Validation of the Charlotte large artery occlusion endovascular therapy outcome score using Viz.ai-derived cerebral blood volume index

Abstract

Background The Charlotte large artery occlusion endovascular therapy outcome score (CLEOS) predicts poor 90-day outcomes for patients presenting with internal carotid artery (ICA) or middle cerebral artery (MCA) occlusions. It incorporates RAPID-derived cerebral blood volume (CBV) index, a marker of collateral circulation. We validated the predictive ability of CLEOS with Viz.ai-processed computed tomography perfusion (CTP) imaging. Methods The original CLEOS derivation cohort was compared to a validation cohort consisting of all ICA and MCA thrombectomy patients treated at a large health system with Viz.ai-processed CTP. Rates of poor 90-day outcome (mRS 4–6) were compared in the derivation and validation cohorts, stratified by CLEOS. CLEOS was compared to previously described prediction models using area under the curve (AUC) analyses. Calibration of CLEOS was performed to compare predicted risk of poor outcomes with observed outcomes. Results One-hundred eighty-one patients (mean age 66.4 years, median NIHSS 16) in the validation cohort were included. The validation cohort had higher median CTP core volumes (24 vs 8 ml) and smaller median mismatch volumes (81 vs 101 ml) than the derivation cohort. CLEOS-predicted poor outcomes strongly correlated with observed outcomes ( R2 = 0.82). AUC for CLEOS in the validation cohort (0.72, 95% CI 0.64–0.80) was similar to the derivation cohort (AUC 0.75, 95% CI 0.70–0.80) and was comparable or superior to previously described prognostic models. Conclusions CLEOS can predict risk of poor 90-day outcomes in ICA and MCA thrombectomy patients evaluated with pre-intervention, Viz.ai-processed CTP.