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 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 4min.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.

Utility of current thrombophilia screening in young patients with stroke and TIA

Introduction Approximately 40%of strokes in young adults are cryptogenic.The diagnostic yield of thrombophilia screening remains controversial.We aimed to determine utility of current thrombophilia testing for young patients with stroke and transient ischaemic attack(TIA).Methods We present a retrospective review of all patients with stroke and TIA≤60 years presenting to University College London Hospital stroke unit and daily TIA clinic from 1 January 2015 to 1 August 2016.Consecutive clinical records and thrombophilia tests,including factor V Leiden(FVL),prothrombin G20210A mutation(PGM),antiphospholipid antibody(APA),and protein S,C and antithrombin(AT)levels,were reviewed.results The mean age of 628 patients with stroke and TIA was 49.1 years(SD 9.2).Thrombophilia testing was performed in 360(57%)patients,including 171 with stroke and 189 with TIA.Positive tests were found in 50(14%)patients,of whom 24 patients were<50 years.Positive results were found in 36(10%)with acute ischaemic stroke,4(1%)with haemorrhagic stroke and 10(3%)with TIA.Thirteen patients(4%)had homozygous/heterozygous FVL or PGM,and 27(7.5%)had positive APA(anticardiolipin antibody,anti-β2 glycoprotein antibody or lupus anticoagulant).Of 27(7.5%)patients with protein C,S or AT deficiency,10(2.8%)had primary deficiency,presumed hereditary with other secondary causes excluded.9%of patients with protein C,S or AT and 27%with APA were followed by confirmatory testing.Conclusion Thrombophilia testing was positive in only 14%of cases overall.Thrombophilia mutations and protein C,S or AT abnormalities were found rarely and were very uncommon in patients with TIA.Follow-up of abnormal results was generally poor for all groups,which further limited the impact of the thrombophilia testing policy.