No abstract

Background and purpose Endovascular thrombectomy is an evidence‐based treatment for large vessel occlusion (LVO) stroke. Commercially available artificial intelligence has been designed to detect the presence of an LVO on computed tomography angiogram (CTA). We compared Viz.ai‐LVO (San Francisco, CA, USA) to CTA interpretation by board‐certified neuroradiologists (NRs) in a large, integrated stroke network. Methods From January 2021 to December 2021, we compared Viz.ai detection of an internal carotid artery (ICA) or middle cerebral artery first segment (MCA‐M1) occlusion to the gold standard of CTA interpretation by board‐certified NRs for all code stroke CTAs. On a monthly basis, sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) were calculated. Trend analyses were conducted to evaluate for any improvement of LVO detection by the software over time. Results 3851 patients met study inclusion criteria, of whom 220 (5.7%) had an ICA or MCA‐M1 occlusion per NR. Sensitivity and specificity were 78.2% (95% CI 72%–83%) and 97% (95% CI 96%–98%), respectively. PPV was 61% (95% CI 55%–67%), NPV 99% (95% CI 98%–99%), and accuracy was 95.9% (95% CI 95.3%–96.5%). Neither specificity or sensitivity improved over time in the trend analysis. Conclusions Viz.ai‐LVO has high specificity and moderately high sensitivity to detect an ICA or proximal MCA occlusion. The software has the potential to streamline code stroke workflows and may be particularly impactful when emergency access to NRs or vascular neurologists is limited.

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.

No abstract

No abstract