Objective: The purpose of this study was to test e-ASPECTS software in stroke patients. Marketed as a decision-support tool, e-ASPECTS may detect ischemia or hemorrhage on computed tomography (CT) imaging and quantify ischemic extent using the Alberta Stroke Program Early CT Score (ASPECTS).

Methods: Using CT scans from nine stroke studies, we compared the software with masked experts. Following software indications, we assessed e-ASPECTS results in patients with/without middle cerebral artery (MCA) ischemia but no other stroke cause. To simulate a representative "front door" hospital population, we enriched the dataset with non-MCA ischemia, hemorrhage, and mimics. With final diagnosis as the reference standard, we tested e-ASPECTS diagnostic accuracy for detecting ischemic features, hyperattenuated arteries, and hemorrhage.

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 diagnoses were ischemia (78%), hemorrhage (14%), or mimic (8%). From 3,035 CTs with expert-rated ASPECTS, most (2,084/3,035, 69%) e-ASPECTS results were within one point of expert ratings. In the representative population, e-ASPECTS diagnostic accuracy was 71% (95% confidence interval [CI] = 70–72%) for ischemic features and 85% (83–86%) for hemorrhage. The software identified more false positives for ischemia (12% vs. 2%) and hemorrhage (14% vs. <1%) than experts.

Conclusions: On independent testing, e-ASPECTS showed moderate agreement with experts but overcalled stroke features. Future prospective trials are needed to evaluate the impact of artificial intelligence (AI) software on patient care and outcomes before widespread implementation of stroke decision-support software.