Real-world evaluation of Brainomix e-Stroke software

Background and purpose Brainomix e-Stroke is an artificial intelligence-based decision support tool that aids the interpretation of CT imaging in the context of acute stroke. While e-Stroke has the potential to improve the speed and accuracy of diagnosis, real-world validation is essential. The aim...

Full description

Saved in:
Bibliographic Details
Main Authors: Tarek Yousry, Robert Simister, Cillian McNamara, Matthew Fallon, Jack Garnham, Peter Cowley, Dermot Mallon, Chak Lam Ip, Eirini Blana, Arathi Menon, David Doig
Format: Article
Language:English
Published: BMJ Publishing Group
Series:Stroke and Vascular Neurology
Online Access:https://svn.bmj.com/content/early/2023/12/22/svn-2023-002859.full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846172062017650688
author Tarek Yousry
Robert Simister
Cillian McNamara
Matthew Fallon
Jack Garnham
Peter Cowley
Dermot Mallon
Chak Lam Ip
Eirini Blana
Arathi Menon
David Doig
author_facet Tarek Yousry
Robert Simister
Cillian McNamara
Matthew Fallon
Jack Garnham
Peter Cowley
Dermot Mallon
Chak Lam Ip
Eirini Blana
Arathi Menon
David Doig
author_sort Tarek Yousry
collection DOAJ
description Background and purpose Brainomix e-Stroke is an artificial intelligence-based decision support tool that aids the interpretation of CT imaging in the context of acute stroke. While e-Stroke has the potential to improve the speed and accuracy of diagnosis, real-world validation is essential. The aim of this study was to prospectively evaluate the performance of Brainomix e-Stroke in an unselected cohort of patients with suspected acute ischaemic stroke.Methods The study cohort included all patients admitted to the University College London Hospital Hyperacute Stroke Unit between October 2021 and April 2022. For e-ASPECTS and e-CTA, the ground truth was determined by a neuroradiologist with access to all clinical and imaging data. For e-CTP, the values of the core infarct and ischaemic penumbra were compared with those derived from syngo.via, an alternate software used at our institution.Results 1163 studies were performed in 551 patients admitted during the study period. Of these, 1130 (97.2%) were successfully processed by e-Stroke in an average of 4 min. For identifying acute middle cerebral artery territory ischaemia, e-ASPECTS had an accuracy of 77.0% and was more specific (83.5%) than sensitive (58.6%). The accuracy for identifying hyperdense thrombus was lower (69.1%), which was mainly due to many false positives (positive predictive value of 22.9%). Identification of acute haemorrhage was highly accurate (97.8%) with a sensitivity of 100% and a specificity of 97.6%; false positives were typically caused by areas of calcification. The accuracy of e-CTA for large vessel occlusions was 91.5%. The core infarct and ischaemic penumbra volumes provided by e-CTP strongly correlated with those provided by syngo.via (ρ=0.804—0.979).Conclusion Brainomix e-Stroke software provides rapid and reliable analysis of CT imaging in the acute stroke setting although, in line with the manufacturer’s guidance, it should be used as an adjunct to expert interpretation rather than a standalone decision-making tool.
format Article
id doaj-art-cae6c6bd1f8c442b9dafaf7189ff19a7
institution Kabale University
issn 2059-8696
language English
publisher BMJ Publishing Group
record_format Article
series Stroke and Vascular Neurology
spelling doaj-art-cae6c6bd1f8c442b9dafaf7189ff19a72024-11-10T12:20:08ZengBMJ Publishing GroupStroke and Vascular Neurology2059-869610.1136/svn-2023-002859Real-world evaluation of Brainomix e-Stroke softwareTarek Yousry0Robert Simister1Cillian McNamara2Matthew Fallon3Jack Garnham4Peter Cowley5Dermot Mallon6Chak Lam Ip7Eirini Blana8Arathi Menon9David Doig107 Lysholm Department of Neuroradiology, University College London Hospitals NHS Foundation Trust National Hospital for Neurology and Neurosurgery, London, UK2 UCL Queen Square Institute of Neurology, London, UKDepartment of Neuroradiology, Imperial College Healthcare NHS Trust, London, UKNeuroradiology, St George`s University Hospitals NHS Foundation Trust, London, UK1 Lysholm Department of Neuroradiology, National Hospital for Neurology and Neurosurgery, University College London Hospitals NHS Foundation Trust, London, UKNational Hospital for Neurology and Neurosurgery, London, UKDepartment of Neuroradiology, Imperial College Healthcare NHS Trust, London, UKNHS Lothian, Edinburgh, UKLysholm Department of Neuroradiology, National Hospital for Neurology and Neurosurgery, University College London Hospitals NHS Foundation Trust, London, UKLysholm Department of Neuroradiology, National Hospital for Neurology and Neurosurgery, University College London Hospitals NHS Foundation Trust, London, UKLysholm Department of Neuroradiology, National Hospital for Neurology and Neurosurgery, University College London Hospitals NHS Foundation Trust, London, UKBackground and purpose Brainomix e-Stroke is an artificial intelligence-based decision support tool that aids the interpretation of CT imaging in the context of acute stroke. While e-Stroke has the potential to improve the speed and accuracy of diagnosis, real-world validation is essential. The aim of this study was to prospectively evaluate the performance of Brainomix e-Stroke in an unselected cohort of patients with suspected acute ischaemic stroke.Methods The study cohort included all patients admitted to the University College London Hospital Hyperacute Stroke Unit between October 2021 and April 2022. For e-ASPECTS and e-CTA, the ground truth was determined by a neuroradiologist with access to all clinical and imaging data. For e-CTP, the values of the core infarct and ischaemic penumbra were compared with those derived from syngo.via, an alternate software used at our institution.Results 1163 studies were performed in 551 patients admitted during the study period. Of these, 1130 (97.2%) were successfully processed by e-Stroke in an average of 4 min. For identifying acute middle cerebral artery territory ischaemia, e-ASPECTS had an accuracy of 77.0% and was more specific (83.5%) than sensitive (58.6%). The accuracy for identifying hyperdense thrombus was lower (69.1%), which was mainly due to many false positives (positive predictive value of 22.9%). Identification of acute haemorrhage was highly accurate (97.8%) with a sensitivity of 100% and a specificity of 97.6%; false positives were typically caused by areas of calcification. The accuracy of e-CTA for large vessel occlusions was 91.5%. The core infarct and ischaemic penumbra volumes provided by e-CTP strongly correlated with those provided by syngo.via (ρ=0.804—0.979).Conclusion Brainomix e-Stroke software provides rapid and reliable analysis of CT imaging in the acute stroke setting although, in line with the manufacturer’s guidance, it should be used as an adjunct to expert interpretation rather than a standalone decision-making tool.https://svn.bmj.com/content/early/2023/12/22/svn-2023-002859.full
spellingShingle Tarek Yousry
Robert Simister
Cillian McNamara
Matthew Fallon
Jack Garnham
Peter Cowley
Dermot Mallon
Chak Lam Ip
Eirini Blana
Arathi Menon
David Doig
Real-world evaluation of Brainomix e-Stroke software
Stroke and Vascular Neurology
title Real-world evaluation of Brainomix e-Stroke software
title_full Real-world evaluation of Brainomix e-Stroke software
title_fullStr Real-world evaluation of Brainomix e-Stroke software
title_full_unstemmed Real-world evaluation of Brainomix e-Stroke software
title_short Real-world evaluation of Brainomix e-Stroke software
title_sort real world evaluation of brainomix e stroke software
url https://svn.bmj.com/content/early/2023/12/22/svn-2023-002859.full
work_keys_str_mv AT tarekyousry realworldevaluationofbrainomixestrokesoftware
AT robertsimister realworldevaluationofbrainomixestrokesoftware
AT cillianmcnamara realworldevaluationofbrainomixestrokesoftware
AT matthewfallon realworldevaluationofbrainomixestrokesoftware
AT jackgarnham realworldevaluationofbrainomixestrokesoftware
AT petercowley realworldevaluationofbrainomixestrokesoftware
AT dermotmallon realworldevaluationofbrainomixestrokesoftware
AT chaklamip realworldevaluationofbrainomixestrokesoftware
AT eiriniblana realworldevaluationofbrainomixestrokesoftware
AT arathimenon realworldevaluationofbrainomixestrokesoftware
AT daviddoig realworldevaluationofbrainomixestrokesoftware