Purpose: This study aimed to investigate the accuracy and clinical significance of an artificial intelligence (AI)-based automated Alberta Stroke Program Early Computed Tomography (ASPECT) scoring software of head CT for the indication of intravenous recombinant tissue plasminogen activator (rt-PA) therapy. Methods: This study included two populations of acute ischemic stroke: one comprised patients who had undergone head CT within 48 h of presentation (Population #1, n = 448), while the other included patients within 4.5 h from onset (Population #2, n = 132). The primary endpoint was the concordance rate of ASPECTS of the neurologists and AI software against the benchmark score. The secondary endpoints were to validate the accuracy of the neurologist and AI software in assessing the ability to rule out extensive infarction (ASPECTS of 0–5) in population #2. Results: The reading accuracy of AI software was comparable to that of the board-certified vascular neurologists. The detection rate of cardiogenic cerebral embolism was better than that of atherothrombotic cerebral infarction. By excluding extensive infarction, AI-software showed a higher specificity and equivalent sensitivity compared to those of experts. Conclusions: The AI software for ASPECTS showed convincing agreement with expert evaluation and would be supportive in determining the indications of intravenous rt-PA therapy.

Purpose: Endovascular therapy (EVT) preceded by intravenous thrombolysis with recombinant tissue plasminogen activator (iv-rtPA) has been established as a standard treatment in patients with stroke caused by large-vessel occlusion (LVO). Primary stroke centers without EVT competence need to identify patients with residual LVO after iv-rtPA therapy and transport them to an EVT-capable facility. Carotid ultrasonography (CUS) is easily applicable at bed side and useful for detecting extra- and intracranial LVO. This study aimed to determine whether CUS findings at admission are useful to predict patients with residual LVO after iv-rtPA. Methods: Patients scheduled to undergo iv-rtPA for acute cerebral infarction were registered. Before iv-rtPA, they underwent CUS, followed by CTA or MRA evaluation within 6 h after iv-rtPA. A model that can achieve 100% sensitivity for detecting residual LVO after iv-rtPA was studied. Results: This study included 68 of 116 patients treated with iv-rtPA during the study period. National Institutes of Health Stroke Scale (NIHSS) score (cutoff value = 10) on arrival, hyperdense MCA sign on non-contrast CT, end-diastolic (ED) ratio on CUS, and eye deviation were significantly different between patients with residual LVO after iv-rtPA and those without. If any of these clinical features are positive in the screening test, residual LVO could be predicted with 100% sensitivity, 50% specificity, 64% positive predictive value, and 100% negative predictive value. Conclusion: Prediction of residual LVO with 100% sensitivity may be feasible by adding CUS to NIHSS score > 10, the presence of eye deviation, and hyperdense MCA sign.