Automated detection of intracranial large vessel occlusions using Viz.ai software: Experience in a large, integrated stroke network

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.

A Telestroke Nurse and Neuroradiologist Model for Extended Window Code Stroke Triage

“…Unfortunately, the sensitivity of such software is suboptimal compared with that of a neuroradiologist. 24,25 Furthermore, the involvement of a neuroradiology physician helps to alleviate any concern regarding TSRNs operating outside their scope of practice. Alternatively, a pragmatic issue with our workflow concerns emerging data suggesting that the time window for systemic thrombolysis may be extended beyond the approved 4.5 hours from the LKW window based on diffusionweighted imaging-fluid-attenuated inversion recovery mismatch on magnetic resonance imaging (MRI).…”

“…A more reasonable question is whether the role of our neuroradiologists could be supplanted by machine learning or artificial intelligence software's ability to accurately diagnose the presence of an LVO. Unfortunately, the sensitivity of such software is suboptimal compared with that of a neuroradiologist 24,25. Furthermore, the involvement of a neuroradiology physician helps to alleviate any concern regarding TSRNs operating outside their scope of practice.…”

AI-support for the detection of intracranial large vessel occlusions: One-year prospective evaluation

“…Most of the missed LVOs by the AI-tool included the M2 vessels, which are also more difficult to detect by radiologists. Most other commercially available AI-tools currently on the market do not (yet) detect M2 occlusions [ 18 , 19 ]. Another reason the users may have experienced limited added value is because of their (unconscious) misinterpretation of the intended use.…”

Role of artificial intelligence and machine learning in the diagnosis of cerebrovascular disease

“…Consequently, rapid detection of LVO is of paramount importance in the initial workup of any stroke. AI has shown tremendous potential in this sphere, leading to the development of commercially available programs, such as and Rapid CTA and Viz.ai-LVO, that have reasonably high sensitivity and specificity (Murray et al, 2020;Karamchandani et al, 2023). Some recent work has even demonstrated a role for AI in detecting LVO using CTAs obtained in mobile stroke units (MSUs) (Czap et al, 2022).…”