Abstract Details

Title Real World Experience with Viz.ai Automated Large Vessel Occlusion in CT Angiogram

Topic Cerebrovascular Disease and Interventional Neurology

Presentation(s) P8 - Poster Session 8 (11:45 AM-12:45 PM)

Poster/Presentation
Number 6-010

Objective To determine the accuracy of Viz.AI LVO at our large academic comprehensive stroke center.

Background Viz.AI LVO is an artificial-intelligence platform which analyzes brain computed tomography angiography (CTA) images in patients with suspected acute ischemic stroke (AIS) and sends an automated alert for suspected large vessel occlusions (LVO). Viz.AI reports high sensitivity and specificity (96.3% and 93.8%); we report our experience with Viz.AI LVO detection.

Design/Methods We performed a retrospective review of suspected stroke patients who had CTA ordered as a stroke code from September 2020- May 2021. Data was collected on sex, age, Viz.AI LVO alert, and CTA radiologist review (considered gold standard). True negative was defined as Viz negative, Radiology negative, False positive as Viz positive, Radiology negative, false negative as Viz negative, Radiology positive, and true positive as Viz positive, Radiology positive. LVO was defined as occlusion of the intracranial carotid (ICAT) or MCA (M1 or M2). Data collected included performance of Viz.AI LVO alert, sensitivity, specificity, positive predictive value, and negative predictive value.

Results Among 980 consecutive suspected AIS patients with CTA analyzed by Viz.AI, the mean age was 64.2 years (range 19- 99) and 531 (54.3%) were female. Viz LVO autodetection alerted for 161 patients (16.4%). Radiologist review reported 85 patients (8.7%) with LVO as follows: 33 (38.8%) M2, 36 (42.4%) M1, and 16 (18.8%) ICAT. The following were adjudicated: 805 true negatives, 90 false positives, 14 false negatives, and 71 true positives. Sensitivity was 83.5%, specificity 89.9%, PPV 44.1%, and NPV 98.3%. All 14 false negatives were M2 occlusions. The median time to alert (TTA) was 11 min (range 6- 656).

Conclusions In our series of AIS patients evaluated with CTA at an academic CSC, Viz.AI automated LVO detection performed well with a sensitivity of 83.5%, specificity of 89.9%, and a median TTA of 11 minutes.

Authors/Disclosures
Nick Mannix, MD (The Ohio State University Wexner Medical Center) PRESENTER	Dr. Mannix has nothing to disclose.
Elena Penhos, MD (University of Colorado)	Ms. Penhos has nothing to disclose.
	No disclosure on file
Mohammad Taimur Shujaat (OSU Wexner Medical Center)	No disclosure on file
Sharon Hammond-Heaton, RN (The Ohio State University Wexner Medical Center)	Ms. Hammond-Heaton has nothing to disclose.
	No disclosure on file
Vivien H. Lee, MD, FAAN (OSU Comprehensive Neurovascular Center)	Dr. Lee has nothing to disclose.

��ɫ��

��ɫ��