwareindetectionoflargevesselocclusioninacuteischemicstroke
AT igorpasek diagnosticvalueofartificialintelligencebasedsoftwareindetectionoflargevesselocclusioninacuteischemicstroke
AT aleksandragajdziel diagnosticvalueofartificialintelligencebasedsoftwareindetectionoflargevesselocclusioninacuteischemicstroke
AT michałgruszewski diagnosticvalueofartificialintelligencebasedsoftwareindetectionoflargevesselocclusioninacuteischemicstroke
AT wojciechponcyljusz diagnosticvalueofartificialintelligencebasedsoftwareindetectionoflargevesselocclusioninacuteischemicstroke
_version_ 1718437122638086144