External Validation of e‐ASPECTS Software for Interpreting Brain CT in Stroke

Abstract

Objective: The purpose of this study was to test e-ASPECTS software in patients with stroke. Marketed as a decisionsupport tool, e-ASPECTS may detect features of ischemia or hemorrhage on computed tomography (CT) imaging and quantify ischemic extent using Alberta Stroke Program Early CT Score (ASPECTS). Methods: Using CT from 9 stroke studies, we compared software with masked experts. As per indications for software use, we assessed e-ASPECTS results for patients with/without middle cerebral artery (MCA) ischemia but no other cause of stroke. In an analysis outside the intended use of the software, we enriched our dataset with non-MCA ischemia, hemorrhage, and mimics to simulate a representative "front door" hospital population. With final diagnosis as the reference standard, we tested the diagnostic accuracy of e-ASPECTS for identifying stroke features (ischemia, hyperattenuated arteries, and hemorrhage) in the representative population. Results: We included 4,100 patients (51% women, median age = 78 years, National Institutes of Health Stroke Scale [NIHSS] = 10, onset to scan = 2.5 hours). Final diagnosis was ischemia (78%), hemorrhage (14%), or mimic (8%). From 3,035 CTs with expert-rated ASPECTS, most (2084/3035, 69%) e-ASPECTS results were within one point of experts. In the representative population, the diagnostic accuracy of e-ASPECTS was 71% (95% confidence interval [CI] = 70-72%) for detecting ischemic features, 85% (83-86%) for hemorrhage. Software identified more false positive ischemia (12% vs 2%) and hemorrhage (14% vs <1%) than experts. Interpretation: On independent testing, e-ASPECTS provided moderate agreement with experts and overcalled stroke features. Therefore, future prospective trials testing impacts of artificial intelligence (AI) software on patient care and outcome are required before widespread implementation of stroke decision-support software.

Accuracy of artificial intelligence software for CT angiography in stroke

“…We have previously described our method for deriving a ‘real‐world’ clinically representative dataset from all patients available to RITeS 10,11 . In this analysis of e‐CTA, we: Aimed for age, sex, stroke severity and time since symptom onset similar to results provided by UK national audit (SSNAP, April 2018–March 2019, www.strokeaudit.org), and pooled randomised‐controlled trial data 1,18 .…”

“…In this analysis of e‐CTA, we: Aimed for age, sex, stroke severity and time since symptom onset similar to results provided by UK national audit (SSNAP, April 2018–March 2019, www.strokeaudit.org), and pooled randomised‐controlled trial data 1,18 . We expected RITeS patients to be within the ranges presented by the other datasets 10,11 . If necessary, we used stratified random sampling to modify the case mix. Did not exclude imaging based solely on quality, if intracranial arterial occlusion involved vessels other than the ICA‐MCA axis, or if the centrally adjudicated final diagnosis (derived using all available clinical and imaging data) was not ischemic stroke (a small number of patients were given a final diagnosis of stroke mimic). …”

“…We have previously described the RITeS (Real-world Independent Testing of e-ASPECTS Software) study, 10,11 a collaboration of up to 10 multicentre national and international acute stroke studies that recruited patients within 6 h of symptom onset. For the present analysis, we identified all patients in RITeS with CTA acquired at baseline.…”

“…1,18 We expected RITeS patients to be within the ranges presented by the other datasets. 10,11 If necessary, we used stratified random sampling to modify the case mix. 2 Did not exclude imaging based solely on quality, if intracranial arterial occlusion involved vessels other than the ICA-MCA axis, or if the centrally adjudicated final diagnosis (derived using all available clinical and imaging data) was not ischemic stroke (a small number of patients were given a final diagnosis of stroke mimic).…”

Reply to “Independent Confirmation”

“…Per our recent Annals publication 1 and pre‐specified statistical analysis plan, 2 RITeS had two co‐primary outcomes: Compare ASPECTS 3 results provided by software to those of experts, and Test the diagnostic accuracy of software for identifying imaging features of stroke. …”